{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D3WE44FSYR4T4QWZO2MTDNWJNT","short_pith_number":"pith:D3WE44FS","schema_version":"1.0","canonical_sha256":"1eec4e70b2c4793e42d9769931b6c96cf28b7694f2d01ff865fb25529e13a3b0","source":{"kind":"arxiv","id":"2411.03537","version":2},"attestation_state":"computed","paper":{"title":"Two-Stage Pretraining for Molecular Property Prediction in the Wild","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","physics.chem-ph","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Hans-Peter Seidel, Kevin Tirta Wijaya, Michael Sun, Minghao Guo, Vahid Babaei, Wojciech Matusik","submitted_at":"2024-11-05T22:36:17Z","abstract_excerpt":"Molecular deep learning models have achieved remarkable success in property prediction, but they often require large amounts of labeled data. The challenge is that, in real-world applications, labels are extremely scarce, as obtaining them through laboratory experimentation is both expensive and time-consuming. In this work, we introduce MoleVers, a versatile pretrained molecular model designed for various types of molecular property prediction in the wild, i.e., where experimentally-validated labels are scarce. MoleVers employs a two-stage pretraining strategy. In the first stage, it learns m"},"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":"2411.03537","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T22:36:17Z","cross_cats_sorted":["cs.AI","physics.chem-ph","q-bio.BM"],"title_canon_sha256":"2ce5ad229cc619721b272dcd99605430c0fa7e3020322020f50180817cbaa0b4","abstract_canon_sha256":"b3c795184db0a3d4b1b669b5a50577a56fbfabdd9723bf8268ef0bb6f7a01a10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:05.431810Z","signature_b64":"i+OPVKQtkHQFOltCllF6G80CF37yOy6hf3TvQVQ2BV3S4Weohlf1Xp4vcI7chPKNOFSV2qpEEvfLJZupBWrdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1eec4e70b2c4793e42d9769931b6c96cf28b7694f2d01ff865fb25529e13a3b0","last_reissued_at":"2026-07-05T11:39:05.431278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:05.431278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Two-Stage Pretraining for Molecular Property Prediction in the Wild","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","physics.chem-ph","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Hans-Peter Seidel, Kevin Tirta Wijaya, Michael Sun, Minghao Guo, Vahid Babaei, Wojciech Matusik","submitted_at":"2024-11-05T22:36:17Z","abstract_excerpt":"Molecular deep learning models have achieved remarkable success in property prediction, but they often require large amounts of labeled data. The challenge is that, in real-world applications, labels are extremely scarce, as obtaining them through laboratory experimentation is both expensive and time-consuming. In this work, we introduce MoleVers, a versatile pretrained molecular model designed for various types of molecular property prediction in the wild, i.e., where experimentally-validated labels are scarce. MoleVers employs a two-stage pretraining strategy. In the first stage, it learns m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03537","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/2411.03537/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":"2411.03537","created_at":"2026-07-05T11:39:05.431338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03537v2","created_at":"2026-07-05T11:39:05.431338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03537","created_at":"2026-07-05T11:39:05.431338+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3WE44FSYR4T","created_at":"2026-07-05T11:39:05.431338+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3WE44FSYR4T4QWZ","created_at":"2026-07-05T11:39:05.431338+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3WE44FS","created_at":"2026-07-05T11:39:05.431338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.19977","citing_title":"Rem3Di: Learning smooth, chiral 3D molecular descriptors from atomistic foundation models","ref_index":62,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D3WE44FSYR4T4QWZO2MTDNWJNT","json":"https://pith.science/pith/D3WE44FSYR4T4QWZO2MTDNWJNT.json","graph_json":"https://pith.science/api/pith-number/D3WE44FSYR4T4QWZO2MTDNWJNT/graph.json","events_json":"https://pith.science/api/pith-number/D3WE44FSYR4T4QWZO2MTDNWJNT/events.json","paper":"https://pith.science/paper/D3WE44FS"},"agent_actions":{"view_html":"https://pith.science/pith/D3WE44FSYR4T4QWZO2MTDNWJNT","download_json":"https://pith.science/pith/D3WE44FSYR4T4QWZO2MTDNWJNT.json","view_paper":"https://pith.science/paper/D3WE44FS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03537&json=true","fetch_graph":"https://pith.science/api/pith-number/D3WE44FSYR4T4QWZO2MTDNWJNT/graph.json","fetch_events":"https://pith.science/api/pith-number/D3WE44FSYR4T4QWZO2MTDNWJNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3WE44FSYR4T4QWZO2MTDNWJNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3WE44FSYR4T4QWZO2MTDNWJNT/action/storage_attestation","attest_author":"https://pith.science/pith/D3WE44FSYR4T4QWZO2MTDNWJNT/action/author_attestation","sign_citation":"https://pith.science/pith/D3WE44FSYR4T4QWZO2MTDNWJNT/action/citation_signature","submit_replication":"https://pith.science/pith/D3WE44FSYR4T4QWZO2MTDNWJNT/action/replication_record"}},"created_at":"2026-07-05T11:39:05.431338+00:00","updated_at":"2026-07-05T11:39:05.431338+00:00"}