{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B7T257DQAVFNROBH2WPOUGS5IW","short_pith_number":"pith:B7T257DQ","schema_version":"1.0","canonical_sha256":"0fe7aefc70054ad8b827d59eea1a5d458d31ff23da6b9de02b609fdb919b433d","source":{"kind":"arxiv","id":"2607.22777","version":1},"attestation_state":"computed","paper":{"title":"LC-SEPLM: long-range contact-supervised adaptation for sequence-only protein representation learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Boming Kang, Chen Wang, Qinghua Cui","submitted_at":"2026-07-24T08:35:06Z","abstract_excerpt":"Protein language models learn transferable sequence representations. However, because they primarily model contextual dependencies along amino-acid sequences, their training objectives do not explicitly constrain the model to learn three-dimensional residue contacts formed after folding . Here, we introduce LC-SEPLM (Long-range Contact-supervised ESM Protein Language Model), which adapts ESM2 with LoRA and long-range residue-pair contact supervision while retaining sequence-only downstream inference. Pair-specific queries use cross-attention over the complete sequence to extract global sequenc"},"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":"2607.22777","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T08:35:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"698da90dc151fcbada1a648db0a360ffe9375c4616ddc7c173f94d0cfdfdc4f9","abstract_canon_sha256":"9a1ff4d456a904c6763122febdcde9965bbdb733cefd7590bdd9ef40b625f8e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:21:53.878604Z","signature_b64":"/VQNEH25v+KlaG50SHJy9QQG2RjOplu2yChqunXJ4b+uXDQ9Z9Mwd6mBVY1YbbtBoldnR1mGeuKcS58dCvfiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fe7aefc70054ad8b827d59eea1a5d458d31ff23da6b9de02b609fdb919b433d","last_reissued_at":"2026-07-28T00:21:53.877762Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:21:53.877762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LC-SEPLM: long-range contact-supervised adaptation for sequence-only protein representation learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Boming Kang, Chen Wang, Qinghua Cui","submitted_at":"2026-07-24T08:35:06Z","abstract_excerpt":"Protein language models learn transferable sequence representations. However, because they primarily model contextual dependencies along amino-acid sequences, their training objectives do not explicitly constrain the model to learn three-dimensional residue contacts formed after folding . Here, we introduce LC-SEPLM (Long-range Contact-supervised ESM Protein Language Model), which adapts ESM2 with LoRA and long-range residue-pair contact supervision while retaining sequence-only downstream inference. Pair-specific queries use cross-attention over the complete sequence to extract global sequenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22777","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/2607.22777/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":"2607.22777","created_at":"2026-07-28T00:21:53.878202+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22777v1","created_at":"2026-07-28T00:21:53.878202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22777","created_at":"2026-07-28T00:21:53.878202+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7T257DQAVFN","created_at":"2026-07-28T00:21:53.878202+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7T257DQAVFNROBH","created_at":"2026-07-28T00:21:53.878202+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7T257DQ","created_at":"2026-07-28T00:21:53.878202+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B7T257DQAVFNROBH2WPOUGS5IW","json":"https://pith.science/pith/B7T257DQAVFNROBH2WPOUGS5IW.json","graph_json":"https://pith.science/api/pith-number/B7T257DQAVFNROBH2WPOUGS5IW/graph.json","events_json":"https://pith.science/api/pith-number/B7T257DQAVFNROBH2WPOUGS5IW/events.json","paper":"https://pith.science/paper/B7T257DQ"},"agent_actions":{"view_html":"https://pith.science/pith/B7T257DQAVFNROBH2WPOUGS5IW","download_json":"https://pith.science/pith/B7T257DQAVFNROBH2WPOUGS5IW.json","view_paper":"https://pith.science/paper/B7T257DQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22777&json=true","fetch_graph":"https://pith.science/api/pith-number/B7T257DQAVFNROBH2WPOUGS5IW/graph.json","fetch_events":"https://pith.science/api/pith-number/B7T257DQAVFNROBH2WPOUGS5IW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7T257DQAVFNROBH2WPOUGS5IW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7T257DQAVFNROBH2WPOUGS5IW/action/storage_attestation","attest_author":"https://pith.science/pith/B7T257DQAVFNROBH2WPOUGS5IW/action/author_attestation","sign_citation":"https://pith.science/pith/B7T257DQAVFNROBH2WPOUGS5IW/action/citation_signature","submit_replication":"https://pith.science/pith/B7T257DQAVFNROBH2WPOUGS5IW/action/replication_record"}},"created_at":"2026-07-28T00:21:53.878202+00:00","updated_at":"2026-07-28T00:21:53.878202+00:00"}