{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YELSG422TYBIF6MNLB75XWN5ZY","short_pith_number":"pith:YELSG422","schema_version":"1.0","canonical_sha256":"c11723735a9e0282f98d587fdbd9bdce2fc759bced929c8d15aa0a8542e0943b","source":{"kind":"arxiv","id":"2507.10865","version":1},"attestation_state":"computed","paper":{"title":"Overview of the TREC 2022 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, Ellen M. Voorhees, Emine Yilmaz, Ian Soboroff, Jimmy Lin, Nick Craswell","submitted_at":"2025-07-10T20:48:22Z","abstract_excerpt":"This is the fourth 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 also leverage both the refreshed passage and document collections that were released last year leading to a nearly $16$ times increase in the size of the passage collection and nearly four times increase in the document collection size. Unlike previous years, in 2022 we mainly focused on constructing a more complete test collection for t"},"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":"2507.10865","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-07-10T20:48:22Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"9d6610b80ea2aeb64491b8dec0340e6761d8ac877e7b90e8d4d4f43540195a30","abstract_canon_sha256":"75083a798b3b2ef98cd37b62ca7c23d6401c1398850a444aeb29dca7cb1c766a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:27.211791Z","signature_b64":"f0Z6d+amJUw+xudQd7yHgdmBqWVe0W7/4afISJRKuE+yJn3M2/wXXB5mxjnFGKLzcfwNDcUFHkHg1c8gLjSEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c11723735a9e0282f98d587fdbd9bdce2fc759bced929c8d15aa0a8542e0943b","last_reissued_at":"2026-07-05T11:37:27.211288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:27.211288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overview of the TREC 2022 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, Ellen M. Voorhees, Emine Yilmaz, Ian Soboroff, Jimmy Lin, Nick Craswell","submitted_at":"2025-07-10T20:48:22Z","abstract_excerpt":"This is the fourth 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 also leverage both the refreshed passage and document collections that were released last year leading to a nearly $16$ times increase in the size of the passage collection and nearly four times increase in the document collection size. Unlike previous years, in 2022 we mainly focused on constructing a more complete test collection for t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10865","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/2507.10865/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":"2507.10865","created_at":"2026-07-05T11:37:27.211353+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10865v1","created_at":"2026-07-05T11:37:27.211353+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10865","created_at":"2026-07-05T11:37:27.211353+00:00"},{"alias_kind":"pith_short_12","alias_value":"YELSG422TYBI","created_at":"2026-07-05T11:37:27.211353+00:00"},{"alias_kind":"pith_short_16","alias_value":"YELSG422TYBIF6MN","created_at":"2026-07-05T11:37:27.211353+00:00"},{"alias_kind":"pith_short_8","alias_value":"YELSG422","created_at":"2026-07-05T11:37:27.211353+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.00004","citing_title":"Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2606.03535","citing_title":"Can LLM Rerankers Predict Their Own Ranking Performance?","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":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05204","citing_title":"Entities as Retrieval Signals: A Systematic Study of Coverage, Supervision, and Evaluation in Entity-Oriented Ranking","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YELSG422TYBIF6MNLB75XWN5ZY","json":"https://pith.science/pith/YELSG422TYBIF6MNLB75XWN5ZY.json","graph_json":"https://pith.science/api/pith-number/YELSG422TYBIF6MNLB75XWN5ZY/graph.json","events_json":"https://pith.science/api/pith-number/YELSG422TYBIF6MNLB75XWN5ZY/events.json","paper":"https://pith.science/paper/YELSG422"},"agent_actions":{"view_html":"https://pith.science/pith/YELSG422TYBIF6MNLB75XWN5ZY","download_json":"https://pith.science/pith/YELSG422TYBIF6MNLB75XWN5ZY.json","view_paper":"https://pith.science/paper/YELSG422","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10865&json=true","fetch_graph":"https://pith.science/api/pith-number/YELSG422TYBIF6MNLB75XWN5ZY/graph.json","fetch_events":"https://pith.science/api/pith-number/YELSG422TYBIF6MNLB75XWN5ZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YELSG422TYBIF6MNLB75XWN5ZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YELSG422TYBIF6MNLB75XWN5ZY/action/storage_attestation","attest_author":"https://pith.science/pith/YELSG422TYBIF6MNLB75XWN5ZY/action/author_attestation","sign_citation":"https://pith.science/pith/YELSG422TYBIF6MNLB75XWN5ZY/action/citation_signature","submit_replication":"https://pith.science/pith/YELSG422TYBIF6MNLB75XWN5ZY/action/replication_record"}},"created_at":"2026-07-05T11:37:27.211353+00:00","updated_at":"2026-07-05T11:37:27.211353+00:00"}