{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JNOHKDLXNACACYO7ILMZRQGEUF","short_pith_number":"pith:JNOHKDLX","schema_version":"1.0","canonical_sha256":"4b5c750d7768040161df42d998c0c4a1613f922dc5c46e7b1dfb03c5719b83c2","source":{"kind":"arxiv","id":"2201.02229","version":1},"attestation_state":"computed","paper":{"title":"Large-scale protein-protein post-translational modification extraction with distant supervision and confidence calibrated BioBERT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Aparna Elangovan, Douglas E. V. Pires, Karin Verspoor, Melissa J. Davis, Yuan Li","submitted_at":"2022-01-06T19:59:14Z","abstract_excerpt":"Protein-protein interactions (PPIs) are critical to normal cellular function and are related to many disease pathways. However, only 4% of PPIs are annotated with PTMs in biological knowledge databases such as IntAct, mainly performed through manual curation, which is neither time nor cost-effective. We use the IntAct PPI database to create a distant supervised dataset annotated with interacting protein pairs, their corresponding PTM type, and associated abstracts from the PubMed database. We train an ensemble of BioBERT models - dubbed PPI-BioBERT-x10 to improve confidence calibration. We ext"},"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":"2201.02229","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-06T19:59:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"42433d9fe1c1c96e11ffbdf7fddb5df5f8a57409dc90f4d890c01f660ad7e1dd","abstract_canon_sha256":"badadc1946f132fcb32e937283b7e35d037afa061bc9f82cc043fd4e9603d74e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:38.972964Z","signature_b64":"CEy66Qb+0xxmtqoq/NwPWqVeqxhyDFO3E/m/i6rPgYExnhNAWahrbxSVmWfSh/R6gStbA1UEZfMQDVwBy0GfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b5c750d7768040161df42d998c0c4a1613f922dc5c46e7b1dfb03c5719b83c2","last_reissued_at":"2026-07-05T03:46:38.972525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:38.972525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-scale protein-protein post-translational modification extraction with distant supervision and confidence calibrated BioBERT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Aparna Elangovan, Douglas E. V. Pires, Karin Verspoor, Melissa J. Davis, Yuan Li","submitted_at":"2022-01-06T19:59:14Z","abstract_excerpt":"Protein-protein interactions (PPIs) are critical to normal cellular function and are related to many disease pathways. However, only 4% of PPIs are annotated with PTMs in biological knowledge databases such as IntAct, mainly performed through manual curation, which is neither time nor cost-effective. We use the IntAct PPI database to create a distant supervised dataset annotated with interacting protein pairs, their corresponding PTM type, and associated abstracts from the PubMed database. We train an ensemble of BioBERT models - dubbed PPI-BioBERT-x10 to improve confidence calibration. We ext"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02229","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/2201.02229/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":"2201.02229","created_at":"2026-07-05T03:46:38.972581+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.02229v1","created_at":"2026-07-05T03:46:38.972581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02229","created_at":"2026-07-05T03:46:38.972581+00:00"},{"alias_kind":"pith_short_12","alias_value":"JNOHKDLXNACA","created_at":"2026-07-05T03:46:38.972581+00:00"},{"alias_kind":"pith_short_16","alias_value":"JNOHKDLXNACACYO7","created_at":"2026-07-05T03:46:38.972581+00:00"},{"alias_kind":"pith_short_8","alias_value":"JNOHKDLX","created_at":"2026-07-05T03:46:38.972581+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/JNOHKDLXNACACYO7ILMZRQGEUF","json":"https://pith.science/pith/JNOHKDLXNACACYO7ILMZRQGEUF.json","graph_json":"https://pith.science/api/pith-number/JNOHKDLXNACACYO7ILMZRQGEUF/graph.json","events_json":"https://pith.science/api/pith-number/JNOHKDLXNACACYO7ILMZRQGEUF/events.json","paper":"https://pith.science/paper/JNOHKDLX"},"agent_actions":{"view_html":"https://pith.science/pith/JNOHKDLXNACACYO7ILMZRQGEUF","download_json":"https://pith.science/pith/JNOHKDLXNACACYO7ILMZRQGEUF.json","view_paper":"https://pith.science/paper/JNOHKDLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.02229&json=true","fetch_graph":"https://pith.science/api/pith-number/JNOHKDLXNACACYO7ILMZRQGEUF/graph.json","fetch_events":"https://pith.science/api/pith-number/JNOHKDLXNACACYO7ILMZRQGEUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JNOHKDLXNACACYO7ILMZRQGEUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JNOHKDLXNACACYO7ILMZRQGEUF/action/storage_attestation","attest_author":"https://pith.science/pith/JNOHKDLXNACACYO7ILMZRQGEUF/action/author_attestation","sign_citation":"https://pith.science/pith/JNOHKDLXNACACYO7ILMZRQGEUF/action/citation_signature","submit_replication":"https://pith.science/pith/JNOHKDLXNACACYO7ILMZRQGEUF/action/replication_record"}},"created_at":"2026-07-05T03:46:38.972581+00:00","updated_at":"2026-07-05T03:46:38.972581+00:00"}