{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5ZBWWFNZRQBPCB7S5YODOLBE4R","short_pith_number":"pith:5ZBWWFNZ","schema_version":"1.0","canonical_sha256":"ee436b15b98c02f107f2ee1c372c24e4573b3d4a3942b0d9179ad6611b5cd120","source":{"kind":"arxiv","id":"2507.08191","version":1},"attestation_state":"computed","paper":{"title":"Overview of the TREC 2021 deep learning track","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Bhaskar Mitra, Daniel Campos, Emine Yilmaz, Jimmy Lin, Nick Craswell","submitted_at":"2025-07-10T21:58:41Z","abstract_excerpt":"This is the third year of the TREC Deep Learning track. As in previous years, we leverage the MS MARCO datasets that made hundreds of thousands of human annotated training labels available for both passage and document ranking tasks. In addition, this year we refreshed both the document and the passage collections which also led to a nearly four times increase in the document collection size and nearly $16$ times increase in the size of the passage collection. Deep neural ranking models that employ large scale pretraininig continued to outperform traditional retrieval methods this year. We als"},"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":"2507.08191","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-07-10T21:58:41Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"5d22f7623e9cbb76ee7caee6bae3eb8186715ff0c0d10027d2a9f457fc430566","abstract_canon_sha256":"91d9e4106f4697c0b25bc6ef374ad766118318c27ab4a35ec672ef696f6edfb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:19.016381Z","signature_b64":"s2KvQG21N8/tADIQLg/CcGebv0bZwsNUqI5lCYZnQYlHqjabR4D6CL7NPw/uLCBGOTHJPbdPlm9Z5mwFdDExBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee436b15b98c02f107f2ee1c372c24e4573b3d4a3942b0d9179ad6611b5cd120","last_reissued_at":"2026-07-05T11:35:19.015928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:19.015928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overview of the TREC 2021 deep learning track","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Bhaskar Mitra, Daniel Campos, Emine Yilmaz, Jimmy Lin, Nick Craswell","submitted_at":"2025-07-10T21:58:41Z","abstract_excerpt":"This is the third year of the TREC Deep Learning track. As in previous years, we leverage the MS MARCO datasets that made hundreds of thousands of human annotated training labels available for both passage and document ranking tasks. In addition, this year we refreshed both the document and the passage collections which also led to a nearly four times increase in the document collection size and nearly $16$ times increase in the size of the passage collection. Deep neural ranking models that employ large scale pretraininig continued to outperform traditional retrieval methods this year. We als"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08191","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/2507.08191/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":"2507.08191","created_at":"2026-07-05T11:35:19.015989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.08191v1","created_at":"2026-07-05T11:35:19.015989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08191","created_at":"2026-07-05T11:35:19.015989+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZBWWFNZRQBP","created_at":"2026-07-05T11:35:19.015989+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZBWWFNZRQBPCB7S","created_at":"2026-07-05T11:35:19.015989+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZBWWFNZ","created_at":"2026-07-05T11:35:19.015989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01162","citing_title":"Trie-based Experiment Plans for Efficient IR Pipeline Experiments","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28522","citing_title":"Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerability","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27244","citing_title":"RAQG-QPP: Query Performance Prediction with Retrieved Query Variants and Retrieval Augmented Query Generation","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ZBWWFNZRQBPCB7S5YODOLBE4R","json":"https://pith.science/pith/5ZBWWFNZRQBPCB7S5YODOLBE4R.json","graph_json":"https://pith.science/api/pith-number/5ZBWWFNZRQBPCB7S5YODOLBE4R/graph.json","events_json":"https://pith.science/api/pith-number/5ZBWWFNZRQBPCB7S5YODOLBE4R/events.json","paper":"https://pith.science/paper/5ZBWWFNZ"},"agent_actions":{"view_html":"https://pith.science/pith/5ZBWWFNZRQBPCB7S5YODOLBE4R","download_json":"https://pith.science/pith/5ZBWWFNZRQBPCB7S5YODOLBE4R.json","view_paper":"https://pith.science/paper/5ZBWWFNZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.08191&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZBWWFNZRQBPCB7S5YODOLBE4R/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZBWWFNZRQBPCB7S5YODOLBE4R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZBWWFNZRQBPCB7S5YODOLBE4R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZBWWFNZRQBPCB7S5YODOLBE4R/action/storage_attestation","attest_author":"https://pith.science/pith/5ZBWWFNZRQBPCB7S5YODOLBE4R/action/author_attestation","sign_citation":"https://pith.science/pith/5ZBWWFNZRQBPCB7S5YODOLBE4R/action/citation_signature","submit_replication":"https://pith.science/pith/5ZBWWFNZRQBPCB7S5YODOLBE4R/action/replication_record"}},"created_at":"2026-07-05T11:35:19.015989+00:00","updated_at":"2026-07-05T11:35:19.015989+00:00"}