{ "ofone_version": "0.6.0", "mode": "Map", "charter": { "objective": "Map formal proof search as a repeat-2 unresolved proof state, separating candidate lemma obligation, countermodel pressure, certificate absence, timeout risk, and update triggers.", "scope": [ "formal proof search", "candidate lemma validation", "countermodel testing", "update behavior after lemma failure" ], "horizon": "bounded proof-search cycle", "stakes": [ "soundness", "false proof risk", "wrong non-provability conclusion" ], "risk_tier": "medium", "movement_jobs": [ "BOUND", "TEST", "WARN" ] }, "artifact_identity": { "artifact_id": "OFONE-2026-05-18-B01-FORMAL-FULL-R2", "case_id": "case-formal-proof-search-001", "objective_head": "formal proof-search map with lemma and countermodel pressure repeat 2", "scope_hash": "sha256:01634155f084b1646ac6930ab1cdc4787575fff4daf285c017271e0e2719e756", "config_hash": "sha256:613afac8909b34accb57fd2c24217bb59a28a45860e32f36f6ec5f7f4ab5587e", "active_evidence_hashes": [ "sha256:34f661606d2f46ef1ac0c5fb0c536824b1bc385ae374484aea3c56c65d81395a", "sha256:c797b129856f6055e9cb81eb9c3eb764dd839b8edaeb93109db0f1337f2b98ff" ], "created_at": "2026-05-18T09:07:00Z", "status": "draft", "movement_jobs": [ "BOUND", "TRIGGER" ] }, "adapter_projection": { "primary": "formal", "axes": { "formal": [ "axioms", "inference system", "candidate lemma", "proof obligation", "countermodel", "checker output" ] }, "movement_jobs": [ "BOUND", "LINK" ] }, "scene": { "scene_id": "S1", "frames": [ { "frame_id": "F1", "type": "logical", "assumptions": [ "The theorem is evaluated only under the declared axiom set and inference rules." ] }, { "frame_id": "F2", "type": "evidential", "assumptions": [ "Proof attempts, proof certificates, and countermodels must stay separate from interpretive claims." ] }, { "frame_id": "F3", "type": "temporal", "assumptions": [ "A failed lemma or changed formalization can invalidate downstream proof-path choices." ] } ], "tokens": [ { "token_id": "K1", "kind": "entity", "label": "axiom set A" }, { "token_id": "K2", "kind": "entity", "label": "target theorem T" }, { "token_id": "K3", "kind": "entity", "label": "candidate lemma L" }, { "token_id": "K4", "kind": "constraint", "label": "inference system R" }, { "token_id": "K5", "kind": "uncertainty", "label": "possible countermodel" }, { "token_id": "K6", "kind": "uncertainty", "label": "bounded solver timeout" } ], "state_variables": [ "proof frontier", "candidate lemma status", "countermodel status", "formal encoding stability" ], "observed_variables": [ "case dossier prompt", "expected formal pressure points" ], "hidden_variables": [ "axiom mismatch", "unproved lemma", "countermodel outside search bounds", "inference-rule mismatch" ], "movement_jobs": [ "BOUND", "WARN", "TEST" ], "subscenes": [ { "subscene_id": "SS1", "parent_scene": "S1", "purpose": "proof_step", "frames": [ "F1" ], "tokens": [ "K1", "K2", "K3", "K4" ], "entry_conditions": [ "formal target and candidate lemma are under review" ], "exit_conditions": [ "proof obligation is certified, rejected, or marked unresolved" ], "movement_jobs": [ "CLAIM", "TEST" ] }, { "subscene_id": "SS2", "parent_scene": "S1", "purpose": "evidence_acquisition", "frames": [ "F2" ], "tokens": [ "K5", "K6" ], "entry_conditions": [ "countermodel pressure or bounded search ambiguity is present" ], "exit_conditions": [ "countermodel artifact, proof certificate, or timeout status is recorded" ], "movement_jobs": [ "GROUND", "TEST" ] }, { "subscene_id": "SS3", "parent_scene": "S1", "purpose": "review_gate", "frames": [ "F3" ], "tokens": [ "K3", "K4" ], "entry_conditions": [ "lemma or encoding changes could invalidate the path" ], "exit_conditions": [ "proof map is patched or scoped rerun is triggered" ], "movement_jobs": [ "TRIGGER", "WARN" ] } ] }, "evidence": [ { "evidence_id": "E1", "source": "file", "span_or_locator": "benchmarks/cases/formal-proof-search.md#Prompt", "provenance": "frozen benchmark case dossier", "recency": "current", "reliability": "medium", "permission": "public", "content_hash": "sha256:34f661606d2f46ef1ac0c5fb0c536824b1bc385ae374484aea3c56c65d81395a", "retrieved_at": "2026-05-18T04:20:00Z", "extract": "The formal proof-search case states that an incomplete proof path has a candidate lemma and possible countermodel pressure.", "source_owner": "OfOne benchmark suite", "chain_of_custody": "Read from frozen local benchmark case during full_ofone formal run construction.", "supports": [ "C1", "C2", "C3" ], "risks": [ "scenario_level_only", "no_actual_axiom_or_theorem_text" ], "movement_jobs": [ "GROUND", "BOUND" ] }, { "evidence_id": "E2", "source": "file", "span_or_locator": "benchmarks/cases/formal-proof-search.md#Expected-OfOne-Pressure-Points", "provenance": "frozen benchmark case dossier", "recency": "current", "reliability": "medium", "permission": "public", "content_hash": "sha256:c797b129856f6055e9cb81eb9c3eb764dd839b8edaeb93109db0f1337f2b98ff", "retrieved_at": "2026-05-18T04:20:00Z", "extract": "Expected pressure points require separation of axioms, claims, proof obligations, countermodel tests, unknowns, and update behavior when a lemma is disproven.", "source_owner": "OfOne benchmark suite", "chain_of_custody": "Read from frozen local benchmark case during full_ofone formal run construction.", "supports": [ "C2", "C3", "C4" ], "risks": [ "requirements_are_not_checker_outputs" ], "movement_jobs": [ "GROUND", "TEST" ] } ], "claims": [ { "claim_id": "C1", "text": "The theorem should remain unresolved until a checkable proof certificate or proof path under R is available.", "type": "formal", "supports": [ "E1" ], "contradicts": [], "depends_on": [ "K2", "K4" ], "confidence": { "level": "high", "basis": [ "mechanism_fit", "adapter_fit" ], "failure_modes": [ "wrong_inference_system", "misencoded_axioms" ] }, "status": "active", "review_gate": false, "movement_jobs": [ "CLAIM", "TEST" ] }, { "claim_id": "C2", "text": "The candidate lemma is a separate proof obligation, not evidence for the theorem until it is proved or checked.", "type": "formal", "supports": [ "E1", "E2" ], "contradicts": [], "depends_on": [ "K3", "K4" ], "confidence": { "level": "high", "basis": [ "mechanism_fit", "adapter_fit" ], "failure_modes": [ "unproved_lemma", "inference_rule_mismatch" ] }, "status": "active", "review_gate": false, "movement_jobs": [ "CLAIM", "LINK" ] }, { "claim_id": "C3", "text": "A verified countermodel under the same formalization would block the theorem entailment claim.", "type": "formal", "supports": [ "E1", "E2" ], "contradicts": [ "C1" ], "depends_on": [ "K1", "K2", "K5" ], "confidence": { "level": "medium", "basis": [ "mechanism_fit", "contradiction_load", "adapter_fit" ], "failure_modes": [ "model_scope_mismatch", "bounded_search_only" ] }, "status": "active", "review_gate": false, "movement_jobs": [ "CLAIM", "TEST", "WARN" ] }, { "claim_id": "C4", "text": "A bounded search timeout is not by itself a proof of non-provability.", "type": "formal", "supports": [ "E2" ], "contradicts": [], "depends_on": [ "K6" ], "confidence": { "level": "medium", "basis": [ "mechanism_fit", "adapter_fit" ], "failure_modes": [ "decidability_boundary", "solver_timeout_misread" ] }, "status": "active", "review_gate": false, "movement_jobs": [ "CLAIM", "WARN" ] } ], "unknowns": [ { "unknown_id": "U1", "kind": "missing_evidence", "description": "No checked proof certificate or countermodel artifact is present.", "blocks": [ "O1", "O2", "R1" ], "resolution_move": "Run proof checker and countermodel search with retained artifacts.", "status": "open", "movement_jobs": [ "WARN", "GATE", "TEST" ] }, { "unknown_id": "U2", "kind": "missing_evidence", "description": "The candidate lemma has not been proved as a separate obligation.", "blocks": [ "O1", "R1" ], "resolution_move": "Prove, reject, or replace candidate lemma L before using it downstream.", "status": "open", "movement_jobs": [ "WARN", "TEST" ] } ], "kill_tests": [ { "test_id": "KT1", "target": "C1", "test_type": "countermodel", "condition": "A valid countermodel exists for theorem T under axiom set A and inference system R.", "falsifies": [ "C1" ], "movement_jobs": [ "TEST", "WARN" ] }, { "test_id": "KT2", "target": "C2", "test_type": "counterexample", "condition": "A failed proof obligation for candidate lemma L shows the lemma is false, irrelevant, or inconsistent with axiom set A.", "falsifies": [ "C2" ], "movement_jobs": [ "TEST", "WARN" ] } ], "criteria": [ { "criterion_id": "CR1", "name": "Proof-certificate validity", "kind": "threshold", "priority": "must", "threshold": "Do not render theorem T proved without a checkable certificate or explicit proof path under R.", "owned_by": [ "A1" ], "movement_jobs": [ "EVALUATE", "GATE" ] }, { "criterion_id": "CR2", "name": "Countermodel exclusion", "kind": "constraint", "priority": "must", "threshold": "A verified countermodel defeats the entailment claim under the same formalization.", "owned_by": [ "A1" ], "movement_jobs": [ "TEST", "WARN" ] }, { "criterion_id": "CR3", "name": "Lemma obligation isolation", "kind": "constraint", "priority": "should", "threshold": "Keep candidate lemma status separate from theorem status until the lemma obligation is resolved.", "owned_by": [ "A1" ], "movement_jobs": [ "LINK", "EVALUATE" ] } ], "actors": [ { "actor_id": "A1", "label": "proof reviewer", "role": "reviewer", "incentives": [ "avoid false proof acceptance", "avoid false non-provability conclusion" ], "exposures": [ "formal error", "benchmark scoring error" ], "authority": "approve", "legitimacy_basis": "responsibility for proof-certificate review", "movement_jobs": [ "BOUND", "GATE" ] } ], "tradeoff_surface": { "surface_id": "TS1", "options": [ "O1", "O2", "O3" ], "criteria": [ "CR1", "CR2", "CR3" ], "dominant_option": "O1", "why": [ "CR1", "CR3" ], "reversal_conditions": [ "U1", "U2", "T1", "T2" ], "movement_jobs": [ "EVALUATE", "TRIGGER" ] }, "temporal_model": { "time_horizon": "bounded proof-search cycle", "decision_deadline": "before declaring proved or not entailed", "evidence_validity_windows": [ { "evidence_id": "E1", "valid_until": "case dossier changes", "staleness_trigger": "formal proof-search case prompt changes" }, { "evidence_id": "E2", "valid_until": "case dossier changes", "staleness_trigger": "formal pressure-point requirements change" } ], "update_cadence": "after every proof-checker or countermodel result", "movement_jobs": [ "BOUND", "TRIGGER", "WARN" ] }, "information_value": [ { "unknown_id": "U1", "decision_impact": "high", "resolution_cost": "medium", "time_to_resolve": "bounded compute run", "risk_reduction": "high", "recommended_next_query": "Run proof checker and countermodel search under the same formalization and retain artifacts.", "movement_jobs": [ "TEST", "MOVE", "EVALUATE" ] }, { "unknown_id": "U2", "decision_impact": "high", "resolution_cost": "medium", "time_to_resolve": "bounded compute run", "risk_reduction": "high", "recommended_next_query": "Resolve candidate lemma L as a separate proof obligation before using it in theorem proof path.", "movement_jobs": [ "TEST", "MOVE", "EVALUATE" ] } ], "lenses": [ { "lens_id": "LENS1", "name": "formal proof lens", "adapter_axis": "formal", "questions": [ "What can be concluded from axioms, inference rules, and proof obligations only?" ], "claims_examined": [ "C1", "C2" ], "blind_spots": [ "actual axiom and theorem text are absent" ], "contention": [ "U2 blocks using the lemma as proof support" ], "movement_jobs": [ "WARN", "TEST", "EVALUATE" ] } ], "council_result": { "coverage": [ "formal" ], "missing_lenses": [], "major_dissent": [ "U1 and U2 block the rendered proof conclusion" ], "decision_effect": "Return unresolved until proof certificate, countermodel, and candidate lemma status are recorded.", "movement_jobs": [ "EVALUATE", "WARN", "GATE" ] }, "edges": [ { "edge_id": "X1", "from": "K4", "to": "C1", "relation_family": "causal", "relation": "constrains", "evidence_refs": [ "E1" ], "confidence": "high", "movement_jobs": [ "LINK" ] }, { "edge_id": "X2", "from": "C2", "to": "C1", "relation_family": "argumentative", "relation": "supports", "evidence_refs": [ "E2" ], "confidence": "medium", "movement_jobs": [ "LINK" ] }, { "edge_id": "X3", "from": "C3", "to": "C1", "relation_family": "argumentative", "relation": "contradicts", "evidence_refs": [ "E1", "E2" ], "confidence": "medium", "movement_jobs": [ "LINK", "TEST" ] }, { "edge_id": "X4", "from": "U1", "to": "O1", "relation_family": "workflow_state", "relation": "blocks", "evidence_refs": [ "E1" ], "confidence": "high", "movement_jobs": [ "WARN", "GATE" ] }, { "edge_id": "X5", "from": "U2", "to": "O1", "relation_family": "workflow_state", "relation": "blocks", "evidence_refs": [ "E2" ], "confidence": "high", "movement_jobs": [ "WARN", "TEST" ] } ], "loops": [ { "loop_id": "L1", "type": "learning", "edges": [ "X1", "X2" ], "failure_mode": "search refinements are mistaken for proof progress without a checked certificate", "polarity": "unknown", "delay": "medium", "gain": "unknown", "control_points": [ "proof checker run", "lemma obligation isolation" ], "observable_cues": [ "new derived obligations, proof frontier changes, checker diagnostics" ], "movement_jobs": [ "TEST", "WARN" ] }, { "loop_id": "L2", "type": "contradiction", "edges": [ "X3" ], "failure_mode": "proof and countermodel artifacts are produced under different encodings and falsely compared", "polarity": "mixed", "delay": "unknown", "gain": "high", "control_points": [ "shared formal encoding", "countermodel verification" ], "observable_cues": [ "countermodel pressure conflicts with a claimed proof path" ], "movement_jobs": [ "TEST", "WARN" ] } ], "option_moves": [ { "option_id": "O1", "move_type": "prove", "preconditions": [ "C1", "C2" ], "expected_effects": [ "X1", "X2" ], "tradeoffs": [ "strongest settlement if certificate checks", "can time out without resolving truth value" ], "blocking_unknowns": [ "U1", "U2" ], "review_gate": "none", "movement_jobs": [ "MOVE", "TEST" ] }, { "option_id": "O2", "move_type": "test", "preconditions": [ "C3" ], "expected_effects": [ "X3" ], "tradeoffs": [ "fast disproof if valid countermodel exists", "bounded search may miss models" ], "blocking_unknowns": [ "U1" ], "review_gate": "none", "movement_jobs": [ "MOVE", "TEST" ] }, { "option_id": "O3", "move_type": "revise", "preconditions": [ "C4" ], "expected_effects": [ "X5" ], "tradeoffs": [ "keeps unresolved status honest", "requires additional proof-engineering effort" ], "blocking_unknowns": [ "U2" ], "review_gate": "none", "movement_jobs": [ "MOVE", "WARN" ] } ], "triggers": [ { "trigger_id": "T1", "condition": "new_evidence", "affected_objects": [ "C3" ], "transition": "patch", "movement_jobs": [ "TRIGGER" ] }, { "trigger_id": "T2", "condition": "scope_change", "affected_objects": [ "K4" ], "transition": "scoped_rerun", "movement_jobs": [ "TRIGGER", "WARN" ] } ], "gates": [], "confidence_model": { "overall": "medium", "provenance_strength": "medium", "source_independence": "low", "recency": "high", "mechanism_fit": "high", "contradiction_load": "medium", "hidden_variable_risk": "medium", "adversarial_risk": "low", "adapter_fit": "high", "movement_jobs": [ "EVALUATE", "WARN" ] }, "decision_rendering": { "rendering_id": "R1", "summary": "Repeat-2 Map rendering: keep theorem status unresolved; require a checked proof certificate for proved status or a verified countermodel for not-entailed status under the frozen formalization.", "recommendation": "Run proof-certificate search and countermodel search against the same frozen encoding; patch on lemma or countermodel evidence and scoped-rerun if axioms or inference rules change.", "confidence": "medium", "depends_on": [ "C1", "C2", "C3", "C4", "U1", "U2", "O1", "O2", "O3", "TS1", "L1", "L2", "COUNCIL", "BT-2026-05-17-B01-FORMAL-FULL-R2" ], "movement_jobs": [ "EVALUATE", "TEST", "WARN" ] }, "review_log": [], "benchmark_trace": { "trace_id": "BT-2026-05-17-B01-FORMAL-FULL-R2", "suite_id": "ofone-v0.5-three-arm-evaluation", "cases_run": 1, "arms_run": [ "full_ofone" ], "model_families": 1, "superiority_ready": false, "diagnostics": [ "single repeat-2 benchmark run only", "no empirical superiority claim supported", "Batch 01 remains below release minimums" ], "case_id": "case-formal-proof-search-001", "run_id": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2", "case_file": "benchmarks/cases/formal-proof-search.md", "case_file_sha256": "sha256:01634155f084b1646ac6930ab1cdc4787575fff4daf285c017271e0e2719e756", "prompt_file": "benchmarks/runs/2026-05-17-batch-01/prompts/full_ofone.md", "prompt_file_sha256": "sha256:613afac8909b34accb57fd2c24217bb59a28a45860e32f36f6ec5f7f4ab5587e", "input_bundle_sha256": "sha256:fc0b94ca224173ad518f3f527356dbe998f29d3eb7ca6d4756e2b343def39c64", "movement_jobs": [ "BOUND", "WARN", "TRIGGER" ] }, "validator_result": { "passed": true, "diagnostics": [ { "code": "OFONE_JSON_SCHEMA", "severity": "info", "check": "json_schema", "object_id": null, "object_type": null, "path": null, "message": "Map artifact matches executable JSON Schema profile", "repair_hint": null }, { "code": "OFONE_ADAPTER_CONTRACT", "severity": "info", "check": "adapter_contract", "object_id": null, "object_type": null, "path": null, "message": "formal adapter contract loaded", "repair_hint": null }, { "code": "OFONE_BENCHMARK_TRACE", "severity": "warning", "check": "benchmark_trace", "object_id": null, "object_type": null, "path": null, "message": "benchmark_trace BT-2026-05-17-B01-FORMAL-FULL-R2 is not superiority-ready", "repair_hint": null }, { "code": "OFONE_DEPENDENCY_CLOSURE", "severity": "info", "check": "dependency_closure", "object_id": null, "object_type": null, "path": null, "message": "trigger T1: L2, O2, R1, T1, TS1, X3 [includes rendering]", "repair_hint": null }, { "code": "OFONE_DEPENDENCY_CLOSURE", "severity": "info", "check": "dependency_closure", "object_id": null, "object_type": null, "path": null, "message": "trigger T2: C1, C2, C3, COUNCIL, KT1, KT2, L1, L2, LENS1, O1, O2, O3, R1, SS1, SS3, T1, T2, TS1, X1, X2, X3, X4, X5 [includes rendering]", "repair_hint": null }, { "code": "OFONE_SEMANTIC_VALIDATION", "severity": "info", "check": "semantic_validation", "object_id": null, "object_type": null, "path": null, "message": "semantic graph checks completed", "repair_hint": null } ], "checks": [ { "check": "json_schema", "passed": true, "notes": "Map artifact matches executable JSON Schema profile", "code": "OFONE_JSON_SCHEMA", "severity": "info" }, { "check": "adapter_contract", "passed": true, "notes": "formal adapter contract loaded", "code": "OFONE_ADAPTER_CONTRACT", "severity": "info" }, { "check": "benchmark_trace", "passed": true, "notes": "benchmark_trace BT-2026-05-17-B01-FORMAL-FULL-R2 is not superiority-ready", "code": "OFONE_BENCHMARK_TRACE", "severity": "warning" }, { "check": "dependency_closure", "passed": true, "notes": "trigger T1: L2, O2, R1, T1, TS1, X3 [includes rendering]", "code": "OFONE_DEPENDENCY_CLOSURE", "severity": "info" }, { "check": "dependency_closure", "passed": true, "notes": "trigger T2: C1, C2, C3, COUNCIL, KT1, KT2, L1, L2, LENS1, O1, O2, O3, R1, SS1, SS3, T1, T2, TS1, X1, X2, X3, X4, X5 [includes rendering]", "code": "OFONE_DEPENDENCY_CLOSURE", "severity": "info" }, { "check": "semantic_validation", "passed": true, "notes": "semantic graph checks completed", "code": "OFONE_SEMANTIC_VALIDATION", "severity": "info" } ] } }