{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:O64GD2LGO6HCPSHMIHQXKP32KZ","short_pith_number":"pith:O64GD2LG","canonical_record":{"source":{"id":"2106.13375","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-06-25T01:02:55Z","cross_cats_sorted":["cs.CL","cs.DL"],"title_canon_sha256":"2354d6a71a83661246707ad660e967ba62c186102163a0a5f18d32cfeca83cc1","abstract_canon_sha256":"5b9f1ccaf22f41fd3a60104930099740a587bb68d03bacaae82ad6b350403d35"},"schema_version":"1.0"},"canonical_sha256":"77b861e966778e27c8ec41e1753f7a566f3ba683966bbbce46d4c2cdc90f52a3","source":{"kind":"arxiv","id":"2106.13375","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13375","created_at":"2026-07-05T03:15:11Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13375v2","created_at":"2026-07-05T03:15:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13375","created_at":"2026-07-05T03:15:11Z"},{"alias_kind":"pith_short_12","alias_value":"O64GD2LGO6HC","created_at":"2026-07-05T03:15:11Z"},{"alias_kind":"pith_short_16","alias_value":"O64GD2LGO6HCPSHM","created_at":"2026-07-05T03:15:11Z"},{"alias_kind":"pith_short_8","alias_value":"O64GD2LG","created_at":"2026-07-05T03:15:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:O64GD2LGO6HCPSHMIHQXKP32KZ","target":"record","payload":{"canonical_record":{"source":{"id":"2106.13375","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-06-25T01:02:55Z","cross_cats_sorted":["cs.CL","cs.DL"],"title_canon_sha256":"2354d6a71a83661246707ad660e967ba62c186102163a0a5f18d32cfeca83cc1","abstract_canon_sha256":"5b9f1ccaf22f41fd3a60104930099740a587bb68d03bacaae82ad6b350403d35"},"schema_version":"1.0"},"canonical_sha256":"77b861e966778e27c8ec41e1753f7a566f3ba683966bbbce46d4c2cdc90f52a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:11.017430Z","signature_b64":"EM9ZQmBPiSChY21Fs4/8ZtSZbKf9NSV0f64kPzChLq1bkgWWjDr3JgII6/bBaTFG98xYeq2So1AsaxYZgwypBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77b861e966778e27c8ec41e1753f7a566f3ba683966bbbce46d4c2cdc90f52a3","last_reissued_at":"2026-07-05T03:15:11.016979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:11.016979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.13375","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":"2026-07-05T03:15:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"thCYREtkvOePW+2CRU+y4UxNq+gStdcswnM7Qe6QMqgAW1RouabtHrG9GMFprEfUmZ73tllRUW40CtIzg+PRCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:12:41.290723Z"},"content_sha256":"256723bda24a459ecf3e66a3ee194a67c05959ecd99378267daca5d168f506ae","schema_version":"1.0","event_id":"sha256:256723bda24a459ecf3e66a3ee194a67c05959ecd99378267daca5d168f506ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:O64GD2LGO6HCPSHMIHQXKP32KZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Domain-Specific Pretraining for Vertical Search: Case Study on Biomedical Literature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.DL"],"primary_cat":"cs.IR","authors_text":"Chenyan Xiong, Cliff Wong, Eric Horvitz, Hao Cheng, Hoifung Poon, Jianfeng Gao, Jinchao Li, Naoto Usuyama, Paul N. Bennett, Richard Rogahn, Robert Tinn, Tristan Naumann, Yang Qin, Yu Wang, Zhihong Shen","submitted_at":"2021-06-25T01:02:55Z","abstract_excerpt":"Information overload is a prevalent challenge in many high-value domains. A prominent case in point is the explosion of the biomedical literature on COVID-19, which swelled to hundreds of thousands of papers in a matter of months. In general, biomedical literature expands by two papers every minute, totalling over a million new papers every year. Search in the biomedical realm, and many other vertical domains is challenging due to the scarcity of direct supervision from click logs. Self-supervised learning has emerged as a promising direction to overcome the annotation bottleneck. We propose a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13375","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/2106.13375/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":"2026-07-05T03:15:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PexwpYoXMRyrdzw77nn+TGziVvvFKN+KjTCfL4pg2W2y8rf6XhMxYLRcFz3NfJZPREcugTNAyZgjITfH2aUPDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:12:41.291096Z"},"content_sha256":"ced5e7b8a14ec4649301648e07d8e107f1f162bd5d2f413e6b88c807733c5803","schema_version":"1.0","event_id":"sha256:ced5e7b8a14ec4649301648e07d8e107f1f162bd5d2f413e6b88c807733c5803"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O64GD2LGO6HCPSHMIHQXKP32KZ/bundle.json","state_url":"https://pith.science/pith/O64GD2LGO6HCPSHMIHQXKP32KZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O64GD2LGO6HCPSHMIHQXKP32KZ/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":"2026-07-06T23:12:41Z","links":{"resolver":"https://pith.science/pith/O64GD2LGO6HCPSHMIHQXKP32KZ","bundle":"https://pith.science/pith/O64GD2LGO6HCPSHMIHQXKP32KZ/bundle.json","state":"https://pith.science/pith/O64GD2LGO6HCPSHMIHQXKP32KZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O64GD2LGO6HCPSHMIHQXKP32KZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:O64GD2LGO6HCPSHMIHQXKP32KZ","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":"5b9f1ccaf22f41fd3a60104930099740a587bb68d03bacaae82ad6b350403d35","cross_cats_sorted":["cs.CL","cs.DL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-06-25T01:02:55Z","title_canon_sha256":"2354d6a71a83661246707ad660e967ba62c186102163a0a5f18d32cfeca83cc1"},"schema_version":"1.0","source":{"id":"2106.13375","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13375","created_at":"2026-07-05T03:15:11Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13375v2","created_at":"2026-07-05T03:15:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13375","created_at":"2026-07-05T03:15:11Z"},{"alias_kind":"pith_short_12","alias_value":"O64GD2LGO6HC","created_at":"2026-07-05T03:15:11Z"},{"alias_kind":"pith_short_16","alias_value":"O64GD2LGO6HCPSHM","created_at":"2026-07-05T03:15:11Z"},{"alias_kind":"pith_short_8","alias_value":"O64GD2LG","created_at":"2026-07-05T03:15:11Z"}],"graph_snapshots":[{"event_id":"sha256:ced5e7b8a14ec4649301648e07d8e107f1f162bd5d2f413e6b88c807733c5803","target":"graph","created_at":"2026-07-05T03:15:11Z","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/2106.13375/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Information overload is a prevalent challenge in many high-value domains. A prominent case in point is the explosion of the biomedical literature on COVID-19, which swelled to hundreds of thousands of papers in a matter of months. In general, biomedical literature expands by two papers every minute, totalling over a million new papers every year. Search in the biomedical realm, and many other vertical domains is challenging due to the scarcity of direct supervision from click logs. Self-supervised learning has emerged as a promising direction to overcome the annotation bottleneck. We propose a","authors_text":"Chenyan Xiong, Cliff Wong, Eric Horvitz, Hao Cheng, Hoifung Poon, Jianfeng Gao, Jinchao Li, Naoto Usuyama, Paul N. Bennett, Richard Rogahn, Robert Tinn, Tristan Naumann, Yang Qin, Yu Wang, Zhihong Shen","cross_cats":["cs.CL","cs.DL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-06-25T01:02:55Z","title":"Domain-Specific Pretraining for Vertical Search: Case Study on Biomedical Literature"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13375","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":"sha256:256723bda24a459ecf3e66a3ee194a67c05959ecd99378267daca5d168f506ae","target":"record","created_at":"2026-07-05T03:15:11Z","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":"5b9f1ccaf22f41fd3a60104930099740a587bb68d03bacaae82ad6b350403d35","cross_cats_sorted":["cs.CL","cs.DL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-06-25T01:02:55Z","title_canon_sha256":"2354d6a71a83661246707ad660e967ba62c186102163a0a5f18d32cfeca83cc1"},"schema_version":"1.0","source":{"id":"2106.13375","kind":"arxiv","version":2}},"canonical_sha256":"77b861e966778e27c8ec41e1753f7a566f3ba683966bbbce46d4c2cdc90f52a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77b861e966778e27c8ec41e1753f7a566f3ba683966bbbce46d4c2cdc90f52a3","first_computed_at":"2026-07-05T03:15:11.016979Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:11.016979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EM9ZQmBPiSChY21Fs4/8ZtSZbKf9NSV0f64kPzChLq1bkgWWjDr3JgII6/bBaTFG98xYeq2So1AsaxYZgwypBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:11.017430Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.13375","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:256723bda24a459ecf3e66a3ee194a67c05959ecd99378267daca5d168f506ae","sha256:ced5e7b8a14ec4649301648e07d8e107f1f162bd5d2f413e6b88c807733c5803"],"state_sha256":"7dbaa82a66713ab2f1a5825d520df827987f505297f85840fa790db1dd62bf24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ENciHBWV2aRJ9mEUg/M3Zmnc7M9NxXmToUD5kB9uG3kec6moAlobsIX7Gdwe6u02ljCYxIstwdZjFEu/TV58AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:12:41.293083Z","bundle_sha256":"4b1fecb562b86040ebfab1f66e3015945ddc679693e7c995de18b439ed229575"}}