{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:73CTECDJQUSYXKAYWPXM52R3SJ","short_pith_number":"pith:73CTECDJ","schema_version":"1.0","canonical_sha256":"fec532086985258ba818b3eeceea3b924790be89d16c9c6c94c0f8a5132c2a2c","source":{"kind":"arxiv","id":"2608.02595","version":1},"attestation_state":"computed","paper":{"title":"onepot-Bench 0: towards lab-aware in silico chemistry benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrei S. Tyrin, Brandon Wang, Daniil A. Boiko","submitted_at":"2026-08-03T17:58:27Z","abstract_excerpt":"Language models are playing an increasingly important role in laboratory science, performing tasks such as experiment planning, execution, and post-hoc analysis. However, precisely measuring their abilities is difficult, as scientific capabilities require a mixture of both problem-solving skills and domain-specific intuition. Existing evaluations rarely measure the capabilities required to make reliable decisions in a physical laboratory and often rely on public data that may have appeared in model training corpora.\n  We introduce onepot-Bench 0, a proprietary benchmark suite for evaluating la"},"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":"2608.02595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T17:58:27Z","cross_cats_sorted":[],"title_canon_sha256":"50bd192476dffd39e1bcfe54fca747e2a378835ac83de52ec093a8d52a2b3baf","abstract_canon_sha256":"e699338f9668be825d49081991e0869688b4a69ee6269a03f0c4863108578538"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:44:20.309674Z","signature_b64":"3rbmJv4YY+c0IR6rKj9fzg4WdhJqHgeX8ZsoGvzlgqAFlHZ2e55rAxa6oieG0FQenYOCGETGPbF6DJwIbE/1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fec532086985258ba818b3eeceea3b924790be89d16c9c6c94c0f8a5132c2a2c","last_reissued_at":"2026-08-04T02:44:20.307356Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:44:20.307356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"onepot-Bench 0: towards lab-aware in silico chemistry benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrei S. Tyrin, Brandon Wang, Daniil A. Boiko","submitted_at":"2026-08-03T17:58:27Z","abstract_excerpt":"Language models are playing an increasingly important role in laboratory science, performing tasks such as experiment planning, execution, and post-hoc analysis. However, precisely measuring their abilities is difficult, as scientific capabilities require a mixture of both problem-solving skills and domain-specific intuition. Existing evaluations rarely measure the capabilities required to make reliable decisions in a physical laboratory and often rely on public data that may have appeared in model training corpora.\n  We introduce onepot-Bench 0, a proprietary benchmark suite for evaluating la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02595","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/2608.02595/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":"2608.02595","created_at":"2026-08-04T02:44:20.309724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.02595v1","created_at":"2026-08-04T02:44:20.309724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02595","created_at":"2026-08-04T02:44:20.309724+00:00"},{"alias_kind":"pith_short_12","alias_value":"73CTECDJQUSY","created_at":"2026-08-04T02:44:20.309724+00:00"},{"alias_kind":"pith_short_16","alias_value":"73CTECDJQUSYXKAY","created_at":"2026-08-04T02:44:20.309724+00:00"},{"alias_kind":"pith_short_8","alias_value":"73CTECDJ","created_at":"2026-08-04T02:44:20.309724+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/73CTECDJQUSYXKAYWPXM52R3SJ","json":"https://pith.science/pith/73CTECDJQUSYXKAYWPXM52R3SJ.json","graph_json":"https://pith.science/api/pith-number/73CTECDJQUSYXKAYWPXM52R3SJ/graph.json","events_json":"https://pith.science/api/pith-number/73CTECDJQUSYXKAYWPXM52R3SJ/events.json","paper":"https://pith.science/paper/73CTECDJ"},"agent_actions":{"view_html":"https://pith.science/pith/73CTECDJQUSYXKAYWPXM52R3SJ","download_json":"https://pith.science/pith/73CTECDJQUSYXKAYWPXM52R3SJ.json","view_paper":"https://pith.science/paper/73CTECDJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.02595&json=true","fetch_graph":"https://pith.science/api/pith-number/73CTECDJQUSYXKAYWPXM52R3SJ/graph.json","fetch_events":"https://pith.science/api/pith-number/73CTECDJQUSYXKAYWPXM52R3SJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73CTECDJQUSYXKAYWPXM52R3SJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73CTECDJQUSYXKAYWPXM52R3SJ/action/storage_attestation","attest_author":"https://pith.science/pith/73CTECDJQUSYXKAYWPXM52R3SJ/action/author_attestation","sign_citation":"https://pith.science/pith/73CTECDJQUSYXKAYWPXM52R3SJ/action/citation_signature","submit_replication":"https://pith.science/pith/73CTECDJQUSYXKAYWPXM52R3SJ/action/replication_record"}},"created_at":"2026-08-04T02:44:20.309724+00:00","updated_at":"2026-08-04T02:44:20.309724+00:00"}