{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DRDPAT4DH6P7CO5O37MWC4QB5P","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":"893a18d804e4a35d71e582fd947540df867039b602e19341634a8031c58d2cd3","cross_cats_sorted":["cs.AI","q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T16:29:21Z","title_canon_sha256":"63c904d32ff6f92546aaa37e7bd8926ec3119e39aa7dda86938b5b1cf0cb0bce"},"schema_version":"1.0","source":{"id":"2502.06634","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06634","created_at":"2026-07-05T10:12:09Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06634v1","created_at":"2026-07-05T10:12:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06634","created_at":"2026-07-05T10:12:09Z"},{"alias_kind":"pith_short_12","alias_value":"DRDPAT4DH6P7","created_at":"2026-07-05T10:12:09Z"},{"alias_kind":"pith_short_16","alias_value":"DRDPAT4DH6P7CO5O","created_at":"2026-07-05T10:12:09Z"},{"alias_kind":"pith_short_8","alias_value":"DRDPAT4D","created_at":"2026-07-05T10:12:09Z"}],"graph_snapshots":[{"event_id":"sha256:e805466c571a1cdcdea02dbed9cff2c086dccb95cd897fd615eaa23e4713687b","target":"graph","created_at":"2026-07-05T10:12:09Z","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/2502.06634/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in AI for biological research focus on integrating molecular data with natural language to accelerate drug discovery. However, the scarcity of high-quality annotations limits progress in this area. This paper introduces LA$^3$, a Language-based Automatic Annotation Augmentation framework that leverages large language models to augment existing datasets, thereby improving AI training. We demonstrate the effectiveness of LA$^3$ by creating an enhanced dataset, LaChEBI-20, where we systematically rewrite the annotations of molecules from an established dataset. These rewritten","authors_text":"Davide Mottin, Haoyu Guo, Kuangyu Zhou, Simon Sataa-Yu Larsen, Tao Tang, Zhiqiang Zhong","cross_cats":["cs.AI","q-bio.BM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T16:29:21Z","title":"Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06634","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":"sha256:0948216d5ceb7a56f7680f9130bf8180c646f0ef7326281266f41ebefb1fc615","target":"record","created_at":"2026-07-05T10:12:09Z","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":"893a18d804e4a35d71e582fd947540df867039b602e19341634a8031c58d2cd3","cross_cats_sorted":["cs.AI","q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T16:29:21Z","title_canon_sha256":"63c904d32ff6f92546aaa37e7bd8926ec3119e39aa7dda86938b5b1cf0cb0bce"},"schema_version":"1.0","source":{"id":"2502.06634","kind":"arxiv","version":1}},"canonical_sha256":"1c46f04f833f9ff13baedfd9617201ebce9790921250cad59aa628c9efe50941","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c46f04f833f9ff13baedfd9617201ebce9790921250cad59aa628c9efe50941","first_computed_at":"2026-07-05T10:12:09.871014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:09.871014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tnOEjizRj8meWrurTWbyP1LfZEPDoz7W7mqX80E+As/JSCEvchkIFiPwWqrdorpX12KD5F7HA1aRKow45PmsCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:09.871551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06634","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0948216d5ceb7a56f7680f9130bf8180c646f0ef7326281266f41ebefb1fc615","sha256:e805466c571a1cdcdea02dbed9cff2c086dccb95cd897fd615eaa23e4713687b"],"state_sha256":"ac621fde2a51c9f2607cda25c02bc52fc61ef21dc76678ced2ea9ca97b6188cc"}