{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BMKYCPTBI2HFYUOEY2ZTA45EUG","short_pith_number":"pith:BMKYCPTB","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"},"canonical_sha256":"0b15813e61468e5c51c4c6b33073a4a1bc76f3afb686d394651e024d0cdb4716","source":{"kind":"arxiv","id":"2301.02120","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.02120","created_at":"2026-07-05T05:30:57Z"},{"alias_kind":"arxiv_version","alias_value":"2301.02120v1","created_at":"2026-07-05T05:30:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02120","created_at":"2026-07-05T05:30:57Z"},{"alias_kind":"pith_short_12","alias_value":"BMKYCPTBI2HF","created_at":"2026-07-05T05:30:57Z"},{"alias_kind":"pith_short_16","alias_value":"BMKYCPTBI2HFYUOE","created_at":"2026-07-05T05:30:57Z"},{"alias_kind":"pith_short_8","alias_value":"BMKYCPTB","created_at":"2026-07-05T05:30:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BMKYCPTBI2HFYUOEY2ZTA45EUG","target":"record","payload":{"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"},"canonical_sha256":"0b15813e61468e5c51c4c6b33073a4a1bc76f3afb686d394651e024d0cdb4716","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"},"source_kind":"arxiv","source_id":"2301.02120","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:30:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ln6FtHuh5kJn4YBjOpls3T6vEb8frKv+xlWb0x1mTypuQRjRkG5WKBS+UpaOZI/j7YgGiO2f0gg2lvsB5eBrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:54:27.779352Z"},"content_sha256":"ce38cca1763d926eba770b6e37e9118a231b62a003cc92721a442e2687aaf9fd","schema_version":"1.0","event_id":"sha256:ce38cca1763d926eba770b6e37e9118a231b62a003cc92721a442e2687aaf9fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BMKYCPTBI2HFYUOEY2ZTA45EUG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:30:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3PtUJp2+LcKrvk6+f8ynbmvW/cPEgCVeoEc47YINIQbRC5IjIXWyEqaoBpF/K4CXKFHBMNSIKOCdSUGienEsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:54:27.779860Z"},"content_sha256":"ba6e487c46e75f7ef2ea073416057b805d811fb9cf9cc883bb4773bf8a770690","schema_version":"1.0","event_id":"sha256:ba6e487c46e75f7ef2ea073416057b805d811fb9cf9cc883bb4773bf8a770690"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BMKYCPTBI2HFYUOEY2ZTA45EUG/bundle.json","state_url":"https://pith.science/pith/BMKYCPTBI2HFYUOEY2ZTA45EUG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BMKYCPTBI2HFYUOEY2ZTA45EUG/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":"2026-08-09T04:54:27Z","links":{"resolver":"https://pith.science/pith/BMKYCPTBI2HFYUOEY2ZTA45EUG","bundle":"https://pith.science/pith/BMKYCPTBI2HFYUOEY2ZTA45EUG/bundle.json","state":"https://pith.science/pith/BMKYCPTBI2HFYUOEY2ZTA45EUG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BMKYCPTBI2HFYUOEY2ZTA45EUG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BMKYCPTBI2HFYUOEY2ZTA45EUG","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":"2630e49b36118034c5765a210a2ab9694d81190f5c22f546a76a8779e51d7b8c","cross_cats_sorted":["cs.CL","q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-05T15:55:18Z","title_canon_sha256":"02b67b62c3e9f335384695aae0930e49c96840b3d7f12d6346a254887d6e67bc"},"schema_version":"1.0","source":{"id":"2301.02120","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.02120","created_at":"2026-07-05T05:30:57Z"},{"alias_kind":"arxiv_version","alias_value":"2301.02120v1","created_at":"2026-07-05T05:30:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02120","created_at":"2026-07-05T05:30:57Z"},{"alias_kind":"pith_short_12","alias_value":"BMKYCPTBI2HF","created_at":"2026-07-05T05:30:57Z"},{"alias_kind":"pith_short_16","alias_value":"BMKYCPTBI2HFYUOE","created_at":"2026-07-05T05:30:57Z"},{"alias_kind":"pith_short_8","alias_value":"BMKYCPTB","created_at":"2026-07-05T05:30:57Z"}],"graph_snapshots":[{"event_id":"sha256:ba6e487c46e75f7ef2ea073416057b805d811fb9cf9cc883bb4773bf8a770690","target":"graph","created_at":"2026-07-05T05:30:57Z","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/2301.02120/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Payel Das, Pin-Yu Chen, Ria Vinod","cross_cats":["cs.CL","q-bio.BM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-05T15:55:18Z","title":"Reprogramming Pretrained Language Models for Protein Sequence Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.02120","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:ce38cca1763d926eba770b6e37e9118a231b62a003cc92721a442e2687aaf9fd","target":"record","created_at":"2026-07-05T05:30:57Z","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":"2630e49b36118034c5765a210a2ab9694d81190f5c22f546a76a8779e51d7b8c","cross_cats_sorted":["cs.CL","q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-05T15:55:18Z","title_canon_sha256":"02b67b62c3e9f335384695aae0930e49c96840b3d7f12d6346a254887d6e67bc"},"schema_version":"1.0","source":{"id":"2301.02120","kind":"arxiv","version":1}},"canonical_sha256":"0b15813e61468e5c51c4c6b33073a4a1bc76f3afb686d394651e024d0cdb4716","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b15813e61468e5c51c4c6b33073a4a1bc76f3afb686d394651e024d0cdb4716","first_computed_at":"2026-07-05T05:30:57.043567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:30:57.043567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qoq7+DucgEALvH9RK4lYhhZrCQRVtcsLIylsBhERVElQX4SJ0LWJQ5PlO5o7b1kVDgr93RhvNwBInvmsErdyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:30:57.043927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.02120","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce38cca1763d926eba770b6e37e9118a231b62a003cc92721a442e2687aaf9fd","sha256:ba6e487c46e75f7ef2ea073416057b805d811fb9cf9cc883bb4773bf8a770690"],"state_sha256":"40ed5d7e582f6702a01229e0b61a6eaa3119e89299f081ca36dc44b76d287fb6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QtnMnh4yfr8SFETScZi24+wuoIlsuzk8uLZC7xFE3djSFBJnIrL7CtGmbyUWCxNDYivzXKzSUmvNrAbGu6YnCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:54:27.784436Z","bundle_sha256":"0a06697f0388eba04b9c78eb3a39abdb11c39534aa5306d90f251ad0cbecde2d"}}