{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V4XWZZW24XRP2FWAAV52YMJF77","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":"dcf6d974f4eebf5fd49b4ef7283c11af21e84b76cced29365c1b1ff370e1348b","cross_cats_sorted":["q-bio.BM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-07T07:32:55Z","title_canon_sha256":"1bff57c9adcd505c8ceb019c2920d4b44019cb9c33e78882e8131da92753a38b"},"schema_version":"1.0","source":{"id":"2412.05569","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05569","created_at":"2026-07-05T11:17:38Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05569v2","created_at":"2026-07-05T11:17:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05569","created_at":"2026-07-05T11:17:38Z"},{"alias_kind":"pith_short_12","alias_value":"V4XWZZW24XRP","created_at":"2026-07-05T11:17:38Z"},{"alias_kind":"pith_short_16","alias_value":"V4XWZZW24XRP2FWA","created_at":"2026-07-05T11:17:38Z"},{"alias_kind":"pith_short_8","alias_value":"V4XWZZW2","created_at":"2026-07-05T11:17:38Z"}],"graph_snapshots":[{"event_id":"sha256:e4db0e860ee5d9be99d7d77c9b69a49511343cdcb5569915373816c0d8029778","target":"graph","created_at":"2026-07-05T11:17:38Z","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/2412.05569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"SMILES, a crucial textual representation of molecular structures, has garnered significant attention as a foundation for pre-trained language models (LMs). However, most existing pre-trained SMILES LMs focus solely on the single-token level supervision during pre-training, failing to fully leverage the substructural information of molecules. This limitation makes the pre-training task overly simplistic, preventing the models from capturing richer molecular semantic information. Moreover, during pre-training, these SMILES LMs only process corrupted SMILES inputs, never encountering any valid SM","authors_text":"Bin Feng, Junwei Yang, Kangjie Zheng, Ming Zhang, Siyue Liang, Wei Ju, Zequn Liu, Zhiping Xiao","cross_cats":["q-bio.BM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-07T07:32:55Z","title":"SMI-Editor: Edit-based SMILES Language Model with Fragment-level Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05569","kind":"arxiv","version":2},"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:d2f64cdc473bcdc5024aa33c99ef7fac517180670cc0dd1edd5e2eccebf1c7fb","target":"record","created_at":"2026-07-05T11:17:38Z","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":"dcf6d974f4eebf5fd49b4ef7283c11af21e84b76cced29365c1b1ff370e1348b","cross_cats_sorted":["q-bio.BM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-07T07:32:55Z","title_canon_sha256":"1bff57c9adcd505c8ceb019c2920d4b44019cb9c33e78882e8131da92753a38b"},"schema_version":"1.0","source":{"id":"2412.05569","kind":"arxiv","version":2}},"canonical_sha256":"af2f6ce6dae5e2fd16c0057bac3125ffdbdaed6d3a1dfca0bf2b3c8f14da4d5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af2f6ce6dae5e2fd16c0057bac3125ffdbdaed6d3a1dfca0bf2b3c8f14da4d5c","first_computed_at":"2026-07-05T11:17:38.682716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:38.682716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kaKBB7lrS9hgsmRQpFCFT2j/mPx+qbpqDzowuVoo3QXMsmDc/oPSkbRFec4BXb0nXhefdjFRZ8cear8zu6W3Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:38.683202Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.05569","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2f64cdc473bcdc5024aa33c99ef7fac517180670cc0dd1edd5e2eccebf1c7fb","sha256:e4db0e860ee5d9be99d7d77c9b69a49511343cdcb5569915373816c0d8029778"],"state_sha256":"d1e83097dfee5f421199cde7cc2d0d58a3fe1b669d6b77b0b14a0ff87d198fca"}