{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VYD6A6A5YSB3ELWXOSLXIRWMCT","short_pith_number":"pith:VYD6A6A5","schema_version":"1.0","canonical_sha256":"ae07e0781dc483b22ed774977446cc14da44738d40d8bd0f7bfa3f6c448a9819","source":{"kind":"arxiv","id":"2106.09553","version":3},"attestation_state":"computed","paper":{"title":"Large-Scale Chemical Language Representations Capture Molecular Structure and Properties","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Brian Belgodere, Inkit Padhi, Jerret Ross, Payel Das, Vijil Chenthamarakshan, Youssef Mroueh","submitted_at":"2021-06-17T14:33:55Z","abstract_excerpt":"Models based on machine learning can enable accurate and fast molecular property predictions, which is of interest in drug discovery and material design. Various supervised machine learning models have demonstrated promising performance, but the vast chemical space and the limited availability of property labels make supervised learning challenging. Recently, unsupervised transformer-based language models pretrained on a large unlabelled corpus have produced state-of-the-art results in many downstream natural language processing tasks. Inspired by this development, we present molecular embeddi"},"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":"2106.09553","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-17T14:33:55Z","cross_cats_sorted":["cs.CL","q-bio.BM"],"title_canon_sha256":"66aca5ec4adbb50fe6e2b943160d25acdfaeb1346374e1743334df6a6f6eb878","abstract_canon_sha256":"e2c92a52e717dbce9e657353c42f7c4746ccc778ea5ab2c399a695a6e263309a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:12.110475Z","signature_b64":"UTwHcPQnZ6Dw0GvjRz2hYDPxAUcN66vI+tqyCPBhaKqm8iUTJYB+XkHzit77IM5iftiKlMJjuZmoWRwiv0isAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae07e0781dc483b22ed774977446cc14da44738d40d8bd0f7bfa3f6c448a9819","last_reissued_at":"2026-07-05T05:25:12.109903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:12.109903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-Scale Chemical Language Representations Capture Molecular Structure and Properties","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Brian Belgodere, Inkit Padhi, Jerret Ross, Payel Das, Vijil Chenthamarakshan, Youssef Mroueh","submitted_at":"2021-06-17T14:33:55Z","abstract_excerpt":"Models based on machine learning can enable accurate and fast molecular property predictions, which is of interest in drug discovery and material design. Various supervised machine learning models have demonstrated promising performance, but the vast chemical space and the limited availability of property labels make supervised learning challenging. Recently, unsupervised transformer-based language models pretrained on a large unlabelled corpus have produced state-of-the-art results in many downstream natural language processing tasks. Inspired by this development, we present molecular embeddi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09553","kind":"arxiv","version":3},"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/2106.09553/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":"2106.09553","created_at":"2026-07-05T05:25:12.109967+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09553v3","created_at":"2026-07-05T05:25:12.109967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09553","created_at":"2026-07-05T05:25:12.109967+00:00"},{"alias_kind":"pith_short_12","alias_value":"VYD6A6A5YSB3","created_at":"2026-07-05T05:25:12.109967+00:00"},{"alias_kind":"pith_short_16","alias_value":"VYD6A6A5YSB3ELWX","created_at":"2026-07-05T05:25:12.109967+00:00"},{"alias_kind":"pith_short_8","alias_value":"VYD6A6A5","created_at":"2026-07-05T05:25:12.109967+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2211.09085","citing_title":"Galactica: A Large Language Model for Science","ref_index":229,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VYD6A6A5YSB3ELWXOSLXIRWMCT","json":"https://pith.science/pith/VYD6A6A5YSB3ELWXOSLXIRWMCT.json","graph_json":"https://pith.science/api/pith-number/VYD6A6A5YSB3ELWXOSLXIRWMCT/graph.json","events_json":"https://pith.science/api/pith-number/VYD6A6A5YSB3ELWXOSLXIRWMCT/events.json","paper":"https://pith.science/paper/VYD6A6A5"},"agent_actions":{"view_html":"https://pith.science/pith/VYD6A6A5YSB3ELWXOSLXIRWMCT","download_json":"https://pith.science/pith/VYD6A6A5YSB3ELWXOSLXIRWMCT.json","view_paper":"https://pith.science/paper/VYD6A6A5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09553&json=true","fetch_graph":"https://pith.science/api/pith-number/VYD6A6A5YSB3ELWXOSLXIRWMCT/graph.json","fetch_events":"https://pith.science/api/pith-number/VYD6A6A5YSB3ELWXOSLXIRWMCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VYD6A6A5YSB3ELWXOSLXIRWMCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VYD6A6A5YSB3ELWXOSLXIRWMCT/action/storage_attestation","attest_author":"https://pith.science/pith/VYD6A6A5YSB3ELWXOSLXIRWMCT/action/author_attestation","sign_citation":"https://pith.science/pith/VYD6A6A5YSB3ELWXOSLXIRWMCT/action/citation_signature","submit_replication":"https://pith.science/pith/VYD6A6A5YSB3ELWXOSLXIRWMCT/action/replication_record"}},"created_at":"2026-07-05T05:25:12.109967+00:00","updated_at":"2026-07-05T05:25:12.109967+00:00"}