{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QSUN37DEEFDTLPAVA7MTLK65TD","short_pith_number":"pith:QSUN37DE","schema_version":"1.0","canonical_sha256":"84a8ddfc64214735bc1507d935abdd98ce750d0d8132c53daa451eb734b33842","source":{"kind":"arxiv","id":"2102.07662","version":1},"attestation_state":"computed","paper":{"title":"Overview of the TREC 2020 deep learning track","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Bhaskar Mitra, Daniel Campos, Emine Yilmaz, Nick Craswell","submitted_at":"2021-02-15T16:47:00Z","abstract_excerpt":"This is the second year of the TREC Deep Learning Track, with the goal of studying ad hoc ranking in the large training data regime. We again have a document retrieval task and a passage retrieval task, each with hundreds of thousands of human-labeled training queries. We evaluate using single-shot TREC-style evaluation, to give us a picture of which ranking methods work best when large data is available, with much more comprehensive relevance labeling on the small number of test queries. This year we have further evidence that rankers with BERT-style pretraining outperform other rankers in th"},"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":"2102.07662","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-02-15T16:47:00Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"270ed50501f869129d9860774fcb19eafaff5809e76a07fa3b0194d102475f27","abstract_canon_sha256":"f0ba9e395bcf28d3e58a3da4b81e9a0fa93da60e4b0a340fcf045857a263254e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:18.673765Z","signature_b64":"ETtjREY+WzFg/1uSvtQ+5NhTwAAV5eJWJm4lnjkBdoV5VXIlb6D7mQL6rVcXUAS2Yp+LUAJ76nck2mseT8ETBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84a8ddfc64214735bc1507d935abdd98ce750d0d8132c53daa451eb734b33842","last_reissued_at":"2026-07-05T02:15:18.673290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:18.673290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overview of the TREC 2020 deep learning track","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Bhaskar Mitra, Daniel Campos, Emine Yilmaz, Nick Craswell","submitted_at":"2021-02-15T16:47:00Z","abstract_excerpt":"This is the second year of the TREC Deep Learning Track, with the goal of studying ad hoc ranking in the large training data regime. We again have a document retrieval task and a passage retrieval task, each with hundreds of thousands of human-labeled training queries. We evaluate using single-shot TREC-style evaluation, to give us a picture of which ranking methods work best when large data is available, with much more comprehensive relevance labeling on the small number of test queries. This year we have further evidence that rankers with BERT-style pretraining outperform other rankers in th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07662","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/2102.07662/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":"2102.07662","created_at":"2026-07-05T02:15:18.673360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.07662v1","created_at":"2026-07-05T02:15:18.673360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07662","created_at":"2026-07-05T02:15:18.673360+00:00"},{"alias_kind":"pith_short_12","alias_value":"QSUN37DEEFDT","created_at":"2026-07-05T02:15:18.673360+00:00"},{"alias_kind":"pith_short_16","alias_value":"QSUN37DEEFDTLPAV","created_at":"2026-07-05T02:15:18.673360+00:00"},{"alias_kind":"pith_short_8","alias_value":"QSUN37DE","created_at":"2026-07-05T02:15:18.673360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.00860","citing_title":"A Counterfactual Explanation Framework for Retrieval Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20683","citing_title":"Layer-wise Token Compression for Efficient Document Reranking","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20683","citing_title":"Layer-wise Token Compression for Efficient Document Reranking","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2601.05649","citing_title":"Statistical Foundations of DIME: Risk Estimation for Practical Index Selection","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22591","citing_title":"Where Relevance Emerges: A Layer-Wise Study of Internal Attention for Zero-Shot Re-Ranking","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27421","citing_title":"A Reproducibility Study of LLM-Based Query Reformulation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26483","citing_title":"Efficient Listwise Reranking with Compressed Document Representations","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27037","citing_title":"Hypencoder Revisited: Reproducibility and Analysis of Non-Linear Scoring for First-Stage Retrieval","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08737","citing_title":"The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22180","citing_title":"ResRank: Unifying Retrieval and Listwise Reranking via End-to-End Joint Training with Residual Passage Compression","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01591","citing_title":"Led to Mislead: Adversarial Content Injection for Attacks on Neural Ranking Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09492","citing_title":"Dynamic Ranked List Truncation for Reranking Pipelines via LLM-generated Reference-Documents","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08834","citing_title":"BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Elimination","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06163","citing_title":"Data, Not Model: Explaining Bias toward LLM Texts in Neural Retrievers","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QSUN37DEEFDTLPAVA7MTLK65TD","json":"https://pith.science/pith/QSUN37DEEFDTLPAVA7MTLK65TD.json","graph_json":"https://pith.science/api/pith-number/QSUN37DEEFDTLPAVA7MTLK65TD/graph.json","events_json":"https://pith.science/api/pith-number/QSUN37DEEFDTLPAVA7MTLK65TD/events.json","paper":"https://pith.science/paper/QSUN37DE"},"agent_actions":{"view_html":"https://pith.science/pith/QSUN37DEEFDTLPAVA7MTLK65TD","download_json":"https://pith.science/pith/QSUN37DEEFDTLPAVA7MTLK65TD.json","view_paper":"https://pith.science/paper/QSUN37DE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.07662&json=true","fetch_graph":"https://pith.science/api/pith-number/QSUN37DEEFDTLPAVA7MTLK65TD/graph.json","fetch_events":"https://pith.science/api/pith-number/QSUN37DEEFDTLPAVA7MTLK65TD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QSUN37DEEFDTLPAVA7MTLK65TD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QSUN37DEEFDTLPAVA7MTLK65TD/action/storage_attestation","attest_author":"https://pith.science/pith/QSUN37DEEFDTLPAVA7MTLK65TD/action/author_attestation","sign_citation":"https://pith.science/pith/QSUN37DEEFDTLPAVA7MTLK65TD/action/citation_signature","submit_replication":"https://pith.science/pith/QSUN37DEEFDTLPAVA7MTLK65TD/action/replication_record"}},"created_at":"2026-07-05T02:15:18.673360+00:00","updated_at":"2026-07-05T02:15:18.673360+00:00"}