{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F7HG4JSHOAPWX2P7W4D3QJVUMD","short_pith_number":"pith:F7HG4JSH","schema_version":"1.0","canonical_sha256":"2fce6e2647701f6be9ffb707b826b460dce78a57c4bb721fa6b048a8ddde3f7c","source":{"kind":"arxiv","id":"2405.04912","version":2},"attestation_state":"computed","paper":{"title":"GP-MoLFormer: A Foundation Model For Molecular Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","physics.chem-ph"],"primary_cat":"q-bio.BM","authors_text":"Brian Belgodere, Jerret Ross, Jiri Navratil, Payel Das, Samuel C. Hoffman, Vijil Chenthamarakshan, Youssef Mroueh","submitted_at":"2024-04-04T16:20:06Z","abstract_excerpt":"Transformer-based models trained on large and general purpose datasets consisting of molecular strings have recently emerged as a powerful tool for successfully modeling various structure-property relations. Inspired by this success, we extend the paradigm of training chemical language transformers on large-scale chemical datasets to generative tasks in this work. Specifically, we propose GP-MoLFormer, an autoregressive molecular string generator that is trained on more than 1.1B (billion) chemical SMILES. GP-MoLFormer uses a 46.8M parameter transformer decoder model with linear attention and "},"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":"2405.04912","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-04-04T16:20:06Z","cross_cats_sorted":["cs.LG","physics.chem-ph"],"title_canon_sha256":"fd425eaea162949fa431d0adbb3a3cb9c728b7eec29495b25331de47cd2b322d","abstract_canon_sha256":"f0cf1f0f412054eeacfdc76b028350c6ccefdc5e051966efb5265c94b2029760"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:11.528083Z","signature_b64":"cJAJNLZl0uWgfHUjXBMnu+SAa4RnyAhCztPsWkQZ4v7xuMWHH0+JcI7iBhcukSSdDEnevajgYKE+WXca0vUGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fce6e2647701f6be9ffb707b826b460dce78a57c4bb721fa6b048a8ddde3f7c","last_reissued_at":"2026-07-05T10:42:11.527600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:11.527600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GP-MoLFormer: A Foundation Model For Molecular Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","physics.chem-ph"],"primary_cat":"q-bio.BM","authors_text":"Brian Belgodere, Jerret Ross, Jiri Navratil, Payel Das, Samuel C. Hoffman, Vijil Chenthamarakshan, Youssef Mroueh","submitted_at":"2024-04-04T16:20:06Z","abstract_excerpt":"Transformer-based models trained on large and general purpose datasets consisting of molecular strings have recently emerged as a powerful tool for successfully modeling various structure-property relations. Inspired by this success, we extend the paradigm of training chemical language transformers on large-scale chemical datasets to generative tasks in this work. Specifically, we propose GP-MoLFormer, an autoregressive molecular string generator that is trained on more than 1.1B (billion) chemical SMILES. GP-MoLFormer uses a 46.8M parameter transformer decoder model with linear attention and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04912","kind":"arxiv","version":2},"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/2405.04912/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":"2405.04912","created_at":"2026-07-05T10:42:11.527658+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04912v2","created_at":"2026-07-05T10:42:11.527658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04912","created_at":"2026-07-05T10:42:11.527658+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7HG4JSHOAPW","created_at":"2026-07-05T10:42:11.527658+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7HG4JSHOAPWX2P7","created_at":"2026-07-05T10:42:11.527658+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7HG4JSH","created_at":"2026-07-05T10:42:11.527658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06322","citing_title":"SMolLM: Small Language Models Learn Small Molecular Grammar","ref_index":91,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F7HG4JSHOAPWX2P7W4D3QJVUMD","json":"https://pith.science/pith/F7HG4JSHOAPWX2P7W4D3QJVUMD.json","graph_json":"https://pith.science/api/pith-number/F7HG4JSHOAPWX2P7W4D3QJVUMD/graph.json","events_json":"https://pith.science/api/pith-number/F7HG4JSHOAPWX2P7W4D3QJVUMD/events.json","paper":"https://pith.science/paper/F7HG4JSH"},"agent_actions":{"view_html":"https://pith.science/pith/F7HG4JSHOAPWX2P7W4D3QJVUMD","download_json":"https://pith.science/pith/F7HG4JSHOAPWX2P7W4D3QJVUMD.json","view_paper":"https://pith.science/paper/F7HG4JSH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04912&json=true","fetch_graph":"https://pith.science/api/pith-number/F7HG4JSHOAPWX2P7W4D3QJVUMD/graph.json","fetch_events":"https://pith.science/api/pith-number/F7HG4JSHOAPWX2P7W4D3QJVUMD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7HG4JSHOAPWX2P7W4D3QJVUMD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7HG4JSHOAPWX2P7W4D3QJVUMD/action/storage_attestation","attest_author":"https://pith.science/pith/F7HG4JSHOAPWX2P7W4D3QJVUMD/action/author_attestation","sign_citation":"https://pith.science/pith/F7HG4JSHOAPWX2P7W4D3QJVUMD/action/citation_signature","submit_replication":"https://pith.science/pith/F7HG4JSHOAPWX2P7W4D3QJVUMD/action/replication_record"}},"created_at":"2026-07-05T10:42:11.527658+00:00","updated_at":"2026-07-05T10:42:11.527658+00:00"}