{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:OOYIO736H6GAN5DL77MBBQF6X6","short_pith_number":"pith:OOYIO736","schema_version":"1.0","canonical_sha256":"73b0877f7e3f8c06f46bffd810c0bebfb1c66f8bc4b2a923e56e5763aa977deb","source":{"kind":"arxiv","id":"2003.07820","version":2},"attestation_state":"computed","paper":{"title":"Overview of the TREC 2019 deep learning track","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Bhaskar Mitra, Daniel Campos, Ellen M. Voorhees, Emine Yilmaz, Nick Craswell","submitted_at":"2020-03-17T17:12:36Z","abstract_excerpt":"The Deep Learning Track is a new track for TREC 2019, with the goal of studying ad hoc ranking in a large data regime. It is the first track with large human-labeled training sets, introducing two sets corresponding to two tasks, each with rigorous TREC-style blind evaluation and reusable test sets. The document retrieval task has a corpus of 3.2 million documents with 367 thousand training queries, for which we generate a reusable test set of 43 queries. The passage retrieval task has a corpus of 8.8 million passages with 503 thousand training queries, for which we generate a reusable test se"},"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":"2003.07820","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-03-17T17:12:36Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"8d27de55168eceeb9f28a68a6fa66f26944f6cacab80c2079e17387d5cbf8077","abstract_canon_sha256":"5158fff99c75be6d990060ef1783ae71d02b7ca1d733786955d0f4c5fadeed4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:02.331660Z","signature_b64":"6PsNfKukEfsc6y63/hbNwrYzIG8mqF4YSP948PvNUSgVRzmmoaFjCIH7zcmQn9UGh7kGuVP8FPlHi8e9fnNmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73b0877f7e3f8c06f46bffd810c0bebfb1c66f8bc4b2a923e56e5763aa977deb","last_reissued_at":"2026-07-05T00:49:02.331135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:02.331135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overview of the TREC 2019 deep learning track","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Bhaskar Mitra, Daniel Campos, Ellen M. Voorhees, Emine Yilmaz, Nick Craswell","submitted_at":"2020-03-17T17:12:36Z","abstract_excerpt":"The Deep Learning Track is a new track for TREC 2019, with the goal of studying ad hoc ranking in a large data regime. It is the first track with large human-labeled training sets, introducing two sets corresponding to two tasks, each with rigorous TREC-style blind evaluation and reusable test sets. The document retrieval task has a corpus of 3.2 million documents with 367 thousand training queries, for which we generate a reusable test set of 43 queries. The passage retrieval task has a corpus of 8.8 million passages with 503 thousand training queries, for which we generate a reusable test se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.07820","kind":"arxiv","version":2},"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/2003.07820/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":"2003.07820","created_at":"2026-07-05T00:49:02.331190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.07820v2","created_at":"2026-07-05T00:49:02.331190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.07820","created_at":"2026-07-05T00:49:02.331190+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOYIO736H6GA","created_at":"2026-07-05T00:49:02.331190+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOYIO736H6GAN5DL","created_at":"2026-07-05T00:49:02.331190+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOYIO736","created_at":"2026-07-05T00:49:02.331190+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01162","citing_title":"Trie-based Experiment Plans for Efficient IR Pipeline Experiments","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07210","citing_title":"DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2502.00709","citing_title":"RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20683","citing_title":"Layer-wise Token Compression for Efficient Document Reranking","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2509.00303","citing_title":"Access Paths for Efficient Ordering with Large Language Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20683","citing_title":"Layer-wise Token Compression for Efficient Document Reranking","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2601.05649","citing_title":"Statistical Foundations of DIME: Risk Estimation for Practical Index Selection","ref_index":3,"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":4,"is_internal_anchor":false},{"citing_arxiv_id":"2603.04816","citing_title":"Scaling Laws for Cross-Encoder Reranking","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04140","citing_title":"Formalized Information Needs Improve Large-Language-Model Relevance Judgments","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2311.12983","citing_title":"GAIA: a benchmark for General AI Assistants","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27421","citing_title":"A Reproducibility Study of LLM-Based Query Reformulation","ref_index":9,"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":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26483","citing_title":"Efficient Listwise Reranking with Compressed Document Representations","ref_index":8,"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":11,"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":25,"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":14,"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":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06163","citing_title":"Data, Not Model: Explaining Bias toward LLM Texts in Neural Retrievers","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04734","citing_title":"Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17237","citing_title":"HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention Heads","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOYIO736H6GAN5DL77MBBQF6X6","json":"https://pith.science/pith/OOYIO736H6GAN5DL77MBBQF6X6.json","graph_json":"https://pith.science/api/pith-number/OOYIO736H6GAN5DL77MBBQF6X6/graph.json","events_json":"https://pith.science/api/pith-number/OOYIO736H6GAN5DL77MBBQF6X6/events.json","paper":"https://pith.science/paper/OOYIO736"},"agent_actions":{"view_html":"https://pith.science/pith/OOYIO736H6GAN5DL77MBBQF6X6","download_json":"https://pith.science/pith/OOYIO736H6GAN5DL77MBBQF6X6.json","view_paper":"https://pith.science/paper/OOYIO736","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.07820&json=true","fetch_graph":"https://pith.science/api/pith-number/OOYIO736H6GAN5DL77MBBQF6X6/graph.json","fetch_events":"https://pith.science/api/pith-number/OOYIO736H6GAN5DL77MBBQF6X6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOYIO736H6GAN5DL77MBBQF6X6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOYIO736H6GAN5DL77MBBQF6X6/action/storage_attestation","attest_author":"https://pith.science/pith/OOYIO736H6GAN5DL77MBBQF6X6/action/author_attestation","sign_citation":"https://pith.science/pith/OOYIO736H6GAN5DL77MBBQF6X6/action/citation_signature","submit_replication":"https://pith.science/pith/OOYIO736H6GAN5DL77MBBQF6X6/action/replication_record"}},"created_at":"2026-07-05T00:49:02.331190+00:00","updated_at":"2026-07-05T00:49:02.331190+00:00"}