drop safety/availability from scoring, holistic p4 rating, phase-parallel pipeline

safety and availability don't reduce to physics formulas the way
power_density/range_fuel/cost_efficiency do -- they're judgment calls
(risk assessment, infrastructure prevalence), and running them through the
same log-normalize() built for physical quantities produced incoherent
results: safety's raw value is already a "0-1" score, and normalizing it
again turned 0.6 into an unexplainable 0.678 that even the LLM reviewing
it could only cite, never justify (see combo 1540). Removed both from
domain_metric_weights (safety from 4 domains, availability from
urban_commuting) and renormalized the remaining weights to sum to 1.0.

Pass 4 now produces one holistic RATING (LOW/MEDIUM/HIGH) alongside the
existing VERDICT, with safety and accessibility folded in as qualitative
considerations feeding that single judgment rather than scored
separately -- not a checklist of independent numbers. New
qualitative_rating column, filterable in the results UI. Also added
domain name/description to the review prompt so the LLM judges a metric
like range against what the domain actually needs (urban_commuting:
1-50km) instead of generic real-world expectations for the platform
category -- confirmed live on a combo where phi4 had called a 396km range
"limited" by comparing to typical aircraft rather than a domain that
needs 1-50km.

Pass 2 is estimator-only now -- self.llm is never consulted there,
reserved entirely for pass 4. Restructured Pipeline.run() from combo-first
to phase-parallel: each pass now runs to completion across every combo
before the next pass starts, rather than walking each combo through all
four passes before the next combo. This surfaced a real bug: domain-
blocked combos (status stays "valid" by design, not "_fail") were
slipping past a naive status-based skip guard and getting silently
re-processed by pass 2. Fixed with a shared dead-combo check that catches
both generic failures and domain blocks correctly.

Also fixes a results-page display bug found while reviewing a live combo:
the per-metric "position" bar showed raw distance from norm_min without
inverting for lower_is_better metrics, so an excellent cost score (near
the good end) rendered as a ~0%, near-empty bar -- looked bad next to its
own 0.99 normalized score.

Validated live against phi4 (real Ollama calls, not mocked): full-domain
phase-parallel run (2,970 combos, estimator-only p2, 1.6s) followed by a
real pass-4 run (111 reviewed, 11m, 0 crashes, 0 null ratings). Two tests
that relied on the old LLM-driven pass 2 to force deterministic outcomes
were updated to test pass 4's verdict-wiring directly instead. All 100
tests pass.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

src/physcom/db/repository.py

@@ -230,24 +230,37 @@ class Repository:
         self.conn.commit()
         return row["id"]
 
-    def backfill_lower_is_better(self, domain_name: str, metric_name: str) -> None:
-        """Set lower_is_better=1 for an existing domain-metric row that still has the default 0."""
+    def sync_domain_metric_weights(self, domain: Domain) -> None:
+        """Make domain_metric_weights exactly match domain.metric_bounds on an
+        already-seeded domain: upserts weight/norm_min/norm_max/unit for every
+        currently-declared metric, and deletes any row for a metric that's been
+        removed from the domain (e.g. safety/availability dropped from the
+        scored set). Safe to call whether the domain was just freshly inserted
+        or already existed.
+        """
+        row = self.conn.execute(
+            "SELECT id FROM domains WHERE name = ?", (domain.name,)
+        ).fetchone()
+        if not row:
+            return
+        domain_id = row["id"]
+        keep_ids = []
+        for mb in domain.metric_bounds:
+            metric_id = self.ensure_metric(mb.metric_name, unit=mb.unit)
+            keep_ids.append(metric_id)
             self.conn.execute(
-            """UPDATE domain_metric_weights SET lower_is_better = 1
-               WHERE lower_is_better = 0
-                 AND domain_id = (SELECT id FROM domains WHERE name = ?)
-                 AND metric_id = (SELECT id FROM metrics WHERE name = ?)""",
-            (domain_name, metric_name),
+                """INSERT OR REPLACE INTO domain_metric_weights
+                   (domain_id, metric_id, weight, norm_min, norm_max, lower_is_better, unit)
+                   VALUES (?, ?, ?, ?, ?, ?, ?)""",
+                (domain_id, metric_id, mb.weight, mb.norm_min, mb.norm_max,
+                 int(mb.lower_is_better), mb.unit),
             )
-        self.conn.commit()
-
-    def backfill_metric_unit(self, domain_name: str, metric_name: str, unit: str) -> None:
-        """Set this domain-metric row's unit — unit is domain-scoped, not global to the metric name."""
+        if keep_ids:
+            placeholders = ",".join("?" * len(keep_ids))
             self.conn.execute(
-            """UPDATE domain_metric_weights SET unit = ?
-               WHERE domain_id = (SELECT id FROM domains WHERE name = ?)
-                 AND metric_id = (SELECT id FROM metrics WHERE name = ?)""",
-            (unit, domain_name, metric_name),
+                f"""DELETE FROM domain_metric_weights
+                    WHERE domain_id = ? AND metric_id NOT IN ({placeholders})""",
+                (domain_id, *keep_ids),
             )
         self.conn.commit()
 
@@ -593,15 +606,18 @@ class Repository:
         llm_review: str | None = None,
         human_notes: str | None = None,
         domain_block_reason: str | None = None,
+        qualitative_rating: str | None = None,
         commit: bool = True,
     ) -> None:
         self.conn.execute(
             """INSERT OR REPLACE INTO combination_results
                (combination_id, domain_id, composite_score, novelty_flag,
-                llm_review, human_notes, pass_reached, domain_block_reason)
-               VALUES (?, ?, ?, ?, ?, ?, ?, ?)""",
+                llm_review, human_notes, pass_reached, domain_block_reason,
+                qualitative_rating)
+               VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)""",
             (combo_id, domain_id, composite_score, novelty_flag,
-             llm_review, human_notes, pass_reached, domain_block_reason),
+             llm_review, human_notes, pass_reached, domain_block_reason,
+             qualitative_rating),
         )
         if commit:
             self.conn.commit()
@@ -641,6 +657,20 @@ class Repository:
             ).fetchall()
         return {r["status"]: r["cnt"] for r in rows}
 
+    def count_results_by_rating(self, domain_name: str) -> dict[str, int]:
+        """Count results by qualitative_rating (LOW/MEDIUM/HIGH) for a domain.
+        Rows with no rating (not yet pass-4 reviewed, or reviewed before this
+        existed) are excluded, not bucketed as a pseudo-status."""
+        rows = self.conn.execute(
+            """SELECT cr.qualitative_rating as rating, COUNT(*) as cnt
+               FROM combination_results cr
+               JOIN domains d ON cr.domain_id = d.id
+               WHERE d.name = ? AND cr.qualitative_rating IS NOT NULL
+               GROUP BY cr.qualitative_rating""",
+            (domain_name,),
+        ).fetchall()
+        return {r["rating"]: r["cnt"] for r in rows}
+
     def get_pipeline_summary(self, domain_name: str) -> dict | None:
         """Return a summary of results for a domain, or None if no results."""
         row = self.conn.execute(
@@ -685,8 +715,12 @@ class Repository:
         ).fetchone()
         return dict(row) if row else None
 
-    def get_all_results(self, domain_name: str, status: str | None = None) -> list[dict]:
-        """Return all results for a domain, optionally filtered by combo status."""
+    def get_all_results(
+        self, domain_name: str, status: str | None = None, rating: str | None = None
+    ) -> list[dict]:
+        """Return all results for a domain, optionally filtered by combo
+        status and/or qualitative_rating (LOW/MEDIUM/HIGH, independent filters
+        that combine with AND)."""
         query = """SELECT cr.*, c.hash, c.status as combo_status, d.name as domain_name
                    FROM combination_results cr
                    JOIN combinations c ON cr.combination_id = c.id
@@ -698,6 +732,9 @@ class Repository:
         elif status:
             query += " AND c.status = ? AND cr.domain_block_reason IS NULL"
             params.append(status)
+        if rating:
+            query += " AND cr.qualitative_rating = ?"
+            params.append(rating)
         query += " ORDER BY cr.composite_score DESC"
         rows = self.conn.execute(query, params).fetchall()
         combo_ids = [r["combination_id"] for r in rows]
@@ -712,6 +749,7 @@ class Repository:
                 "pass_reached": r["pass_reached"],
                 "domain_id": r["domain_id"],
                 "domain_block_reason": r["domain_block_reason"],
+                "qualitative_rating": r["qualitative_rating"],
             }
             for r in rows
         ]

src/physcom/db/schema.py

@@ -91,6 +91,7 @@ CREATE TABLE IF NOT EXISTS combination_results (
     human_notes         TEXT,
     pass_reached        INTEGER,
     domain_block_reason TEXT,
+    qualitative_rating  TEXT,
     UNIQUE(combination_id, domain_id)
 );
 
@@ -165,6 +166,10 @@ def _migrate(conn: sqlite3.Connection) -> None:
         conn.execute(
             "ALTER TABLE combination_results ADD COLUMN domain_block_reason TEXT"
         )
+    if "qualitative_rating" not in result_cols:
+        conn.execute(
+            "ALTER TABLE combination_results ADD COLUMN qualitative_rating TEXT"
+        )
 
     # Backfill: cost_efficiency is lower-is-better in all domains
     conn.execute(

src/physcom/engine/pipeline.py

@@ -12,6 +12,7 @@ from physcom.engine.combinator import generate_combinations
 from physcom.engine.constraint_resolver import ConstraintResolver, ConstraintResult
 from physcom.engine.scorer import Scorer
 from physcom.llm.base import LLMProvider, LLMRateLimitError
+from physcom.llm.parsing import parse_rating
 from physcom.models.combination import Combination, ScoredResult
 from physcom.models.domain import Domain, MetricBound
 
@@ -385,308 +386,57 @@ class Pipeline:
         # Prepare metric lookup
         bounds_by_name = {mb.metric_name: mb for mb in domain.metric_bounds}
 
-        # ── Combo-first loop ─────────────────────────────────────
-        # Deterministic passes (1, 3, and 2 without an LLM) defer commits and
-        # get flushed periodically + in `finally` below -- a crash there costs
-        # a cheap recompute, not lost work worth committing per write. Pass 4
-        # (and pass 2 with an LLM) commit immediately after each call: those
-        # are slow and crash-prone (see the QwQ timeout saga), so that result
-        # is worth protecting the moment it lands.
+        # ── Phase-parallel: each pass runs to completion across every combo
+        # before the next pass starts, instead of walking each combo through
+        # every pass before moving to the next combo. This maximizes
+        # progress before the expensive/slow phase (pass 4's LLM calls) and
+        # keeps that phase's cost visible on its own, separate from the
+        # deterministic passes. It also removes any need for the two options
+        # to reconcile: pass 2 is estimator-only now (no LLM call in it at
+        # all -- self.llm is reserved for pass 4), so there's no combo that
+        # touches an LLM in both pass 2 and pass 4, and nothing here needs a
+        # live/resumed conversation across passes.
+        #
+        # Deterministic passes (1, 2, 3) defer commits and get flushed
+        # periodically + in `finally` below -- a crash there costs a cheap
+        # recompute, not lost work worth committing per write. Pass 4
+        # commits immediately after each call: those are slow and
+        # crash-prone (see the QwQ timeout saga), so that result is worth
+        # protecting the moment it lands.
         combos_since_commit = 0
-        try:
-            for combo in combos:
-                self._check_cancelled(run_id)
+
+        def _tick_commit() -> None:
+            nonlocal combos_since_commit
             combos_since_commit += 1
             if combos_since_commit >= 200:
                 self.repo.commit()
                 combos_since_commit = 0
 
-                # Check existing progress for this combo in this domain
-                existing_pass = self.repo.get_combo_pass_reached(
-                    combo.id, domain.id
-                ) or 0
+        try:
+            if 1 in passes:
+                for combo in combos:
+                    self._check_cancelled(run_id)
+                    _tick_commit()
+                    self._process_pass1(combo, domain, result, run_id)
 
-                # Load existing result to preserve human review data
-                existing_result = self.repo.get_existing_result(
-                    combo.id, domain.id
+            if 2 in passes:
+                for combo in combos:
+                    self._check_cancelled(run_id)
+                    _tick_commit()
+                    self._process_pass2(combo, domain, bounds_by_name, result, run_id)
+
+            if 3 in passes:
+                for combo in combos:
+                    self._check_cancelled(run_id)
+                    _tick_commit()
+                    self._process_pass3(
+                        combo, domain, bounds_by_name, result, score_threshold, run_id
                     )
 
-                # ── Pass 1: Constraint Resolution ────────────────
-                if 1 in passes and existing_pass < 1:
-                    cr: ConstraintResult = self.resolver.resolve(combo)
-                    if cr.status == "p1_fail":
-                        combo.status = "p1_fail"
-                        combo.block_reason = "; ".join(cr.violations)
-                        self.repo.update_combination_status(
-                            combo.id, "p1_fail", combo.block_reason, commit=False
-                        )
-                        # Save a result row so failed combos appear in results
-                        self.repo.save_result(
-                            combo.id,
-                            domain.id,
-                            composite_score=0.0,
-                            pass_reached=1,
-                            commit=False,
-                        )
-                        result.pass1_failed += 1
-                        self._update_run_counters(run_id, result, current_pass=1)
-                        continue  # p1_fail — skip remaining passes
-                    else:
-                        combo.status = "valid"
-                        self.repo.update_combination_status(combo.id, "valid", commit=False)
-
-                        # Domain constraint check (per-domain block only). combo.status
-                        # stays "valid" here on purpose: it's domain-agnostic and the
-                        # same combo can be blocked in this domain but valid in another.
-                        # The per-domain block lives on combination_results.domain_block_reason
-                        # (see count_combinations_by_status / get_all_results, which bucket on it).
-                        if domain.constraints:
-                            dc_result = self.resolver.check_domain_constraints(
-                                combo, domain.constraints
-                            )
-                            if dc_result.status == "p1_fail":
-                                self.repo.save_result(
-                                    combo.id, domain.id,
-                                    composite_score=0.0, pass_reached=1,
-                                    domain_block_reason="; ".join(
-                                        dc_result.violations
-                                    ),
-                                    commit=False,
-                                )
-                                result.pass1_failed += 1
-                                self._update_run_counters(
-                                    run_id, result, current_pass=1
-                                )
-                                continue
-
-                        if cr.status == "conditional":
-                            result.pass1_conditional += 1
-                        else:
-                            result.pass1_valid += 1
-
-                    self._update_run_counters(run_id, result, current_pass=1)
-                elif 1 in passes:
-                    # Already pass1'd — check if it failed
-                    if combo.status.endswith("_fail"):
-                        result.pass1_failed += 1
-                        continue
-                    # Check if domain-blocked from a prior run
-                    if existing_result and existing_result["pass_reached"] == 1:
-                        result.pass1_failed += 1
-                        continue
-                    result.pass1_valid += 1
-                else:
-                    # Pass 1 not requested; check if failed from a prior run
-                    if combo.status.endswith("_fail"):
-                        result.pass1_failed += 1
-                        continue
-
-                # ── Pass 2: Physics Estimation ───────────────────
-                raw_metrics: dict[str, float] = {}
-                if 2 in passes and existing_pass < 2:
-                    description = _describe_combination(combo)
-                    if self.llm:
-                        raw_metrics = self.llm.estimate_physics(
-                            description, domain.metric_bounds
-                        )
-                    else:
-                        raw_metrics = self._stub_estimate(combo, domain.metric_bounds)
-
-                    # Save raw estimates immediately (crash-safe)
-                    estimate_dicts = []
-                    for mname, rval in raw_metrics.items():
-                        mb = bounds_by_name.get(mname)
-                        if mb and mb.metric_id:
-                            estimate_dicts.append({
-                                "metric_id": mb.metric_id,
-                                "raw_value": rval,
-                                "estimation_method": "llm" if self.llm else "stub",
-                                "confidence": 1.0,
-                            })
-                    # LLM-produced estimates commit immediately (slow/crash-
-                    # prone, worth protecting); stub estimates are instant
-                    # and defer, same as the rest of the deterministic passes.
-                    used_llm = self.llm is not None
-                    if estimate_dicts:
-                        self.repo.save_raw_estimates(
-                            combo.id, domain.id, estimate_dicts, commit=used_llm
-                        )
-
-                    # Check for all-zero estimates → p2_fail
-                    if raw_metrics and all(v == 0.0 for v in raw_metrics.values()):
-                        combo.status = "p2_fail"
-                        combo.block_reason = "All metric estimates are zero"
-                        self.repo.update_combination_status(
-                            combo.id, "p2_fail", combo.block_reason, commit=used_llm
-                        )
-                        self.repo.save_result(
-                            combo.id, domain.id,
-                            composite_score=0.0, pass_reached=2,
-                            commit=used_llm,
-                        )
-                        result.pass2_failed += 1
-                        self._update_run_counters(run_id, result, current_pass=2)
-                        continue
-
-                    result.pass2_estimated += 1
-                    self._update_run_counters(run_id, result, current_pass=2)
-                elif 2 in passes:
-                    # Already estimated — reload raw values from DB
-                    existing_scores = self.repo.get_combination_scores(
-                        combo.id, domain.id
-                    )
-                    raw_metrics = {
-                        s["metric_name"]: s["raw_value"] for s in existing_scores
-                    }
-                    result.pass2_estimated += 1
-                else:
-                    # Pass 2 not requested, use empty metrics
-                    raw_metrics = {}
-
-                # ── Pass 3: Scoring & Ranking ────────────────────
-                if 3 in passes and existing_pass < 3:
-                    sr = self.scorer.score_combination(combo, raw_metrics)
-
-                    # Persist per-metric scores with normalized values
-                    score_dicts = []
-                    for s in sr.scores:
-                        mb = bounds_by_name.get(s.metric_name)
-                        if mb and mb.metric_id:
-                            score_dicts.append({
-                                "metric_id": mb.metric_id,
-                                "raw_value": s.raw_value,
-                                "normalized_score": s.normalized_score,
-                                "estimation_method": s.estimation_method,
-                                "confidence": s.confidence,
-                            })
-                    if score_dicts:
-                        self.repo.save_scores(combo.id, domain.id, score_dicts, commit=False)
-
-                    # Preserve existing human data
-                    novelty_flag = (
-                        existing_result["novelty_flag"] if existing_result else None
-                    )
-                    human_notes = (
-                        existing_result["human_notes"] if existing_result else None
-                    )
-
-                    if sr.composite_score < score_threshold:
-                        self.repo.save_result(
-                            combo.id, domain.id,
-                            sr.composite_score, pass_reached=3,
-                            novelty_flag=novelty_flag,
-                            human_notes=human_notes,
-                            commit=False,
-                        )
-                        combo.status = "p3_fail"
-                        combo.block_reason = (
-                            f"Composite score {sr.composite_score:.4f} "
-                            f"below threshold {score_threshold}"
-                        )
-                        self.repo.update_combination_status(
-                            combo.id, "p3_fail", combo.block_reason, commit=False
-                        )
-                        result.pass3_failed += 1
-                        result.pass3_scored += 1
-                        self._update_run_counters(run_id, result, current_pass=3)
-                        continue
-
-                    self.repo.save_result(
-                        combo.id,
-                        domain.id,
-                        sr.composite_score,
-                        pass_reached=3,
-                        novelty_flag=novelty_flag,
-                        human_notes=human_notes,
-                        commit=False,
-                    )
-                    self.repo.update_combination_status(combo.id, "scored", commit=False)
-
-                    result.pass3_scored += 1
-                    result.pass3_above_threshold += 1
-
-                    self._update_run_counters(run_id, result, current_pass=3)
-                elif 3 in passes and existing_pass >= 3:
-                    # Already scored — count it
-                    result.pass3_scored += 1
-                    if existing_result and existing_result["composite_score"] is not None:
-                        if existing_result["composite_score"] >= score_threshold:
-                            result.pass3_above_threshold += 1
-
-                # ── Pass 4: LLM Review ───────────────────────────
             if 4 in passes and self.llm:
-                    cur_pass = self.repo.get_combo_pass_reached(
-                        combo.id, domain.id
-                    ) or 0
-                    if cur_pass < 4:
-                        cur_result = self.repo.get_existing_result(
-                            combo.id, domain.id
-                        )
-                        if (
-                            cur_result
-                            and cur_result["composite_score"] is not None
-                            and cur_result["composite_score"] >= score_threshold
-                        ):
-                            description = _describe_combination(combo)
-                            db_scores = self.repo.get_combination_scores(
-                                combo.id, domain.id
-                            )
-                            score_dict = {
-                                s["metric_name"]: s["normalized_score"]
-                                for s in db_scores
-                                if s["normalized_score"] is not None
-                            }
-                            raw_dict = {
-                                s["metric_name"]: s["raw_value"]
-                                for s in db_scores
-                                if s["raw_value"] is not None
-                            }
-                            review_result: tuple[str, bool] | None = None
-                            try:
-                                review_result = self.llm.review_plausibility(
-                                    description, raw_dict, score_dict, domain.metric_bounds
-                                )
-                            except LLMRateLimitError as exc:
-                                self._wait_for_rate_limit(run_id, exc.retry_after)
-                                try:
-                                    review_result = self.llm.review_plausibility(
-                                        description, raw_dict, score_dict, domain.metric_bounds
-                                    )
-                                except LLMRateLimitError:
-                                    pass  # still limited; skip, retry next run
-                            if review_result is not None:
-                                review_text, plausible = review_result
-                                if not plausible:
-                                    self.repo.save_result(
-                                        combo.id, domain.id,
-                                        cur_result["composite_score"],
-                                        pass_reached=4,
-                                        novelty_flag=cur_result.get("novelty_flag"),
-                                        llm_review=review_text,
-                                        human_notes=cur_result.get("human_notes"),
-                                    )
-                                    combo.status = "p4_fail"
-                                    combo.block_reason = "LLM deemed implausible"
-                                    self.repo.update_combination_status(
-                                        combo.id, "p4_fail", combo.block_reason
-                                    )
-                                    result.pass4_failed += 1
-                                else:
-                                    self.repo.save_result(
-                                        combo.id, domain.id,
-                                        cur_result["composite_score"],
-                                        pass_reached=4,
-                                        novelty_flag=cur_result.get("novelty_flag"),
-                                        llm_review=review_text,
-                                        human_notes=cur_result.get("human_notes"),
-                                    )
-                                    self.repo.update_combination_status(
-                                        combo.id, "llm_reviewed"
-                                    )
-                                    result.pass4_reviewed += 1
-                                self._update_run_counters(
-                                    run_id, result, current_pass=4
-                                )
+                for combo in combos:
+                    self._check_cancelled(run_id)
+                    self._process_pass4(combo, domain, result, score_threshold, run_id)
 
         except CancelledError:
             if run_id is not None:
@@ -716,6 +466,271 @@ class Pipeline:
         result.top_results = self.repo.get_top_results(domain.name, limit=20)
         return result
 
+    @staticmethod
+    def _already_dead(combo: Combination, existing_result: dict | None) -> bool:
+        """True if this combo is dead for every pass after 1 -- either a
+        generic failure (status ends in _fail) or a domain-specific block.
+        The domain-block case needs the extra existing_result check:
+        combo.status stays "valid" on purpose for it (domain-agnostic,
+        see _process_pass1's own comment on this), so pass_reached==1 with
+        the block already recorded is what actually marks it dead --
+        status alone isn't enough to catch it."""
+        if combo.status.endswith("_fail"):
+            return True
+        return bool(existing_result and existing_result["pass_reached"] == 1)
+
+    def _process_pass1(
+        self, combo: Combination, domain: Domain, result: PipelineResult, run_id: int | None
+    ) -> None:
+        """Constraint resolution for one combo. All writes deferred (commit=False)."""
+        existing_pass = self.repo.get_combo_pass_reached(combo.id, domain.id) or 0
+        if existing_pass >= 1:
+            if combo.status.endswith("_fail"):
+                result.pass1_failed += 1
+                return
+            existing_result = self.repo.get_existing_result(combo.id, domain.id)
+            if existing_result and existing_result["pass_reached"] == 1:
+                result.pass1_failed += 1
+                return
+            result.pass1_valid += 1
+            return
+
+        cr: ConstraintResult = self.resolver.resolve(combo)
+        if cr.status == "p1_fail":
+            combo.status = "p1_fail"
+            combo.block_reason = "; ".join(cr.violations)
+            self.repo.update_combination_status(
+                combo.id, "p1_fail", combo.block_reason, commit=False
+            )
+            # Save a result row so failed combos appear in results
+            self.repo.save_result(
+                combo.id, domain.id, composite_score=0.0, pass_reached=1, commit=False
+            )
+            result.pass1_failed += 1
+            self._update_run_counters(run_id, result, current_pass=1)
+            return
+
+        combo.status = "valid"
+        self.repo.update_combination_status(combo.id, "valid", commit=False)
+
+        # Domain constraint check (per-domain block only). combo.status stays
+        # "valid" here on purpose: it's domain-agnostic and the same combo can
+        # be blocked in this domain but valid in another. The per-domain
+        # block lives on combination_results.domain_block_reason (see
+        # count_combinations_by_status / get_all_results, which bucket on it).
+        if domain.constraints:
+            dc_result = self.resolver.check_domain_constraints(combo, domain.constraints)
+            if dc_result.status == "p1_fail":
+                self.repo.save_result(
+                    combo.id, domain.id,
+                    composite_score=0.0, pass_reached=1,
+                    domain_block_reason="; ".join(dc_result.violations),
+                    commit=False,
+                )
+                result.pass1_failed += 1
+                self._update_run_counters(run_id, result, current_pass=1)
+                return
+
+        if cr.status == "conditional":
+            result.pass1_conditional += 1
+        else:
+            result.pass1_valid += 1
+        self._update_run_counters(run_id, result, current_pass=1)
+
+    def _process_pass2(
+        self,
+        combo: Combination,
+        domain: Domain,
+        bounds_by_name: dict[str, MetricBound],
+        result: PipelineResult,
+        run_id: int | None,
+    ) -> None:
+        """Physics estimation for one combo. Estimator-only -- self.llm is
+        reserved for pass 4, never consulted here. All writes deferred."""
+        existing_result = self.repo.get_existing_result(combo.id, domain.id)
+        if self._already_dead(combo, existing_result):
+            return
+        existing_pass = self.repo.get_combo_pass_reached(combo.id, domain.id) or 0
+        if existing_pass >= 2:
+            result.pass2_estimated += 1
+            return
+
+        raw_metrics = self._stub_estimate(combo, domain.metric_bounds)
+
+        estimate_dicts = []
+        for mname, rval in raw_metrics.items():
+            mb = bounds_by_name.get(mname)
+            if mb and mb.metric_id:
+                estimate_dicts.append({
+                    "metric_id": mb.metric_id,
+                    "raw_value": rval,
+                    "estimation_method": "stub",
+                    "confidence": 1.0,
+                })
+        if estimate_dicts:
+            self.repo.save_raw_estimates(combo.id, domain.id, estimate_dicts, commit=False)
+
+        # Check for all-zero estimates → p2_fail
+        if raw_metrics and all(v == 0.0 for v in raw_metrics.values()):
+            combo.status = "p2_fail"
+            combo.block_reason = "All metric estimates are zero"
+            self.repo.update_combination_status(
+                combo.id, "p2_fail", combo.block_reason, commit=False
+            )
+            self.repo.save_result(
+                combo.id, domain.id, composite_score=0.0, pass_reached=2, commit=False
+            )
+            result.pass2_failed += 1
+            self._update_run_counters(run_id, result, current_pass=2)
+            return
+
+        result.pass2_estimated += 1
+        self._update_run_counters(run_id, result, current_pass=2)
+
+    def _process_pass3(
+        self,
+        combo: Combination,
+        domain: Domain,
+        bounds_by_name: dict[str, MetricBound],
+        result: PipelineResult,
+        score_threshold: float,
+        run_id: int | None,
+    ) -> None:
+        """Scoring for one combo. Reloads raw estimates from the DB (pass 2
+        ran as its own separate phase, not in-memory from this iteration).
+        All writes deferred."""
+        existing_result = self.repo.get_existing_result(combo.id, domain.id)
+        if self._already_dead(combo, existing_result):
+            return
+        existing_pass = self.repo.get_combo_pass_reached(combo.id, domain.id) or 0
+        if existing_pass >= 3:
+            result.pass3_scored += 1
+            if existing_result and existing_result["composite_score"] is not None:
+                if existing_result["composite_score"] >= score_threshold:
+                    result.pass3_above_threshold += 1
+            return
+
+        existing_scores = self.repo.get_combination_scores(combo.id, domain.id)
+        raw_metrics = {s["metric_name"]: s["raw_value"] for s in existing_scores}
+        sr = self.scorer.score_combination(combo, raw_metrics)
+
+        score_dicts = []
+        for s in sr.scores:
+            mb = bounds_by_name.get(s.metric_name)
+            if mb and mb.metric_id:
+                score_dicts.append({
+                    "metric_id": mb.metric_id,
+                    "raw_value": s.raw_value,
+                    "normalized_score": s.normalized_score,
+                    "estimation_method": s.estimation_method,
+                    "confidence": s.confidence,
+                })
+        if score_dicts:
+            self.repo.save_scores(combo.id, domain.id, score_dicts, commit=False)
+
+        # Preserve existing human data
+        novelty_flag = existing_result["novelty_flag"] if existing_result else None
+        human_notes = existing_result["human_notes"] if existing_result else None
+
+        if sr.composite_score < score_threshold:
+            self.repo.save_result(
+                combo.id, domain.id, sr.composite_score, pass_reached=3,
+                novelty_flag=novelty_flag, human_notes=human_notes, commit=False,
+            )
+            combo.status = "p3_fail"
+            combo.block_reason = (
+                f"Composite score {sr.composite_score:.4f} below threshold {score_threshold}"
+            )
+            self.repo.update_combination_status(
+                combo.id, "p3_fail", combo.block_reason, commit=False
+            )
+            result.pass3_failed += 1
+            result.pass3_scored += 1
+            self._update_run_counters(run_id, result, current_pass=3)
+            return
+
+        self.repo.save_result(
+            combo.id, domain.id, sr.composite_score, pass_reached=3,
+            novelty_flag=novelty_flag, human_notes=human_notes, commit=False,
+        )
+        self.repo.update_combination_status(combo.id, "scored", commit=False)
+        result.pass3_scored += 1
+        result.pass3_above_threshold += 1
+        self._update_run_counters(run_id, result, current_pass=3)
+
+    def _process_pass4(
+        self,
+        combo: Combination,
+        domain: Domain,
+        result: PipelineResult,
+        score_threshold: float,
+        run_id: int | None,
+    ) -> None:
+        """LLM plausibility review for one combo. Writes commit immediately
+        (default commit=True) -- slow, crash-prone calls worth protecting
+        the moment a result lands."""
+        cur_result = self.repo.get_existing_result(combo.id, domain.id)
+        if self._already_dead(combo, cur_result):
+            return
+        cur_pass = self.repo.get_combo_pass_reached(combo.id, domain.id) or 0
+        if cur_pass >= 4:
+            return
+        if not (
+            cur_result
+            and cur_result["composite_score"] is not None
+            and cur_result["composite_score"] >= score_threshold
+        ):
+            return
+
+        description = _describe_combination(combo)
+        db_scores = self.repo.get_combination_scores(combo.id, domain.id)
+        score_dict = {
+            s["metric_name"]: s["normalized_score"]
+            for s in db_scores if s["normalized_score"] is not None
+        }
+        raw_dict = {
+            s["metric_name"]: s["raw_value"]
+            for s in db_scores if s["raw_value"] is not None
+        }
+
+        review_result: tuple[str, bool] | None = None
+        try:
+            review_result = self.llm.review_plausibility(
+                description, raw_dict, score_dict, domain
+            )
+        except LLMRateLimitError as exc:
+            self._wait_for_rate_limit(run_id, exc.retry_after)
+            try:
+                review_result = self.llm.review_plausibility(
+                    description, raw_dict, score_dict, domain.metric_bounds
+                )
+            except LLMRateLimitError:
+                return  # still limited; skip, retry next run
+
+        if review_result is None:
+            return
+        review_text, plausible = review_result
+        rating = parse_rating(review_text)
+        if not plausible:
+            self.repo.save_result(
+                combo.id, domain.id, cur_result["composite_score"], pass_reached=4,
+                novelty_flag=cur_result.get("novelty_flag"), llm_review=review_text,
+                human_notes=cur_result.get("human_notes"), qualitative_rating=rating,
+            )
+            combo.status = "p4_fail"
+            combo.block_reason = "LLM deemed implausible"
+            self.repo.update_combination_status(combo.id, "p4_fail", combo.block_reason)
+            result.pass4_failed += 1
+        else:
+            self.repo.save_result(
+                combo.id, domain.id, cur_result["composite_score"], pass_reached=4,
+                novelty_flag=cur_result.get("novelty_flag"), llm_review=review_text,
+                human_notes=cur_result.get("human_notes"), qualitative_rating=rating,
+            )
+            self.repo.update_combination_status(combo.id, "llm_reviewed")
+            result.pass4_reviewed += 1
+        self._update_run_counters(run_id, result, current_pass=4)
+
     def _wait_for_rate_limit(self, run_id: int | None, retry_after: int) -> None:
         """Mark run rate_limited, sleep with cancel checks, then resume."""
         if run_id is not None:

src/physcom/llm/base.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 
 from abc import ABC, abstractmethod
 
-from physcom.models.domain import MetricBound
+from physcom.models.domain import Domain, MetricBound
 
 
 class LLMRateLimitError(Exception):
@@ -40,7 +40,7 @@ class LLMProvider(ABC):
         combination_description: str,
         raw_metrics: dict[str, float],
         normalized_scores: dict[str, float],
-        metrics: list[MetricBound],
+        domain: Domain,
     ) -> tuple[str, bool]:
         """Given a combination, its raw physical estimates, and their
         normalized scores, return a (text, is_plausible) tuple:
@@ -50,6 +50,11 @@ class LLMProvider(ABC):
         normalized score) so the review can reason from the actual physics
         rather than only a compressed 0-1 number, which can look
         deceptively bad for a metric whose scale was built for a different
-        kind of vehicle. `metrics` carries each metric's unit for
-        formatting the raw value meaningfully."""
+        kind of vehicle. `domain` carries both each metric's unit (via
+        domain.metric_bounds, for formatting the raw value meaningfully)
+        and the domain's own name/description, so the review judges a
+        metric like range against what THIS domain actually needs rather
+        than generic real-world expectations for the platform category
+        (e.g. a short-hop domain shouldn't get judged against typical
+        long-haul aircraft range)."""
         ...

src/physcom/llm/parsing.py

@@ -16,6 +16,13 @@ def parse_verdict(text: str) -> bool:
     return True
 
 
+def parse_rating(text: str) -> str | None:
+    """Extract RATING: LOW/MEDIUM/HIGH from response; None if absent (older
+    reviews saved before this existed, or a malformed response)."""
+    m = re.search(r"RATING:\s*(LOW|MEDIUM|HIGH)", text, re.IGNORECASE)
+    return m.group(1).upper() if m else None
+
+
 def parse_metric_json(text: str, metrics: list[MetricBound]) -> dict[str, float]:
     """Strip markdown fences and parse JSON; fall back to each metric's own
     norm_min/norm_max midpoint on error — a flat constant like 0.5 is

src/physcom/llm/prompts.py

@@ -116,6 +116,14 @@ You are reviewing a transportation concept for real-world viability — could th
 actually be built and operated safely. Whether it is new, exciting, or original
 is NOT the question.
 
+## Domain
+This concept is being evaluated for "{domain_name}": {domain_description}
+Judge every metric against what THIS domain actually needs, not general
+expectations for the platform category. A range far beyond what this domain
+requires is a strength or a non-issue, never a weakness -- don't reason about
+range, speed, or capacity by comparing to what other vehicles of this type
+typically have in general use; compare to what this specific domain calls for.
+
 ## Concept
 {description}
 
@@ -139,6 +147,14 @@ before treating the score as evidence of a problem.
 
 {scores}
 
+Safety and accessibility (infrastructure/regulatory availability) are NOT
+among the scores above — neither reduces to a physics formula the way the
+metrics above do, so nothing here estimates them numerically. Reason about
+both directly from the concept description: does this combination carry a
+specific safety hazard, and is the infrastructure/regulatory environment it
+needs realistic? Both feed into the RATING below as qualitative judgment
+calls, not as scores of their own.
+
 ## What makes something IMPLAUSIBLE
 Mark IMPLAUSIBLE if either of these is true:
 - It is physically or engineering-wise impossible given the components
@@ -150,15 +166,13 @@ Mark IMPLAUSIBLE if either of these is true:
   fatiguing a hull over time is a real structural risk, not just "explosives
   are dangerous in general"; a fuel that's fine in the open becoming
   concentrated in a sealed tube is a real risk, not just "fuel is
-  flammable"). A low given safety score is a signal the pipeline already
-  found something concerning — treat it as evidence, not noise to explain
-  away.
+  flammable").
 - Or: a real regulatory/infrastructure barrier with no plausible workaround.
 
 None of these make something implausible on their own:
 - being unoriginal or something like it already exists
 - being expensive, slow, or short-range
-- a single mediocre score on one metric that isn't safety-related
+- a single mediocre score on one metric
 
 Most concepts that reach this review are ordinary and workable; reserve
 IMPLAUSIBLE for a real, specific problem you can name — but don't require
@@ -167,14 +181,26 @@ Reason from the physics and engineering actually described here, not from
 whether something like it already exists — novelty or lack of it is not
 evidence either way.
 
+## Overall Rating
+Separately from the plausibility verdict, give ONE holistic rating —
+LOW, MEDIUM, or HIGH — for how good this combination is overall. This is a
+single combined judgment, not a separate score per attribute: weigh the
+metric scores above together with your own qualitative read on safety and
+accessibility into one rating, the way a person sizing up the whole concept
+would, not a checklist of independent numbers.
+
 ## What to write
 In 2-4 sentences, give your reasoning, then check it against the scores
-above: if your reasoning conflicts with a score (e.g. you believe this is
-hazardous but its safety score is high), name the metric and say so
+above: if your reasoning conflicts with a score (e.g. you believe cost is
+a serious problem but its cost score is high), name the metric and say so
 explicitly — don't silently contradict a given score.
 
-Finish with exactly one line:
+Finish with exactly two lines. For the first, pick exactly one:
+RATING: LOW
+RATING: MEDIUM
+RATING: HIGH
+
+Then, for the second, pick exactly one:
 VERDICT: PLAUSIBLE
-or
 VERDICT: IMPLAUSIBLE
 """

src/physcom/llm/providers/gemini.py

@@ -13,7 +13,7 @@ from physcom.llm.prompts import (
     format_metrics_for_prompt,
     format_scores_for_prompt,
 )
-from physcom.models.domain import MetricBound
+from physcom.models.domain import Domain, MetricBound
 
 
 class GeminiLLMProvider(LLMProvider):
@@ -51,12 +51,14 @@ class GeminiLLMProvider(LLMProvider):
         combination_description: str,
         raw_metrics: dict[str, float],
         normalized_scores: dict[str, float],
-        metrics: list[MetricBound],
+        domain: Domain,
     ) -> tuple[str, bool]:
-        scores_str = format_scores_for_prompt(raw_metrics, normalized_scores, metrics)
+        scores_str = format_scores_for_prompt(raw_metrics, normalized_scores, domain.metric_bounds)
         prompt = PLAUSIBILITY_REVIEW_PROMPT.format(
             description=combination_description,
             scores=scores_str,
+            domain_name=domain.name,
+            domain_description=domain.description,
         )
         try:
             response = self._client.models.generate_content(

src/physcom/llm/providers/mock.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 from physcom.llm.base import LLMProvider
-from physcom.models.domain import MetricBound
+from physcom.models.domain import Domain, MetricBound
 
 
 class MockLLMProvider(LLMProvider):
@@ -25,7 +25,7 @@ class MockLLMProvider(LLMProvider):
         combination_description: str,
         raw_metrics: dict[str, float],
         normalized_scores: dict[str, float],
-        metrics: list[MetricBound],
+        domain: Domain,
     ) -> tuple[str, bool]:
         avg = sum(normalized_scores.values()) / max(len(normalized_scores), 1)
         if avg > 0.5:

src/physcom/llm/providers/ollama.py

@@ -14,7 +14,7 @@ from physcom.llm.prompts import (
     format_metrics_for_prompt,
     format_scores_for_prompt,
 )
-from physcom.models.domain import MetricBound
+from physcom.models.domain import Domain, MetricBound
 
 
 class OllamaLLMProvider(LLMProvider):
@@ -39,12 +39,14 @@ class OllamaLLMProvider(LLMProvider):
         combination_description: str,
         raw_metrics: dict[str, float],
         normalized_scores: dict[str, float],
-        metrics: list[MetricBound],
+        domain: Domain,
     ) -> tuple[str, bool]:
-        scores_str = format_scores_for_prompt(raw_metrics, normalized_scores, metrics)
+        scores_str = format_scores_for_prompt(raw_metrics, normalized_scores, domain.metric_bounds)
         prompt = PLAUSIBILITY_REVIEW_PROMPT.format(
             description=combination_description,
             scores=scores_str,
+            domain_name=domain.name,
+            domain_description=domain.description,
         )
         text = self._generate(prompt, json_mode=False).strip()
         return (text, parse_verdict(text))

src/physcom/seed/transport_example.py

@@ -728,11 +728,22 @@ URBAN_COMMUTING = Domain(
     name="urban_commuting",
     description="Daily travel within a city, 1-50km range",
     metric_bounds=[
-        MetricBound("power_density", weight=0.25, norm_min=1, norm_max=2000, unit="W/kg"),
-        MetricBound("cost_efficiency", weight=0.25, norm_min=1e-5, norm_max=2e-3, unit="$/m", lower_is_better=True),
-        MetricBound("safety", weight=0.25, norm_min=0.0, norm_max=1.0, unit="0-1"),
-        MetricBound("availability", weight=0.15, norm_min=0.0, norm_max=1.0, unit="0-1"),
-        MetricBound("range_fuel", weight=0.10, norm_min=5000, norm_max=500000, unit="m"),
+        # safety and availability removed from the scored/weighted metric set:
+        # both are judgment calls (risk assessment, infrastructure prevalence),
+        # not physics quantities with a formula, and running them through the
+        # same log-normalize() built for physical quantities produced
+        # incoherent results (a safety raw value already declared as "0-1"
+        # getting re-normalized into a different, unexplainable 0-1 number --
+        # see combo 1540's review, where phi4 could only cite the post-
+        # normalization number with no way to justify it). Safety is now a
+        # qualitative consideration folded into pass 4's holistic RATING
+        # instead. Availability needs real per-infrastructure-type research
+        # this project hasn't done -- not scored anywhere for now rather than
+        # pretend a quick formula or an equally uninformed LLM guess settles it.
+        # Weights renormalized to sum to 1.0 across the remaining metrics.
+        MetricBound("power_density", weight=0.4167, norm_min=1, norm_max=2000, unit="W/kg"),
+        MetricBound("cost_efficiency", weight=0.4167, norm_min=1e-5, norm_max=2e-3, unit="$/m", lower_is_better=True),
+        MetricBound("range_fuel", weight=0.1666, norm_min=5000, norm_max=500000, unit="m"),
     ],
     constraints=[DomainConstraint("medium", ["ground", "air"])],
 )
@@ -741,11 +752,12 @@ INTERPLANETARY = Domain(
     name="interplanetary_travel",
     description="Travel between planets within a solar system",
     metric_bounds=[
-        MetricBound("power_density", weight=0.30, norm_min=10, norm_max=10000, unit="W/kg"),
-        MetricBound("range_fuel", weight=0.30, norm_min=1e9, norm_max=1e13, unit="m"),
-        MetricBound("safety", weight=0.20, norm_min=0.0, norm_max=1.0, unit="0-1"),
-        MetricBound("cost_efficiency", weight=0.10, norm_min=1.0, norm_max=1e6, unit="$/m", lower_is_better=True),
-        MetricBound("range_degradation", weight=0.10, norm_min=8640000, norm_max=3.1536e9, unit="s"),
+        # safety removed -- see URBAN_COMMUTING comment above. Weights
+        # renormalized across the remaining metrics.
+        MetricBound("power_density", weight=0.375, norm_min=10, norm_max=10000, unit="W/kg"),
+        MetricBound("range_fuel", weight=0.375, norm_min=1e9, norm_max=1e13, unit="m"),
+        MetricBound("cost_efficiency", weight=0.125, norm_min=1.0, norm_max=1e6, unit="$/m", lower_is_better=True),
+        MetricBound("range_degradation", weight=0.125, norm_min=8640000, norm_max=3.1536e9, unit="s"),
     ],
     constraints=[DomainConstraint("medium", ["space"])],
 )
@@ -754,11 +766,12 @@ MARITIME_SHIPPING = Domain(
     name="maritime_shipping",
     description="Ocean cargo transport between ports, 100-40000km range",
     metric_bounds=[
-        MetricBound("power_density", weight=0.15, norm_min=1, norm_max=1000, unit="W/kg"),
-        MetricBound("cargo_capacity", weight=0.25, norm_min=1000, norm_max=2e8, unit="kg"),
-        MetricBound("cost_efficiency", weight=0.25, norm_min=1e-9, norm_max=1e-6, unit="$/(kg\u00b7m)", lower_is_better=True),
-        MetricBound("safety", weight=0.20, norm_min=0.0, norm_max=1.0, unit="0-1"),
-        MetricBound("range_fuel", weight=0.15, norm_min=100000, norm_max=40000000, unit="m"),
+        # safety removed -- see URBAN_COMMUTING comment above. Weights
+        # renormalized across the remaining metrics.
+        MetricBound("power_density", weight=0.1875, norm_min=1, norm_max=1000, unit="W/kg"),
+        MetricBound("cargo_capacity", weight=0.3125, norm_min=1000, norm_max=2e8, unit="kg"),
+        MetricBound("cost_efficiency", weight=0.3125, norm_min=1e-9, norm_max=1e-6, unit="$/(kg\u00b7m)", lower_is_better=True),
+        MetricBound("range_fuel", weight=0.1875, norm_min=100000, norm_max=40000000, unit="m"),
     ],
     constraints=[DomainConstraint("medium", ["water"])],
 )
@@ -767,11 +780,12 @@ LAST_MILE_DELIVERY = Domain(
     name="last_mile_delivery",
     description="Short-range package delivery within neighborhoods, 0.5-15km",
     metric_bounds=[
-        MetricBound("power_density", weight=0.25, norm_min=1, norm_max=500, unit="W/kg"),
-        MetricBound("cost_efficiency", weight=0.30, norm_min=1e-5, norm_max=5e-3, unit="$/m", lower_is_better=True),
-        MetricBound("cargo_capacity_kg", weight=0.20, norm_min=1, norm_max=500, unit="kg"),
-        MetricBound("safety", weight=0.15, norm_min=0.0, norm_max=1.0, unit="0-1"),
-        MetricBound("environmental_impact", weight=0.10, norm_min=0, norm_max=5e-4, unit="kg/m", lower_is_better=True),
+        # safety removed -- see URBAN_COMMUTING comment above. Weights
+        # renormalized across the remaining metrics.
+        MetricBound("power_density", weight=0.2941, norm_min=1, norm_max=500, unit="W/kg"),
+        MetricBound("cost_efficiency", weight=0.3529, norm_min=1e-5, norm_max=5e-3, unit="$/m", lower_is_better=True),
+        MetricBound("cargo_capacity_kg", weight=0.2353, norm_min=1, norm_max=500, unit="kg"),
+        MetricBound("environmental_impact", weight=0.1177, norm_min=0, norm_max=5e-4, unit="kg/m", lower_is_better=True),
     ],
     constraints=[DomainConstraint("medium", ["ground", "air"])],
 )
@@ -839,12 +853,11 @@ def load_transport_seed(repo) -> dict:
             counts["domains"] += 1
         except sqlite3.IntegrityError:
             pass
-        # Backfill metric units and lower_is_better on existing DBs.
-        for mb in domain.metric_bounds:
-            repo.ensure_metric(mb.metric_name, unit=mb.unit)
-            repo.backfill_metric_unit(domain.name, mb.metric_name, mb.unit)
-            if mb.lower_is_better:
-                repo.backfill_lower_is_better(domain.name, mb.metric_name)
+        # Sync domain_metric_weights to exactly match this domain's current
+        # metric_bounds on existing DBs -- upserts weight/norm_min/norm_max/
+        # unit for current metrics and removes any that were dropped (e.g.
+        # safety/availability no longer scored).
+        repo.sync_domain_metric_weights(domain)
         # Backfill domain constraints
         repo.replace_domain_constraints(domain)
 

src/physcom_web/routes/results.py

@@ -25,9 +25,11 @@ def results_domain(domain_name: str):
         return redirect(url_for("results.results_index"))
 
     status_filter = request.args.get("status")
-    results = repo.get_all_results(domain_name, status=status_filter)
+    rating_filter = request.args.get("rating")
+    results = repo.get_all_results(domain_name, status=status_filter, rating=rating_filter)
     # Domain-scoped status counts (only combos that have results in this domain)
     statuses = repo.count_combinations_by_status(domain_name=domain_name)
+    ratings = repo.count_results_by_rating(domain_name)
 
     return render_template(
         "results/list.html",
@@ -35,7 +37,9 @@ def results_domain(domain_name: str):
         domain=domain,
         results=results,
         status_filter=status_filter,
+        rating_filter=rating_filter,
         statuses=statuses,
+        ratings=ratings,
         total_results=sum(statuses.values()),
     )
 
@@ -101,6 +105,7 @@ def submit_review(domain_name: str, combo_id: int):
         novelty_flag=novelty_flag,
         llm_review=existing.get("llm_review") if existing else None,
         human_notes=human_notes,
+        qualitative_rating=existing.get("qualitative_rating") if existing else None,
     )
     repo.update_combination_status(combo_id, "reviewed")
 

src/physcom_web/static/style.css

@@ -214,6 +214,9 @@ table.compact th, table.compact td { padding: 0.25rem 0.4rem; font-size: 0.83rem
 .badge-llm_reviewed { background: rgba(107,163,160,0.12); color: var(--accent-teal); border-color: rgba(107,163,160,0.25); }
 .badge-reviewed  { background: rgba(155,142,196,0.12); color: var(--accent-violet); border-color: rgba(155,142,196,0.25); }
 .badge-pending   { background: rgba(184,147,92,0.12);  color: var(--accent-amber);  border-color: rgba(184,147,92,0.25); }
+.badge-rating-low    { background: rgba(184,92,92,0.12);   color: var(--accent-red);    border-color: rgba(184,92,92,0.25); }
+.badge-rating-medium { background: rgba(184,147,92,0.12);  color: var(--accent-amber);  border-color: rgba(184,147,92,0.25); }
+.badge-rating-high   { background: rgba(122,171,138,0.12); color: var(--accent-green);  border-color: rgba(122,171,138,0.25); }
 
 /* ── Buttons ─────────────────────────────────────────────── */
 .btn {

src/physcom_web/templates/home.html

@@ -50,12 +50,13 @@
     <div class="step-body">
       <h3>Physics Estimation</h3>
       <p>
-        Surviving combinations get raw metric estimates &mdash; speed, cost,
-        safety, range &mdash; via heuristic stubs or an LLM provider that
-        reasons about the physical properties of each pairing.
+        Surviving combinations get raw metric estimates &mdash; power
+        density, cost, range &mdash; from a deterministic physics engine
+        that sizes each combination from its own declared attributes, not
+        a guess.
       </p>
       <div class="step-example">
-        Bicycle + Human Pedalling &rarr; speed: 20 km/h, cost: $0.01/km
+        Bicycle + Human Muscle &rarr; power density: 4.4 W/kg, range: 500km
       </div>
     </div>
   </div>
@@ -72,8 +73,8 @@
         Combinations are ranked within their domain.
       </p>
       <div class="step-example">
-        Domain <code>urban_commuting</code> weights: speed 25%, cost 25%,
-        safety 25%, availability 15%, range 10%
+        Domain <code>urban_commuting</code> weights: power density 42%,
+        cost 42%, range 17%
       </div>
     </div>
   </div>
@@ -85,9 +86,11 @@
     <div class="step-body">
       <h3>LLM Review</h3>
       <p>
-        Top-scoring combinations are sent to a language model for plausibility
-        and novelty assessment &mdash; catching physically valid but practically
-        absurd pairings.
+        Top-scoring combinations are sent to a language model for a
+        plausibility verdict plus a holistic LOW/MEDIUM/HIGH rating &mdash;
+        weighing safety and accessibility as qualitative judgment calls
+        alongside the physics scores, catching physically valid but
+        practically absurd pairings.
       </p>
       <div class="step-example">
         "Train + Solar Sail: structurally valid constraints, but solar radiation
@@ -163,14 +166,15 @@
   <div class="card concept-card">
     <h3>Metrics</h3>
     <p>
-      Quantitative axes like speed, cost, safety, and range. Each metric
-      has a domain-specific weight and normalization range. Some are
-      inverted &mdash; lower cost is better.
+      Quantitative physics axes like power density, cost, and range. Each
+      metric has a domain-specific weight and normalization range. Some
+      are inverted &mdash; lower cost is better. Safety and accessibility
+      are judgment calls, not physics quantities &mdash; they're weighed
+      qualitatively in the LLM review pass instead of scored here.
     </p>
     <div class="concept-examples">
-      <span class="badge">speed</span>
+      <span class="badge">power_density</span>
       <span class="badge">cost_efficiency</span>
-      <span class="badge">safety</span>
       <span class="badge">range_fuel</span>
     </div>
   </div>

src/physcom_web/templates/results/detail.html

@@ -27,6 +27,9 @@
     {% if result %}
     <dt>Composite Score</dt><dd class="score-cell">{{ "%.4f"|format(result.composite_score) }}</dd>
     <dt>Pass Reached</dt><dd>{{ result.pass_reached }}</dd>
+    {% if result.qualitative_rating %}
+    <dt>Rating</dt><dd><span class="badge badge-rating-{{ result.qualitative_rating|lower }}">{{ result.qualitative_rating }}</span></dd>
+    {% endif %}
     {% if result.novelty_flag %}
     <dt>Novelty</dt><dd>{{ result.novelty_flag }}</dd>
     {% endif %}
@@ -102,11 +105,16 @@
             {%- elif s.raw_value >= mb.norm_max -%}
               <span class="badge badge-{{ 'p1_fail' if mb.lower_is_better else 'valid' }}">at/above max{{ ' (worst)' if mb.lower_is_better else '' }}</span>
             {%- else -%}
-              {% set pct = ((s.raw_value - mb.norm_min) / (mb.norm_max - mb.norm_min) * 100) | int %}
+              {% set raw_pct = (s.raw_value - mb.norm_min) / (mb.norm_max - mb.norm_min) * 100 %}
+              {# For lower_is_better metrics, raw_pct alone measures distance from norm_min,
+                 not quality -- a value near norm_min (excellent, cost near its floor) would
+                 otherwise render as a near-empty bar. Invert so the bar and percentage always
+                 mean "how good", matching the normalized score's own higher-is-better convention. #}
+              {% set pct = ((100 - raw_pct) if mb.lower_is_better else raw_pct) | int %}
               <div class="metric-bar-container">
                 <div class="metric-bar" style="width: {{ pct }}%"></div>
               </div>
-              <span class="metric-bar-label">~{{ pct }}%{{ ' ↓' if mb.lower_is_better else '' }}</span>
+              <span class="metric-bar-label">~{{ pct }}%{{ ' (lower is better)' if mb.lower_is_better else '' }}</span>
             {%- endif -%}
           {%- else -%}
             —

src/physcom_web/templates/results/list.html

@@ -26,11 +26,11 @@
 
   {% if statuses %}
   <div class="filter-row">
-    <span>Filter:</span>
-    <a href="{{ url_for('results.results_domain', domain_name=domain.name) }}"
+    <span>Status:</span>
+    <a href="{{ url_for('results.results_domain', domain_name=domain.name, rating=rating_filter) }}"
        class="btn btn-sm {{ '' if status_filter else 'btn-primary' }}">All ({{ total_results }})</a>
     {% for s, cnt in statuses.items() %}
-    <a href="{{ url_for('results.results_domain', domain_name=domain.name, status=s) }}"
+    <a href="{{ url_for('results.results_domain', domain_name=domain.name, status=s, rating=rating_filter) }}"
        class="btn btn-sm {{ 'btn-primary' if status_filter == s else '' }}">
       {{ s }} ({{ cnt }})
     </a>
@@ -38,9 +38,25 @@
   </div>
   {% endif %}
 
+  {% if ratings %}
+  <div class="filter-row">
+    <span>Rating:</span>
+    <a href="{{ url_for('results.results_domain', domain_name=domain.name, status=status_filter) }}"
+       class="btn btn-sm {{ '' if not rating_filter else 'btn-primary' }}">All</a>
+    {% for rt in ['HIGH', 'MEDIUM', 'LOW'] %}
+    {% if rt in ratings %}
+    <a href="{{ url_for('results.results_domain', domain_name=domain.name, status=status_filter, rating=rt) }}"
+       class="btn btn-sm {{ 'btn-primary' if rating_filter == rt else '' }}">
+      {{ rt }} ({{ ratings[rt] }})
+    </a>
+    {% endif %}
+    {% endfor %}
+  </div>
+  {% endif %}
+
   {% if not results %}
-    {% if status_filter %}
-    <p class="empty">No results with status "{{ status_filter }}" in this domain.</p>
+    {% if status_filter or rating_filter %}
+    <p class="empty">No results matching that filter in this domain.</p>
     {% else %}
     <p class="empty">No results for this domain yet. <a href="{{ url_for('pipeline.pipeline_form') }}">Run the pipeline</a> first.</p>
     {% endif %}
@@ -52,6 +68,7 @@
         <th>Score</th>
         <th>Entities</th>
         <th>Status</th>
+        <th>Rating</th>
         <th>Details</th>
         <th></th>
       </tr>
@@ -69,6 +86,13 @@
             <span class="badge badge-{{ r.combination.status }}">{{ r.combination.status }}</span>
           {%- endif -%}
         </td>
+        <td>
+          {%- if r.qualitative_rating -%}
+            <span class="badge badge-rating-{{ r.qualitative_rating|lower }}">{{ r.qualitative_rating }}</span>
+          {%- else -%}
+            —
+          {%- endif -%}
+        </td>
         <td class="block-reason-cell">
           {%- if r.domain_block_reason -%}
             {{ r.domain_block_reason }}

tests/test_pipeline_async.py

@@ -335,28 +335,34 @@ def test_p3_fail_below_threshold(seeded_repo):
 
 
 def test_p4_fail_implausible(seeded_repo):
-    """Combos deemed implausible by LLM should get p4_fail status."""
+    """Combos deemed implausible by LLM should get p4_fail status.
+
+    Pass 2 is estimator-only now (never calls the LLM), so there's no way
+    to force every combo's raw estimates toward a controlled low/high value
+    the way MockLLMProvider's default_estimates used to. Force the pass-4
+    verdict directly instead -- what's under test here is pipeline.py's
+    wiring of review_plausibility's return value to status/counters, not
+    MockLLMProvider's avg-based heuristic.
+    """
     from physcom.llm.providers.mock import MockLLMProvider
 
+    class AlwaysImplausibleLLM(MockLLMProvider):
+        def review_plausibility(self, description, raw_metrics, normalized_scores, domain):
+            return ("Always implausible for testing.", False)
+
     repo = seeded_repo
     domain = repo.get_domain("urban_commuting")
 
     resolver = ConstraintResolver()
     scorer = Scorer(domain)
-    # Low estimates → normalized scores avg <= 0.5 → MockLLMProvider returns (text, False)
     # Use threshold=0.0 so no combo gets p3_fail and all reach pass 4
-    mock_llm = MockLLMProvider(default_estimates={
-        "power_density": 0.1, "cost_efficiency": 0.1, "safety": 0.1,
-        "availability": 0.1, "range_fuel": 0.1,
-    })
-    pipeline = Pipeline(repo, resolver, scorer, llm=mock_llm)
+    pipeline = Pipeline(repo, resolver, scorer, llm=AlwaysImplausibleLLM())
 
     result = pipeline.run(
         domain, ["platform", "actuator", "energy_storage"],
         score_threshold=0.0, passes=[1, 2, 3, 4],
     )
 
-    # With low normalized scores (avg <= 0.5), reviewed combos should be p4_fail
     assert result.pass4_failed > 0
     assert result.pass4_reviewed == 0
 
@@ -367,20 +373,23 @@ def test_p4_fail_implausible(seeded_repo):
 
 
 def test_p4_pass_plausible(seeded_repo):
-    """Combos deemed plausible by LLM should get llm_reviewed status."""
+    """Combos deemed plausible by LLM should get llm_reviewed status.
+
+    See test_p4_fail_implausible on why the verdict is forced directly
+    rather than via controlled pass-2 estimates.
+    """
     from physcom.llm.providers.mock import MockLLMProvider
 
+    class AlwaysPlausibleLLM(MockLLMProvider):
+        def review_plausibility(self, description, raw_metrics, normalized_scores, domain):
+            return ("Always plausible for testing.", True)
+
     repo = seeded_repo
     domain = repo.get_domain("urban_commuting")
 
     resolver = ConstraintResolver()
     scorer = Scorer(domain)
-    # High estimates → avg > 0.5 → MockLLMProvider returns (text, True)
-    mock_llm = MockLLMProvider(default_estimates={
-        "power_density": 500.0, "cost_efficiency": 5e-4, "safety": 0.6,
-        "availability": 0.7, "range_fuel": 200000.0,
-    })
-    pipeline = Pipeline(repo, resolver, scorer, llm=mock_llm)
+    pipeline = Pipeline(repo, resolver, scorer, llm=AlwaysPlausibleLLM())
 
     result = pipeline.run(
         domain, ["platform", "actuator", "energy_storage"],