{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QHOQY7USLV4KWPN7R5ESVFLL74","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":"5978cefdd26fd62001c7d81003712c69e639f2075eb0297c22fe9de57bbe87ad","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2020-12-05T17:37:41Z","title_canon_sha256":"aa7cef44edf1ee1d5a5fa633af953e71bdde1ef826e8ac0ab3cd5d88c25398b1"},"schema_version":"1.0","source":{"id":"2012.03084","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.03084","created_at":"2026-07-05T01:57:25Z"},{"alias_kind":"arxiv_version","alias_value":"2012.03084v1","created_at":"2026-07-05T01:57:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.03084","created_at":"2026-07-05T01:57:25Z"},{"alias_kind":"pith_short_12","alias_value":"QHOQY7USLV4K","created_at":"2026-07-05T01:57:25Z"},{"alias_kind":"pith_short_16","alias_value":"QHOQY7USLV4KWPN7","created_at":"2026-07-05T01:57:25Z"},{"alias_kind":"pith_short_8","alias_value":"QHOQY7US","created_at":"2026-07-05T01:57:25Z"}],"graph_snapshots":[{"event_id":"sha256:9fe3620a7aac1971e561d03037f388dd0e0eb4b930d4dfe2731533bf174efb3a","target":"graph","created_at":"2026-07-05T01:57:25Z","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/2012.03084/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Less than 1% of protein sequences are structurally and functionally annotated. Natural Language Processing (NLP) community has recently embraced self-supervised learning as a powerful approach to learn representations from unlabeled text, in large part due to the attention-based context-aware Transformer models. In this work we present a modification to the RoBERTa model by inputting during pre-training a mixture of binding and non-binding protein sequences (from STRING database). However, the sequence pairs have no label to indicate their binding status, as the model relies solely on Masked L","authors_text":"Joris Cadow, Maria Rodriguez Martinez, Matteo Manica, Modestas Filipavicius","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2020-12-05T17:37:41Z","title":"Pre-training Protein Language Models with Label-Agnostic Binding Pairs Enhances Performance in Downstream Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.03084","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":"sha256:6aec5414daf1e916e125759758931633dca98a3c4a4f9e89465d975bf47b3ca7","target":"record","created_at":"2026-07-05T01:57:25Z","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":"5978cefdd26fd62001c7d81003712c69e639f2075eb0297c22fe9de57bbe87ad","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2020-12-05T17:37:41Z","title_canon_sha256":"aa7cef44edf1ee1d5a5fa633af953e71bdde1ef826e8ac0ab3cd5d88c25398b1"},"schema_version":"1.0","source":{"id":"2012.03084","kind":"arxiv","version":1}},"canonical_sha256":"81dd0c7e925d78ab3dbf8f492a956bff2c1173f791f2850e86fdae6bd081669f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81dd0c7e925d78ab3dbf8f492a956bff2c1173f791f2850e86fdae6bd081669f","first_computed_at":"2026-07-05T01:57:25.607723Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:57:25.607723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"teWqxoOT/VjmSEm9d7aryWlaKJz3DMAlAYYiLz+xuPcpYUqxksgWS5B0zqfLzD/13PTim2gGki3pD7PuW1UlCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:57:25.608163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.03084","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6aec5414daf1e916e125759758931633dca98a3c4a4f9e89465d975bf47b3ca7","sha256:9fe3620a7aac1971e561d03037f388dd0e0eb4b930d4dfe2731533bf174efb3a"],"state_sha256":"89d655a06a12d0ef2ccc66294daf11bafa9f30e4cb78ef5176a3290a0b2c8b8d"}