{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:X2TST4DSXGOP3U3L5UEUYLATQF","short_pith_number":"pith:X2TST4DS","canonical_record":{"source":{"id":"2106.09700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T17:55:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6cb3d2cd2ae4fc7c68fe8db96ecca9821aff0de588ce3c39eeecf711adba3c7a","abstract_canon_sha256":"84801dac1875bc24af97cf827443e2a48f22f9ede742c1e14e1a3a20dca10289"},"schema_version":"1.0"},"canonical_sha256":"bea729f072b99cfdd36bed094c2c13817406a9c9dd5f8a9ab8bb1af7a1d75430","source":{"kind":"arxiv","id":"2106.09700","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09700","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09700v2","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09700","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_12","alias_value":"X2TST4DSXGOP","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_16","alias_value":"X2TST4DSXGOP3U3L","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_8","alias_value":"X2TST4DS","created_at":"2026-07-05T03:15:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:X2TST4DSXGOP3U3L5UEUYLATQF","target":"record","payload":{"canonical_record":{"source":{"id":"2106.09700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T17:55:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6cb3d2cd2ae4fc7c68fe8db96ecca9821aff0de588ce3c39eeecf711adba3c7a","abstract_canon_sha256":"84801dac1875bc24af97cf827443e2a48f22f9ede742c1e14e1a3a20dca10289"},"schema_version":"1.0"},"canonical_sha256":"bea729f072b99cfdd36bed094c2c13817406a9c9dd5f8a9ab8bb1af7a1d75430","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:52.991416Z","signature_b64":"yZXBDzbl7tAQQ2/jwg2yt2JXG7pVHJvmz+O4c+ieDaEghOXDP86g96+xDIhGS3PIRfG6JnavfDOFQM8zt4SOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bea729f072b99cfdd36bed094c2c13817406a9c9dd5f8a9ab8bb1af7a1d75430","last_reissued_at":"2026-07-05T03:15:52.990900Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:52.990900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.09700","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:15:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p2cgBoRRHsItuMK5RengTmpVw5ZchvTSDJh/WOQcFZ8y87rqB2TdiRWuVV203F70In9QdALvU6UY3thnPIUCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:18:06.997548Z"},"content_sha256":"4f2da71adfb9334002338edc0197d7a462b9def1286238fd725fe4e15085448e","schema_version":"1.0","event_id":"sha256:4f2da71adfb9334002338edc0197d7a462b9def1286238fd725fe4e15085448e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:X2TST4DSXGOP3U3L5UEUYLATQF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scientific Language Models for Biomedical Knowledge Base Completion: An Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"David Wadden, Hannaneh Hajishirzi, Iz Beltagy, Noah A. Smith, Rahul Nadkarni, Tom Hope","submitted_at":"2021-06-17T17:55:33Z","abstract_excerpt":"Biomedical knowledge graphs (KGs) hold rich information on entities such as diseases, drugs, and genes. Predicting missing links in these graphs can boost many important applications, such as drug design and repurposing. Recent work has shown that general-domain language models (LMs) can serve as \"soft\" KGs, and that they can be fine-tuned for the task of KG completion. In this work, we study scientific LMs for KG completion, exploring whether we can tap into their latent knowledge to enhance biomedical link prediction. We evaluate several domain-specific LMs, fine-tuning them on datasets cent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09700","kind":"arxiv","version":2},"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/2106.09700/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":"2026-07-05T03:15:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I9P/yBw7Bjw9SVVn6MDa43HKFFPMZv+ZceUkoVUD/zTlAxPAqtWTkUXuzNk9cUPLD3JAkBxyysviDjMJjINTCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:18:06.998067Z"},"content_sha256":"9cf3371fe5c78c236904c4a8b4234d8c2e70184d47ea47f40e9a8098078b9a4f","schema_version":"1.0","event_id":"sha256:9cf3371fe5c78c236904c4a8b4234d8c2e70184d47ea47f40e9a8098078b9a4f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X2TST4DSXGOP3U3L5UEUYLATQF/bundle.json","state_url":"https://pith.science/pith/X2TST4DSXGOP3U3L5UEUYLATQF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X2TST4DSXGOP3U3L5UEUYLATQF/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":"2026-08-07T19:18:07Z","links":{"resolver":"https://pith.science/pith/X2TST4DSXGOP3U3L5UEUYLATQF","bundle":"https://pith.science/pith/X2TST4DSXGOP3U3L5UEUYLATQF/bundle.json","state":"https://pith.science/pith/X2TST4DSXGOP3U3L5UEUYLATQF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X2TST4DSXGOP3U3L5UEUYLATQF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:X2TST4DSXGOP3U3L5UEUYLATQF","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":"84801dac1875bc24af97cf827443e2a48f22f9ede742c1e14e1a3a20dca10289","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T17:55:33Z","title_canon_sha256":"6cb3d2cd2ae4fc7c68fe8db96ecca9821aff0de588ce3c39eeecf711adba3c7a"},"schema_version":"1.0","source":{"id":"2106.09700","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09700","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09700v2","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09700","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_12","alias_value":"X2TST4DSXGOP","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_16","alias_value":"X2TST4DSXGOP3U3L","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_8","alias_value":"X2TST4DS","created_at":"2026-07-05T03:15:52Z"}],"graph_snapshots":[{"event_id":"sha256:9cf3371fe5c78c236904c4a8b4234d8c2e70184d47ea47f40e9a8098078b9a4f","target":"graph","created_at":"2026-07-05T03:15:52Z","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/2106.09700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Biomedical knowledge graphs (KGs) hold rich information on entities such as diseases, drugs, and genes. Predicting missing links in these graphs can boost many important applications, such as drug design and repurposing. Recent work has shown that general-domain language models (LMs) can serve as \"soft\" KGs, and that they can be fine-tuned for the task of KG completion. In this work, we study scientific LMs for KG completion, exploring whether we can tap into their latent knowledge to enhance biomedical link prediction. We evaluate several domain-specific LMs, fine-tuning them on datasets cent","authors_text":"David Wadden, Hannaneh Hajishirzi, Iz Beltagy, Noah A. Smith, Rahul Nadkarni, Tom Hope","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T17:55:33Z","title":"Scientific Language Models for Biomedical Knowledge Base Completion: An Empirical Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09700","kind":"arxiv","version":2},"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":"sha256:4f2da71adfb9334002338edc0197d7a462b9def1286238fd725fe4e15085448e","target":"record","created_at":"2026-07-05T03:15:52Z","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":"84801dac1875bc24af97cf827443e2a48f22f9ede742c1e14e1a3a20dca10289","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T17:55:33Z","title_canon_sha256":"6cb3d2cd2ae4fc7c68fe8db96ecca9821aff0de588ce3c39eeecf711adba3c7a"},"schema_version":"1.0","source":{"id":"2106.09700","kind":"arxiv","version":2}},"canonical_sha256":"bea729f072b99cfdd36bed094c2c13817406a9c9dd5f8a9ab8bb1af7a1d75430","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bea729f072b99cfdd36bed094c2c13817406a9c9dd5f8a9ab8bb1af7a1d75430","first_computed_at":"2026-07-05T03:15:52.990900Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:52.990900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yZXBDzbl7tAQQ2/jwg2yt2JXG7pVHJvmz+O4c+ieDaEghOXDP86g96+xDIhGS3PIRfG6JnavfDOFQM8zt4SOAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:52.991416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.09700","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f2da71adfb9334002338edc0197d7a462b9def1286238fd725fe4e15085448e","sha256:9cf3371fe5c78c236904c4a8b4234d8c2e70184d47ea47f40e9a8098078b9a4f"],"state_sha256":"fc1dfb55751fdf15f87164f812babc18db0e5c84d06337268832acdad2aa5d6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lE5cixyHyfjXjor0nF+GSo7/onORtRDRoslY9Rw42BeoOukGfJq+NP23/6YJD54Jh+rsXk4qtuKDCum6QPl4Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:18:07.005547Z","bundle_sha256":"dc0bd0fd3aa0e2c8a0d7396cbcf4ccedf183652accdb3c43165ffc518618cd1b"}}