{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F7HG4JSHOAPWX2P7W4D3QJVUMD","short_pith_number":"pith:F7HG4JSH","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"},"canonical_sha256":"2fce6e2647701f6be9ffb707b826b460dce78a57c4bb721fa6b048a8ddde3f7c","source":{"kind":"arxiv","id":"2405.04912","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04912","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04912v2","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04912","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_12","alias_value":"F7HG4JSHOAPW","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_16","alias_value":"F7HG4JSHOAPWX2P7","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_8","alias_value":"F7HG4JSH","created_at":"2026-07-05T10:42:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F7HG4JSHOAPWX2P7W4D3QJVUMD","target":"record","payload":{"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"},"canonical_sha256":"2fce6e2647701f6be9ffb707b826b460dce78a57c4bb721fa6b048a8ddde3f7c","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"},"source_kind":"arxiv","source_id":"2405.04912","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:42:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OE3DuIigU04ZBgOl/xHd2sQBSuHfI6/OqTWdnjsSdp30uXjJ1O0iLAWPi7TNG+Gi17fBHraKY1hlB/vgSeZrDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:31:59.706894Z"},"content_sha256":"30004fdf8020f83b7eb0705b2e914fc6826b4147e403149270eb2f61949cc4ac","schema_version":"1.0","event_id":"sha256:30004fdf8020f83b7eb0705b2e914fc6826b4147e403149270eb2f61949cc4ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F7HG4JSHOAPWX2P7W4D3QJVUMD","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:42:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xnRgajvMZ2G4XKCpT+sqWaYi4YRe1AuVpPKj3RdqtbxXf4DdodFiU5q1UUhja/AVeKV8i0M9YTtwn1ZOPCkGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:31:59.707263Z"},"content_sha256":"c12035657c93a536ee95baca0b833cf823d965ccb79c22ccbd967a7d023cf589","schema_version":"1.0","event_id":"sha256:c12035657c93a536ee95baca0b833cf823d965ccb79c22ccbd967a7d023cf589"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F7HG4JSHOAPWX2P7W4D3QJVUMD/bundle.json","state_url":"https://pith.science/pith/F7HG4JSHOAPWX2P7W4D3QJVUMD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F7HG4JSHOAPWX2P7W4D3QJVUMD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T08:31:59Z","links":{"resolver":"https://pith.science/pith/F7HG4JSHOAPWX2P7W4D3QJVUMD","bundle":"https://pith.science/pith/F7HG4JSHOAPWX2P7W4D3QJVUMD/bundle.json","state":"https://pith.science/pith/F7HG4JSHOAPWX2P7W4D3QJVUMD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F7HG4JSHOAPWX2P7W4D3QJVUMD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F7HG4JSHOAPWX2P7W4D3QJVUMD","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":"f0cf1f0f412054eeacfdc76b028350c6ccefdc5e051966efb5265c94b2029760","cross_cats_sorted":["cs.LG","physics.chem-ph"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-04-04T16:20:06Z","title_canon_sha256":"fd425eaea162949fa431d0adbb3a3cb9c728b7eec29495b25331de47cd2b322d"},"schema_version":"1.0","source":{"id":"2405.04912","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04912","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04912v2","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04912","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_12","alias_value":"F7HG4JSHOAPW","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_16","alias_value":"F7HG4JSHOAPWX2P7","created_at":"2026-07-05T10:42:11Z"},{"alias_kind":"pith_short_8","alias_value":"F7HG4JSH","created_at":"2026-07-05T10:42:11Z"}],"graph_snapshots":[{"event_id":"sha256:c12035657c93a536ee95baca0b833cf823d965ccb79c22ccbd967a7d023cf589","target":"graph","created_at":"2026-07-05T10:42:11Z","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/2405.04912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Brian Belgodere, Jerret Ross, Jiri Navratil, Payel Das, Samuel C. Hoffman, Vijil Chenthamarakshan, Youssef Mroueh","cross_cats":["cs.LG","physics.chem-ph"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-04-04T16:20:06Z","title":"GP-MoLFormer: A Foundation Model For Molecular Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04912","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":"sha256:30004fdf8020f83b7eb0705b2e914fc6826b4147e403149270eb2f61949cc4ac","target":"record","created_at":"2026-07-05T10:42:11Z","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":"f0cf1f0f412054eeacfdc76b028350c6ccefdc5e051966efb5265c94b2029760","cross_cats_sorted":["cs.LG","physics.chem-ph"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-04-04T16:20:06Z","title_canon_sha256":"fd425eaea162949fa431d0adbb3a3cb9c728b7eec29495b25331de47cd2b322d"},"schema_version":"1.0","source":{"id":"2405.04912","kind":"arxiv","version":2}},"canonical_sha256":"2fce6e2647701f6be9ffb707b826b460dce78a57c4bb721fa6b048a8ddde3f7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fce6e2647701f6be9ffb707b826b460dce78a57c4bb721fa6b048a8ddde3f7c","first_computed_at":"2026-07-05T10:42:11.527600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:11.527600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cJAJNLZl0uWgfHUjXBMnu+SAa4RnyAhCztPsWkQZ4v7xuMWHH0+JcI7iBhcukSSdDEnevajgYKE+WXca0vUGAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:11.528083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.04912","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30004fdf8020f83b7eb0705b2e914fc6826b4147e403149270eb2f61949cc4ac","sha256:c12035657c93a536ee95baca0b833cf823d965ccb79c22ccbd967a7d023cf589"],"state_sha256":"7b7d4d633f1a0a5e7418f0c8a63314b79d50df62e71b6c9a1cecfc6b2ae0f9dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zYT6Ax108oPsIoDnGxjb5Z24CDdLhM9eF+ut9Uo26iDWup1Ju8vPYeQt5X7LXwCDH9+xTU0H19D9L203ezgABA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:31:59.709355Z","bundle_sha256":"5066ffba6d2f072a1dddfbadcb0a5964f818b80d0b8ae62c51ec15f73ba44712"}}