{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4AXXQZPHDKAYCKHPDMDPZQNZZ6","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":"a445f2515573b21d7866b4fac3aac37cd8735912949eeddfeb0d2f4b2d03c17d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-26T10:55:05Z","title_canon_sha256":"84f173be46c90ac9c5823299d60aff14e4808645ad231fdbdd569a655df8e9ca"},"schema_version":"1.0","source":{"id":"2011.13230","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.13230","created_at":"2026-07-05T01:54:52Z"},{"alias_kind":"arxiv_version","alias_value":"2011.13230v1","created_at":"2026-07-05T01:54:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.13230","created_at":"2026-07-05T01:54:52Z"},{"alias_kind":"pith_short_12","alias_value":"4AXXQZPHDKAY","created_at":"2026-07-05T01:54:52Z"},{"alias_kind":"pith_short_16","alias_value":"4AXXQZPHDKAYCKHP","created_at":"2026-07-05T01:54:52Z"},{"alias_kind":"pith_short_8","alias_value":"4AXXQZPH","created_at":"2026-07-05T01:54:52Z"}],"graph_snapshots":[{"event_id":"sha256:928e0fcfc0fdf6bcb4066bc70e295d401b79863d43ff9af30c0b7210d87a1586","target":"graph","created_at":"2026-07-05T01:54:52Z","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/2011.13230/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We apply a Transformer architecture, specifically BERT, to learn flexible and high quality molecular representations for drug discovery problems. We study the impact of using different combinations of self-supervised tasks for pre-training, and present our results for the established Virtual Screening and QSAR benchmarks. We show that: i) The selection of appropriate self-supervised task(s) for pre-training has a significant impact on performance in subsequent downstream tasks such as Virtual Screening. ii) Using auxiliary tasks with more domain relevance for Chemistry, such as learning to pre","authors_text":"Benedek Fabian, H\\'el\\'ena Gaspar, Joshua Meyers, Marco Fiscato, Marwin Segler, Mohamed Ahmed, Thomas Edlich","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-26T10:55:05Z","title":"Molecular representation learning with language models and domain-relevant auxiliary tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.13230","kind":"arxiv","version":1},"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:dfdf8d3f84f978b385a130d1989c63fba9e2e51336f6c7c60d9c0de8ff966ae1","target":"record","created_at":"2026-07-05T01:54:52Z","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":"a445f2515573b21d7866b4fac3aac37cd8735912949eeddfeb0d2f4b2d03c17d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-26T10:55:05Z","title_canon_sha256":"84f173be46c90ac9c5823299d60aff14e4808645ad231fdbdd569a655df8e9ca"},"schema_version":"1.0","source":{"id":"2011.13230","kind":"arxiv","version":1}},"canonical_sha256":"e02f7865e71a818128ef1b06fcc1b9cfa196dd5d12fe2ff889556babc15354c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e02f7865e71a818128ef1b06fcc1b9cfa196dd5d12fe2ff889556babc15354c1","first_computed_at":"2026-07-05T01:54:52.205020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:54:52.205020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4+ufZm8PdnToJkxaakFG04LTBRFP45u6tClCwVdzG/RyR+GNRDHhD2Ikyu84ItXBqBe6wvEQmnWqYSYUgpKeBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:54:52.205581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.13230","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfdf8d3f84f978b385a130d1989c63fba9e2e51336f6c7c60d9c0de8ff966ae1","sha256:928e0fcfc0fdf6bcb4066bc70e295d401b79863d43ff9af30c0b7210d87a1586"],"state_sha256":"d29455bb01f9c479f85f469867a95d2cae23ba86d6d9c7e44c559f5d71b1e4ad"}