{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OPNUOH5JYZJTFMD7ACOS7W73OY","short_pith_number":"pith:OPNUOH5J","schema_version":"1.0","canonical_sha256":"73db471fa9c65332b07f009d2fdbfb76158227cb8282ea9fa42e2a7569c590ab","source":{"kind":"arxiv","id":"2108.10307","version":1},"attestation_state":"computed","paper":{"title":"C5T5: Controllable Generation of Organic Molecules with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alex Tamkin, Daniel Rothchild, Joseph Gonzalez, Julie Yu, Ujval Misra","submitted_at":"2021-08-23T17:53:07Z","abstract_excerpt":"Methods for designing organic materials with desired properties have high potential impact across fields such as medicine, renewable energy, petrochemical engineering, and agriculture. However, using generative modeling to design substances with desired properties is difficult because candidate compounds must satisfy multiple constraints, including synthetic accessibility and other metrics that are intuitive to domain experts but challenging to quantify. We propose C5T5, a novel self-supervised pretraining method that enables transformers to make zero-shot select-and-replace edits, altering or"},"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":"2108.10307","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-23T17:53:07Z","cross_cats_sorted":[],"title_canon_sha256":"e8d679e3170b8184511b229ca9ccf00aad15e5cd46d52169b7551a890b865616","abstract_canon_sha256":"c48025cbfe5031cf09f8e80144c5f8de653214d872660f883cb2719b64ba45d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:08:04.306022Z","signature_b64":"SkYOHl8NIuSHNrYxfsXIGP6fr+vQbaz3Oyty3YCtN5fKWA7mUxl+AqnbMTQ1XAqPNYTRKC1Cl/NcVW5UFGv0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73db471fa9c65332b07f009d2fdbfb76158227cb8282ea9fa42e2a7569c590ab","last_reissued_at":"2026-07-05T03:08:04.305565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:08:04.305565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"C5T5: Controllable Generation of Organic Molecules with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alex Tamkin, Daniel Rothchild, Joseph Gonzalez, Julie Yu, Ujval Misra","submitted_at":"2021-08-23T17:53:07Z","abstract_excerpt":"Methods for designing organic materials with desired properties have high potential impact across fields such as medicine, renewable energy, petrochemical engineering, and agriculture. However, using generative modeling to design substances with desired properties is difficult because candidate compounds must satisfy multiple constraints, including synthetic accessibility and other metrics that are intuitive to domain experts but challenging to quantify. We propose C5T5, a novel self-supervised pretraining method that enables transformers to make zero-shot select-and-replace edits, altering or"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.10307","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/2108.10307/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":"2108.10307","created_at":"2026-07-05T03:08:04.305623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.10307v1","created_at":"2026-07-05T03:08:04.305623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.10307","created_at":"2026-07-05T03:08:04.305623+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPNUOH5JYZJT","created_at":"2026-07-05T03:08:04.305623+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPNUOH5JYZJTFMD7","created_at":"2026-07-05T03:08:04.305623+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPNUOH5J","created_at":"2026-07-05T03:08:04.305623+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/OPNUOH5JYZJTFMD7ACOS7W73OY","json":"https://pith.science/pith/OPNUOH5JYZJTFMD7ACOS7W73OY.json","graph_json":"https://pith.science/api/pith-number/OPNUOH5JYZJTFMD7ACOS7W73OY/graph.json","events_json":"https://pith.science/api/pith-number/OPNUOH5JYZJTFMD7ACOS7W73OY/events.json","paper":"https://pith.science/paper/OPNUOH5J"},"agent_actions":{"view_html":"https://pith.science/pith/OPNUOH5JYZJTFMD7ACOS7W73OY","download_json":"https://pith.science/pith/OPNUOH5JYZJTFMD7ACOS7W73OY.json","view_paper":"https://pith.science/paper/OPNUOH5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.10307&json=true","fetch_graph":"https://pith.science/api/pith-number/OPNUOH5JYZJTFMD7ACOS7W73OY/graph.json","fetch_events":"https://pith.science/api/pith-number/OPNUOH5JYZJTFMD7ACOS7W73OY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPNUOH5JYZJTFMD7ACOS7W73OY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPNUOH5JYZJTFMD7ACOS7W73OY/action/storage_attestation","attest_author":"https://pith.science/pith/OPNUOH5JYZJTFMD7ACOS7W73OY/action/author_attestation","sign_citation":"https://pith.science/pith/OPNUOH5JYZJTFMD7ACOS7W73OY/action/citation_signature","submit_replication":"https://pith.science/pith/OPNUOH5JYZJTFMD7ACOS7W73OY/action/replication_record"}},"created_at":"2026-07-05T03:08:04.305623+00:00","updated_at":"2026-07-05T03:08:04.305623+00:00"}