{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OW74HKNXMCQ2PUUMMLXLE3PPQL","short_pith_number":"pith:OW74HKNX","schema_version":"1.0","canonical_sha256":"75bfc3a9b760a1a7d28c62eeb26def82d159025857aaf574e1a39e4cb1a78045","source":{"kind":"arxiv","id":"2606.03660","version":1},"attestation_state":"computed","paper":{"title":"From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gongbo Zhang, Hao Li, He Cao, Hongyu Guo, Li Yuan","submitted_at":"2026-06-02T13:47:19Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.03660","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T13:47:19Z","cross_cats_sorted":[],"title_canon_sha256":"2a512bb4f6c73f2b0265db25e753b4255765468fb944fc3bdc84ad3397a10b8a","abstract_canon_sha256":"696673730e861d31c62cc1d1ab882ca1187b3c00fccdc8838a4e6ed924cd0c74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:06:03.764521Z","signature_b64":"uYfHH7Cc4BqUSsKUHecebPiDLO6bPklmCw078BNewyKSWElW9DzAM3ti7p+Bk3Mc2vJAu0ayjTogpdgxun2gAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75bfc3a9b760a1a7d28c62eeb26def82d159025857aaf574e1a39e4cb1a78045","last_reissued_at":"2026-06-03T01:06:03.764103Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:06:03.764103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gongbo Zhang, Hao Li, He Cao, Hongyu Guo, Li Yuan","submitted_at":"2026-06-02T13:47:19Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03660","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.03660/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.03660","created_at":"2026-06-03T01:06:03.764158+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03660v1","created_at":"2026-06-03T01:06:03.764158+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03660","created_at":"2026-06-03T01:06:03.764158+00:00"},{"alias_kind":"pith_short_12","alias_value":"OW74HKNXMCQ2","created_at":"2026-06-03T01:06:03.764158+00:00"},{"alias_kind":"pith_short_16","alias_value":"OW74HKNXMCQ2PUUM","created_at":"2026-06-03T01:06:03.764158+00:00"},{"alias_kind":"pith_short_8","alias_value":"OW74HKNX","created_at":"2026-06-03T01:06:03.764158+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OW74HKNXMCQ2PUUMMLXLE3PPQL","json":"https://pith.science/pith/OW74HKNXMCQ2PUUMMLXLE3PPQL.json","graph_json":"https://pith.science/api/pith-number/OW74HKNXMCQ2PUUMMLXLE3PPQL/graph.json","events_json":"https://pith.science/api/pith-number/OW74HKNXMCQ2PUUMMLXLE3PPQL/events.json","paper":"https://pith.science/paper/OW74HKNX"},"agent_actions":{"view_html":"https://pith.science/pith/OW74HKNXMCQ2PUUMMLXLE3PPQL","download_json":"https://pith.science/pith/OW74HKNXMCQ2PUUMMLXLE3PPQL.json","view_paper":"https://pith.science/paper/OW74HKNX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03660&json=true","fetch_graph":"https://pith.science/api/pith-number/OW74HKNXMCQ2PUUMMLXLE3PPQL/graph.json","fetch_events":"https://pith.science/api/pith-number/OW74HKNXMCQ2PUUMMLXLE3PPQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OW74HKNXMCQ2PUUMMLXLE3PPQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OW74HKNXMCQ2PUUMMLXLE3PPQL/action/storage_attestation","attest_author":"https://pith.science/pith/OW74HKNXMCQ2PUUMMLXLE3PPQL/action/author_attestation","sign_citation":"https://pith.science/pith/OW74HKNXMCQ2PUUMMLXLE3PPQL/action/citation_signature","submit_replication":"https://pith.science/pith/OW74HKNXMCQ2PUUMMLXLE3PPQL/action/replication_record"}},"created_at":"2026-06-03T01:06:03.764158+00:00","updated_at":"2026-06-03T01:06:03.764158+00:00"}