{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R4NJBLVYGONAQ5FU2WN4MZKNI6","short_pith_number":"pith:R4NJBLVY","schema_version":"1.0","canonical_sha256":"8f1a90aeb8339a0874b4d59bc6654d4786769b5362b7657934da1c196c6c264e","source":{"kind":"arxiv","id":"2603.25062","version":2},"attestation_state":"computed","paper":{"title":"SIGMA: Semantic Identifier Grouping for Molecular Autoregression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fei Dou, Jinbo Bi, Minghu Song, Xinyu Wang","submitted_at":"2026-03-26T05:55:17Z","abstract_excerpt":"Autoregressive molecular models assign probability to molecular serializations even though chemical identity is invariant to serialization. Equivalent serializations can therefore represent a common molecular identity yet induce inconsistent next-token decisions. Randomized strings broaden exposure, but do not reveal which intermediate decisions should agree. We introduce SIGMA, a dense suffix-position objective built from chemically certified same-suffix triplets: two equivalent histories, one non-equivalent history, and a shared suffix. SIGMA aligns corresponding pre-token hidden states alon"},"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":"2603.25062","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-26T05:55:17Z","cross_cats_sorted":[],"title_canon_sha256":"6ba74554eeaa6fd99ba27fbfad1472ee261ecf11f4231f6afcfd3c787a7b24ef","abstract_canon_sha256":"2a4e22bdc3b88b97f15271f60e59cfe69fdf04ec04bf7784a8533f1e493730b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:36:18.456887Z","signature_b64":"3FnqR1zGtSqq1Dw9YnSLU0dMntJA9iN/4rxfhOgye756PlBjWiDmtlRGf0V1DlNbNIfywxT4akoyTRLuIlgBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f1a90aeb8339a0874b4d59bc6654d4786769b5362b7657934da1c196c6c264e","last_reissued_at":"2026-08-04T00:36:18.455456Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:36:18.455456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SIGMA: Semantic Identifier Grouping for Molecular Autoregression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fei Dou, Jinbo Bi, Minghu Song, Xinyu Wang","submitted_at":"2026-03-26T05:55:17Z","abstract_excerpt":"Autoregressive molecular models assign probability to molecular serializations even though chemical identity is invariant to serialization. Equivalent serializations can therefore represent a common molecular identity yet induce inconsistent next-token decisions. Randomized strings broaden exposure, but do not reveal which intermediate decisions should agree. We introduce SIGMA, a dense suffix-position objective built from chemically certified same-suffix triplets: two equivalent histories, one non-equivalent history, and a shared suffix. SIGMA aligns corresponding pre-token hidden states alon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.25062","kind":"arxiv","version":2},"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/2603.25062/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":"2603.25062","created_at":"2026-08-04T00:36:18.456574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.25062v2","created_at":"2026-08-04T00:36:18.456574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.25062","created_at":"2026-08-04T00:36:18.456574+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4NJBLVYGONA","created_at":"2026-08-04T00:36:18.456574+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4NJBLVYGONAQ5FU","created_at":"2026-08-04T00:36:18.456574+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4NJBLVY","created_at":"2026-08-04T00:36:18.456574+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/R4NJBLVYGONAQ5FU2WN4MZKNI6","json":"https://pith.science/pith/R4NJBLVYGONAQ5FU2WN4MZKNI6.json","graph_json":"https://pith.science/api/pith-number/R4NJBLVYGONAQ5FU2WN4MZKNI6/graph.json","events_json":"https://pith.science/api/pith-number/R4NJBLVYGONAQ5FU2WN4MZKNI6/events.json","paper":"https://pith.science/paper/R4NJBLVY"},"agent_actions":{"view_html":"https://pith.science/pith/R4NJBLVYGONAQ5FU2WN4MZKNI6","download_json":"https://pith.science/pith/R4NJBLVYGONAQ5FU2WN4MZKNI6.json","view_paper":"https://pith.science/paper/R4NJBLVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.25062&json=true","fetch_graph":"https://pith.science/api/pith-number/R4NJBLVYGONAQ5FU2WN4MZKNI6/graph.json","fetch_events":"https://pith.science/api/pith-number/R4NJBLVYGONAQ5FU2WN4MZKNI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4NJBLVYGONAQ5FU2WN4MZKNI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4NJBLVYGONAQ5FU2WN4MZKNI6/action/storage_attestation","attest_author":"https://pith.science/pith/R4NJBLVYGONAQ5FU2WN4MZKNI6/action/author_attestation","sign_citation":"https://pith.science/pith/R4NJBLVYGONAQ5FU2WN4MZKNI6/action/citation_signature","submit_replication":"https://pith.science/pith/R4NJBLVYGONAQ5FU2WN4MZKNI6/action/replication_record"}},"created_at":"2026-08-04T00:36:18.456574+00:00","updated_at":"2026-08-04T00:36:18.456574+00:00"}