{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BMKYCPTBI2HFYUOEY2ZTA45EUG","short_pith_number":"pith:BMKYCPTB","schema_version":"1.0","canonical_sha256":"0b15813e61468e5c51c4c6b33073a4a1bc76f3afb686d394651e024d0cdb4716","source":{"kind":"arxiv","id":"2301.02120","version":1},"attestation_state":"computed","paper":{"title":"Reprogramming Pretrained Language Models for Protein Sequence Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Payel Das, Pin-Yu Chen, Ria Vinod","submitted_at":"2023-01-05T15:55:18Z","abstract_excerpt":"Machine Learning-guided solutions for protein learning tasks have made significant headway in recent years. However, success in scientific discovery tasks is limited by the accessibility of well-defined and labeled in-domain data. To tackle the low-data constraint, recent adaptions of deep learning models pretrained on millions of protein sequences have shown promise; however, the construction of such domain-specific large-scale model is computationally expensive. Here, we propose Representation Learning via Dictionary Learning (R2DL), an end-to-end representation learning framework in which w"},"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":"2301.02120","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-05T15:55:18Z","cross_cats_sorted":["cs.CL","q-bio.BM"],"title_canon_sha256":"02b67b62c3e9f335384695aae0930e49c96840b3d7f12d6346a254887d6e67bc","abstract_canon_sha256":"2630e49b36118034c5765a210a2ab9694d81190f5c22f546a76a8779e51d7b8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:57.043927Z","signature_b64":"Qoq7+DucgEALvH9RK4lYhhZrCQRVtcsLIylsBhERVElQX4SJ0LWJQ5PlO5o7b1kVDgr93RhvNwBInvmsErdyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b15813e61468e5c51c4c6b33073a4a1bc76f3afb686d394651e024d0cdb4716","last_reissued_at":"2026-07-05T05:30:57.043567Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:57.043567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reprogramming Pretrained Language Models for Protein Sequence Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Payel Das, Pin-Yu Chen, Ria Vinod","submitted_at":"2023-01-05T15:55:18Z","abstract_excerpt":"Machine Learning-guided solutions for protein learning tasks have made significant headway in recent years. However, success in scientific discovery tasks is limited by the accessibility of well-defined and labeled in-domain data. To tackle the low-data constraint, recent adaptions of deep learning models pretrained on millions of protein sequences have shown promise; however, the construction of such domain-specific large-scale model is computationally expensive. Here, we propose Representation Learning via Dictionary Learning (R2DL), an end-to-end representation learning framework in which w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.02120","kind":"arxiv","version":1},"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/2301.02120/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":"2301.02120","created_at":"2026-07-05T05:30:57.043624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.02120v1","created_at":"2026-07-05T05:30:57.043624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02120","created_at":"2026-07-05T05:30:57.043624+00:00"},{"alias_kind":"pith_short_12","alias_value":"BMKYCPTBI2HF","created_at":"2026-07-05T05:30:57.043624+00:00"},{"alias_kind":"pith_short_16","alias_value":"BMKYCPTBI2HFYUOE","created_at":"2026-07-05T05:30:57.043624+00:00"},{"alias_kind":"pith_short_8","alias_value":"BMKYCPTB","created_at":"2026-07-05T05:30:57.043624+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00620","citing_title":"Model Reprogramming Demystified: A Neural Tangent Kernel Perspective","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BMKYCPTBI2HFYUOEY2ZTA45EUG","json":"https://pith.science/pith/BMKYCPTBI2HFYUOEY2ZTA45EUG.json","graph_json":"https://pith.science/api/pith-number/BMKYCPTBI2HFYUOEY2ZTA45EUG/graph.json","events_json":"https://pith.science/api/pith-number/BMKYCPTBI2HFYUOEY2ZTA45EUG/events.json","paper":"https://pith.science/paper/BMKYCPTB"},"agent_actions":{"view_html":"https://pith.science/pith/BMKYCPTBI2HFYUOEY2ZTA45EUG","download_json":"https://pith.science/pith/BMKYCPTBI2HFYUOEY2ZTA45EUG.json","view_paper":"https://pith.science/paper/BMKYCPTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.02120&json=true","fetch_graph":"https://pith.science/api/pith-number/BMKYCPTBI2HFYUOEY2ZTA45EUG/graph.json","fetch_events":"https://pith.science/api/pith-number/BMKYCPTBI2HFYUOEY2ZTA45EUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BMKYCPTBI2HFYUOEY2ZTA45EUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BMKYCPTBI2HFYUOEY2ZTA45EUG/action/storage_attestation","attest_author":"https://pith.science/pith/BMKYCPTBI2HFYUOEY2ZTA45EUG/action/author_attestation","sign_citation":"https://pith.science/pith/BMKYCPTBI2HFYUOEY2ZTA45EUG/action/citation_signature","submit_replication":"https://pith.science/pith/BMKYCPTBI2HFYUOEY2ZTA45EUG/action/replication_record"}},"created_at":"2026-07-05T05:30:57.043624+00:00","updated_at":"2026-07-05T05:30:57.043624+00:00"}