{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OW74HKNXMCQ2PUUMMLXLE3PPQL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"696673730e861d31c62cc1d1ab882ca1187b3c00fccdc8838a4e6ed924cd0c74","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T13:47:19Z","title_canon_sha256":"2a512bb4f6c73f2b0265db25e753b4255765468fb944fc3bdc84ad3397a10b8a"},"schema_version":"1.0","source":{"id":"2606.03660","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03660","created_at":"2026-06-03T01:06:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03660v1","created_at":"2026-06-03T01:06:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03660","created_at":"2026-06-03T01:06:03Z"},{"alias_kind":"pith_short_12","alias_value":"OW74HKNXMCQ2","created_at":"2026-06-03T01:06:03Z"},{"alias_kind":"pith_short_16","alias_value":"OW74HKNXMCQ2PUUM","created_at":"2026-06-03T01:06:03Z"},{"alias_kind":"pith_short_8","alias_value":"OW74HKNX","created_at":"2026-06-03T01:06:03Z"}],"graph_snapshots":[{"event_id":"sha256:05b9f535380a26af0a78c7c98009f2dc65a39f3405262a440ed6458f72d9a860","target":"graph","created_at":"2026-06-03T01:06:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.03660/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are increasingly used as chemistry assistants, yet most chemistry benchmarks still score only final answers. This masks a critical failure mode: a model may output the correct molecule, product, or option while its reasoning violates chemical logic. Existing process-level evaluators are hard to scale because LLM judges and human step-level process annotation are costly, inconsistent, and vulnerable to hallucination. We introduce ChemCoTBench-V2, a rule-verifiable diagnostic benchmark for low-cost, auditable evaluation of structured, verifier-addressable chemical reasoning","authors_text":"Gongbo Zhang, Hao Li, He Cao, Hongyu Guo, Li Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T13:47:19Z","title":"From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03660","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4e597e18fb569e1147f68198dac8134c4c43adf810328830942739df4b120899","target":"record","created_at":"2026-06-03T01:06:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"696673730e861d31c62cc1d1ab882ca1187b3c00fccdc8838a4e6ed924cd0c74","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T13:47:19Z","title_canon_sha256":"2a512bb4f6c73f2b0265db25e753b4255765468fb944fc3bdc84ad3397a10b8a"},"schema_version":"1.0","source":{"id":"2606.03660","kind":"arxiv","version":1}},"canonical_sha256":"75bfc3a9b760a1a7d28c62eeb26def82d159025857aaf574e1a39e4cb1a78045","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75bfc3a9b760a1a7d28c62eeb26def82d159025857aaf574e1a39e4cb1a78045","first_computed_at":"2026-06-03T01:06:03.764103Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:06:03.764103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uYfHH7Cc4BqUSsKUHecebPiDLO6bPklmCw078BNewyKSWElW9DzAM3ti7p+Bk3Mc2vJAu0ayjTogpdgxun2gAw==","signature_status":"signed_v1","signed_at":"2026-06-03T01:06:03.764521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03660","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e597e18fb569e1147f68198dac8134c4c43adf810328830942739df4b120899","sha256:05b9f535380a26af0a78c7c98009f2dc65a39f3405262a440ed6458f72d9a860"],"state_sha256":"bc5068f0bd2b544a45bbaed464affabb026c29691a759829d54b52d30290a658"}