{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DRDPAT4DH6P7CO5O37MWC4QB5P","short_pith_number":"pith:DRDPAT4D","schema_version":"1.0","canonical_sha256":"1c46f04f833f9ff13baedfd9617201ebce9790921250cad59aa628c9efe50941","source":{"kind":"arxiv","id":"2502.06634","version":1},"attestation_state":"computed","paper":{"title":"Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Davide Mottin, Haoyu Guo, Kuangyu Zhou, Simon Sataa-Yu Larsen, Tao Tang, Zhiqiang Zhong","submitted_at":"2025-02-10T16:29:21Z","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"},"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":"2502.06634","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T16:29:21Z","cross_cats_sorted":["cs.AI","q-bio.BM"],"title_canon_sha256":"63c904d32ff6f92546aaa37e7bd8926ec3119e39aa7dda86938b5b1cf0cb0bce","abstract_canon_sha256":"893a18d804e4a35d71e582fd947540df867039b602e19341634a8031c58d2cd3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:09.871551Z","signature_b64":"tnOEjizRj8meWrurTWbyP1LfZEPDoz7W7mqX80E+As/JSCEvchkIFiPwWqrdorpX12KD5F7HA1aRKow45PmsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c46f04f833f9ff13baedfd9617201ebce9790921250cad59aa628c9efe50941","last_reissued_at":"2026-07-05T10:12:09.871014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:09.871014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Davide Mottin, Haoyu Guo, Kuangyu Zhou, Simon Sataa-Yu Larsen, Tao Tang, Zhiqiang Zhong","submitted_at":"2025-02-10T16:29:21Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06634","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/2502.06634/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":"2502.06634","created_at":"2026-07-05T10:12:09.871067+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06634v1","created_at":"2026-07-05T10:12:09.871067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06634","created_at":"2026-07-05T10:12:09.871067+00:00"},{"alias_kind":"pith_short_12","alias_value":"DRDPAT4DH6P7","created_at":"2026-07-05T10:12:09.871067+00:00"},{"alias_kind":"pith_short_16","alias_value":"DRDPAT4DH6P7CO5O","created_at":"2026-07-05T10:12:09.871067+00:00"},{"alias_kind":"pith_short_8","alias_value":"DRDPAT4D","created_at":"2026-07-05T10:12:09.871067+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/DRDPAT4DH6P7CO5O37MWC4QB5P","json":"https://pith.science/pith/DRDPAT4DH6P7CO5O37MWC4QB5P.json","graph_json":"https://pith.science/api/pith-number/DRDPAT4DH6P7CO5O37MWC4QB5P/graph.json","events_json":"https://pith.science/api/pith-number/DRDPAT4DH6P7CO5O37MWC4QB5P/events.json","paper":"https://pith.science/paper/DRDPAT4D"},"agent_actions":{"view_html":"https://pith.science/pith/DRDPAT4DH6P7CO5O37MWC4QB5P","download_json":"https://pith.science/pith/DRDPAT4DH6P7CO5O37MWC4QB5P.json","view_paper":"https://pith.science/paper/DRDPAT4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06634&json=true","fetch_graph":"https://pith.science/api/pith-number/DRDPAT4DH6P7CO5O37MWC4QB5P/graph.json","fetch_events":"https://pith.science/api/pith-number/DRDPAT4DH6P7CO5O37MWC4QB5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DRDPAT4DH6P7CO5O37MWC4QB5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DRDPAT4DH6P7CO5O37MWC4QB5P/action/storage_attestation","attest_author":"https://pith.science/pith/DRDPAT4DH6P7CO5O37MWC4QB5P/action/author_attestation","sign_citation":"https://pith.science/pith/DRDPAT4DH6P7CO5O37MWC4QB5P/action/citation_signature","submit_replication":"https://pith.science/pith/DRDPAT4DH6P7CO5O37MWC4QB5P/action/replication_record"}},"created_at":"2026-07-05T10:12:09.871067+00:00","updated_at":"2026-07-05T10:12:09.871067+00:00"}