{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MZTCQ2KRDZLGMUQKI4BNH5WVQX","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":"b0732cba18636e8e9082f9bea17a9c738059d58a7c8d3abfd59baf29725276a1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-25T17:48:09Z","title_canon_sha256":"da86d2a24fdd20a3dd711ae9d157adc2c690e779136466f6df6516d599949948"},"schema_version":"1.0","source":{"id":"2204.11817","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.11817","created_at":"2026-07-05T05:13:06Z"},{"alias_kind":"arxiv_version","alias_value":"2204.11817v3","created_at":"2026-07-05T05:13:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.11817","created_at":"2026-07-05T05:13:06Z"},{"alias_kind":"pith_short_12","alias_value":"MZTCQ2KRDZLG","created_at":"2026-07-05T05:13:06Z"},{"alias_kind":"pith_short_16","alias_value":"MZTCQ2KRDZLGMUQK","created_at":"2026-07-05T05:13:06Z"},{"alias_kind":"pith_short_8","alias_value":"MZTCQ2KR","created_at":"2026-07-05T05:13:06Z"}],"graph_snapshots":[{"event_id":"sha256:22b3405bb16cc39b9a90adfe655f1cbfd29519db49be14fe2ccdee6463d3862a","target":"graph","created_at":"2026-07-05T05:13:06Z","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/2204.11817/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present $\\textbf{MolT5}$ $-$ a self-supervised learning framework for pretraining models on a vast amount of unlabeled natural language text and molecule strings. $\\textbf{MolT5}$ allows for new, useful, and challenging analogs of traditional vision-language tasks, such as molecule captioning and text-based de novo molecule generation (altogether: translation between molecules and language), which we explore for the first time. Since $\\textbf{MolT5}$ pretrains models on single-modal data, it helps overcome the chemistry domain shortcoming of data scarcity. Furthermore, we consider several m","authors_text":"Carl Edwards, Garrett Honke, Heng Ji, Kevin Ros, Kyunghyun Cho, Tuan Lai","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-25T17:48:09Z","title":"Translation between Molecules and Natural Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.11817","kind":"arxiv","version":3},"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":"sha256:9f6a58a7dd930700869e8644d94a451383335ac13df250891cab7a7a2e847144","target":"record","created_at":"2026-07-05T05:13:06Z","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":"b0732cba18636e8e9082f9bea17a9c738059d58a7c8d3abfd59baf29725276a1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-25T17:48:09Z","title_canon_sha256":"da86d2a24fdd20a3dd711ae9d157adc2c690e779136466f6df6516d599949948"},"schema_version":"1.0","source":{"id":"2204.11817","kind":"arxiv","version":3}},"canonical_sha256":"66662869511e5666520a4702d3f6d585d9d32b246a417045de9bb0b3dbc69a0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66662869511e5666520a4702d3f6d585d9d32b246a417045de9bb0b3dbc69a0d","first_computed_at":"2026-07-05T05:13:06.484747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:06.484747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lODBV7WRng4nfApU0Neyp1A33xLE+3XjyBN3um7xCtfInWU9qSXfHDhcMku0upcXuYQdMlgG9Uh4XqAGL96pBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:06.485175Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.11817","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f6a58a7dd930700869e8644d94a451383335ac13df250891cab7a7a2e847144","sha256:22b3405bb16cc39b9a90adfe655f1cbfd29519db49be14fe2ccdee6463d3862a"],"state_sha256":"a8dd324556b20f58f08275180f3868ae483c3845f1a7100e71fe673910cd54e3"}