{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:BDWI55HMEM7HJBQ2OX3GC6YKLY","short_pith_number":"pith:BDWI55HM","schema_version":"1.0","canonical_sha256":"08ec8ef4ec233e74861a75f6617b0a5e2a4101b41408fb04cd3c73593b18173d","source":{"kind":"arxiv","id":"1601.01611","version":1},"attestation_state":"computed","paper":{"title":"Automatic Construction of Evaluation Sets and Evaluation of Document Similarity Models in Large Scholarly Retrieval Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"David A. Smith, Kriste Krstovski, Michael J. Kurtz","submitted_at":"2016-01-07T17:27:31Z","abstract_excerpt":"Retrieval systems for scholarly literature offer the ability for the scientific community to search, explore and download scholarly articles across various scientific disciplines. Mostly used by the experts in the particular field, these systems contain user community logs including information on user specific downloaded articles. In this paper we present a novel approach for automatically evaluating document similarity models in large collections of scholarly publications. Unlike typical evaluation settings that use test collections consisting of query documents and human annotated relevance"},"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":"1601.01611","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-01-07T17:27:31Z","cross_cats_sorted":[],"title_canon_sha256":"bc03e2cd9732407aa3e27bcdb249c4d48a971b2781481cfe7dc9ab0debc1c498","abstract_canon_sha256":"947ce7632e1c78db9c1b143bcc5d7cc1faf4346f5fb73d90047d8766ef48cd76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:23:13.215443Z","signature_b64":"gWn+EXTjnRFwOpe+LMvVy1nkC47WEtomvmalzl9qwZJkmH0u2wBl/k7V0AJr8bIZ5Lnhur0vffnJtTrk3jaXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08ec8ef4ec233e74861a75f6617b0a5e2a4101b41408fb04cd3c73593b18173d","last_reissued_at":"2026-05-18T01:23:13.214722Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:23:13.214722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Construction of Evaluation Sets and Evaluation of Document Similarity Models in Large Scholarly Retrieval Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"David A. Smith, Kriste Krstovski, Michael J. Kurtz","submitted_at":"2016-01-07T17:27:31Z","abstract_excerpt":"Retrieval systems for scholarly literature offer the ability for the scientific community to search, explore and download scholarly articles across various scientific disciplines. Mostly used by the experts in the particular field, these systems contain user community logs including information on user specific downloaded articles. In this paper we present a novel approach for automatically evaluating document similarity models in large collections of scholarly publications. Unlike typical evaluation settings that use test collections consisting of query documents and human annotated relevance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.01611","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":""},"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":"1601.01611","created_at":"2026-05-18T01:23:13.214842+00:00"},{"alias_kind":"arxiv_version","alias_value":"1601.01611v1","created_at":"2026-05-18T01:23:13.214842+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.01611","created_at":"2026-05-18T01:23:13.214842+00:00"},{"alias_kind":"pith_short_12","alias_value":"BDWI55HMEM7H","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_16","alias_value":"BDWI55HMEM7HJBQ2","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_8","alias_value":"BDWI55HM","created_at":"2026-05-18T12:30:07.202191+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/BDWI55HMEM7HJBQ2OX3GC6YKLY","json":"https://pith.science/pith/BDWI55HMEM7HJBQ2OX3GC6YKLY.json","graph_json":"https://pith.science/api/pith-number/BDWI55HMEM7HJBQ2OX3GC6YKLY/graph.json","events_json":"https://pith.science/api/pith-number/BDWI55HMEM7HJBQ2OX3GC6YKLY/events.json","paper":"https://pith.science/paper/BDWI55HM"},"agent_actions":{"view_html":"https://pith.science/pith/BDWI55HMEM7HJBQ2OX3GC6YKLY","download_json":"https://pith.science/pith/BDWI55HMEM7HJBQ2OX3GC6YKLY.json","view_paper":"https://pith.science/paper/BDWI55HM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1601.01611&json=true","fetch_graph":"https://pith.science/api/pith-number/BDWI55HMEM7HJBQ2OX3GC6YKLY/graph.json","fetch_events":"https://pith.science/api/pith-number/BDWI55HMEM7HJBQ2OX3GC6YKLY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BDWI55HMEM7HJBQ2OX3GC6YKLY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BDWI55HMEM7HJBQ2OX3GC6YKLY/action/storage_attestation","attest_author":"https://pith.science/pith/BDWI55HMEM7HJBQ2OX3GC6YKLY/action/author_attestation","sign_citation":"https://pith.science/pith/BDWI55HMEM7HJBQ2OX3GC6YKLY/action/citation_signature","submit_replication":"https://pith.science/pith/BDWI55HMEM7HJBQ2OX3GC6YKLY/action/replication_record"}},"created_at":"2026-05-18T01:23:13.214842+00:00","updated_at":"2026-05-18T01:23:13.214842+00:00"}