{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:YJKO5W47H3XKFEG4P6ABMBXZ2A","short_pith_number":"pith:YJKO5W47","schema_version":"1.0","canonical_sha256":"c254eedb9f3eeea290dc7f801606f9d036e8b41d5871daaad28e20673c46cb54","source":{"kind":"arxiv","id":"1707.00189","version":3},"attestation_state":"computed","paper":{"title":"Content-Based Weak Supervision for Ad-Hoc Re-Ranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Andrew Yates, Kai Hui, Ophir Frieder, Sean MacAvaney","submitted_at":"2017-07-01T18:42:29Z","abstract_excerpt":"One challenge with neural ranking is the need for a large amount of manually-labeled relevance judgments for training. In contrast with prior work, we examine the use of weak supervision sources for training that yield pseudo query-document pairs that already exhibit relevance (e.g., newswire headline-content pairs and encyclopedic heading-paragraph pairs). We also propose filtering techniques to eliminate training samples that are too far out of domain using two techniques: a heuristic-based approach and novel supervised filter that re-purposes a neural ranker. Using several leading neural ra"},"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":"1707.00189","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-07-01T18:42:29Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8042d546711f39f090a9060896158d397bd7dc52e53a3823d7084f350600aecd","abstract_canon_sha256":"57c0948e94d278ef70158e873fac52da73ae5d6f3e0b6dcab7c708e6b9faae88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:27.991073Z","signature_b64":"gEKaLhUy4kBbQAokdQSpDyuTJxc5QwAYdlW/UUzO2FvDBco4A/VwAfotpV+X9Uen+xqGNIm+cWurR3KgFd+QBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c254eedb9f3eeea290dc7f801606f9d036e8b41d5871daaad28e20673c46cb54","last_reissued_at":"2026-05-17T23:41:27.990291Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:27.990291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Content-Based Weak Supervision for Ad-Hoc Re-Ranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Andrew Yates, Kai Hui, Ophir Frieder, Sean MacAvaney","submitted_at":"2017-07-01T18:42:29Z","abstract_excerpt":"One challenge with neural ranking is the need for a large amount of manually-labeled relevance judgments for training. In contrast with prior work, we examine the use of weak supervision sources for training that yield pseudo query-document pairs that already exhibit relevance (e.g., newswire headline-content pairs and encyclopedic heading-paragraph pairs). We also propose filtering techniques to eliminate training samples that are too far out of domain using two techniques: a heuristic-based approach and novel supervised filter that re-purposes a neural ranker. Using several leading neural ra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.00189","kind":"arxiv","version":3},"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":"1707.00189","created_at":"2026-05-17T23:41:27.990432+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.00189v3","created_at":"2026-05-17T23:41:27.990432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.00189","created_at":"2026-05-17T23:41:27.990432+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJKO5W47H3XK","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJKO5W47H3XKFEG4","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJKO5W47","created_at":"2026-05-18T12:31:56.362134+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/YJKO5W47H3XKFEG4P6ABMBXZ2A","json":"https://pith.science/pith/YJKO5W47H3XKFEG4P6ABMBXZ2A.json","graph_json":"https://pith.science/api/pith-number/YJKO5W47H3XKFEG4P6ABMBXZ2A/graph.json","events_json":"https://pith.science/api/pith-number/YJKO5W47H3XKFEG4P6ABMBXZ2A/events.json","paper":"https://pith.science/paper/YJKO5W47"},"agent_actions":{"view_html":"https://pith.science/pith/YJKO5W47H3XKFEG4P6ABMBXZ2A","download_json":"https://pith.science/pith/YJKO5W47H3XKFEG4P6ABMBXZ2A.json","view_paper":"https://pith.science/paper/YJKO5W47","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.00189&json=true","fetch_graph":"https://pith.science/api/pith-number/YJKO5W47H3XKFEG4P6ABMBXZ2A/graph.json","fetch_events":"https://pith.science/api/pith-number/YJKO5W47H3XKFEG4P6ABMBXZ2A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJKO5W47H3XKFEG4P6ABMBXZ2A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJKO5W47H3XKFEG4P6ABMBXZ2A/action/storage_attestation","attest_author":"https://pith.science/pith/YJKO5W47H3XKFEG4P6ABMBXZ2A/action/author_attestation","sign_citation":"https://pith.science/pith/YJKO5W47H3XKFEG4P6ABMBXZ2A/action/citation_signature","submit_replication":"https://pith.science/pith/YJKO5W47H3XKFEG4P6ABMBXZ2A/action/replication_record"}},"created_at":"2026-05-17T23:41:27.990432+00:00","updated_at":"2026-05-17T23:41:27.990432+00:00"}