{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EUUBRITOVMIGHN4SOZKHCAEWIQ","short_pith_number":"pith:EUUBRITO","schema_version":"1.0","canonical_sha256":"252818a26eab1063b792765471009644213e890d9b5fe92fdee9fc0a185e40a9","source":{"kind":"arxiv","id":"2004.12832","version":2},"attestation_state":"computed","paper":{"title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Matei Zaharia, Omar Khattab","submitted_at":"2020-04-27T14:21:03Z","abstract_excerpt":"Recent progress in Natural Language Understanding (NLU) is driving fast-paced advances in Information Retrieval (IR), largely owed to fine-tuning deep language models (LMs) for document ranking. While remarkably effective, the ranking models based on these LMs increase computational cost by orders of magnitude over prior approaches, particularly as they must feed each query-document pair through a massive neural network to compute a single relevance score. To tackle this, we present ColBERT, a novel ranking model that adapts deep LMs (in particular, BERT) for efficient retrieval. ColBERT intro"},"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":"2004.12832","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-04-27T14:21:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"81cc73fae3211a07ce87ec5eea776e4bcdec59be28e5905b084af2f172fa0433","abstract_canon_sha256":"79c3100a5bcfb6c33e4385b906af45298fe060629de2878766369d293a5de0ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:53.691954Z","signature_b64":"g9RvXQHRXINMazy0Q9fJknzuTKesfBhIg/fzxd9C6fEuL/Bhaqt+zk4ofgG6F3dcLglXvRIp8unG9sC3Zf3RDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"252818a26eab1063b792765471009644213e890d9b5fe92fdee9fc0a185e40a9","last_reissued_at":"2026-07-05T01:07:53.691524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:53.691524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Matei Zaharia, Omar Khattab","submitted_at":"2020-04-27T14:21:03Z","abstract_excerpt":"Recent progress in Natural Language Understanding (NLU) is driving fast-paced advances in Information Retrieval (IR), largely owed to fine-tuning deep language models (LMs) for document ranking. While remarkably effective, the ranking models based on these LMs increase computational cost by orders of magnitude over prior approaches, particularly as they must feed each query-document pair through a massive neural network to compute a single relevance score. To tackle this, we present ColBERT, a novel ranking model that adapts deep LMs (in particular, BERT) for efficient retrieval. ColBERT intro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12832","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/2004.12832/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":"2004.12832","created_at":"2026-07-05T01:07:53.691590+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.12832v2","created_at":"2026-07-05T01:07:53.691590+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12832","created_at":"2026-07-05T01:07:53.691590+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUUBRITOVMIG","created_at":"2026-07-05T01:07:53.691590+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUUBRITOVMIGHN4S","created_at":"2026-07-05T01:07:53.691590+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUUBRITO","created_at":"2026-07-05T01:07:53.691590+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22778","citing_title":"HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24937","citing_title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","ref_index":299,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08151","citing_title":"Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24764","citing_title":"Spectral Retrieval: Multi-Scale Sinc Convolution over Token Embeddings for Localized Retrieval in LLM Multi-Agent Systems","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28365","citing_title":"CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24938","citing_title":"Your Embedding Model is SMARTer Than You Think","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00994","citing_title":"Should We Still Pretrain Encoders with Masked Language Modeling?","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2401.18059","citing_title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02486","citing_title":"VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25142","citing_title":"UnIte: Uncertainty-based Iterative Document Sampling for Domain Adaptation in Information Retrieval","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EUUBRITOVMIGHN4SOZKHCAEWIQ","json":"https://pith.science/pith/EUUBRITOVMIGHN4SOZKHCAEWIQ.json","graph_json":"https://pith.science/api/pith-number/EUUBRITOVMIGHN4SOZKHCAEWIQ/graph.json","events_json":"https://pith.science/api/pith-number/EUUBRITOVMIGHN4SOZKHCAEWIQ/events.json","paper":"https://pith.science/paper/EUUBRITO"},"agent_actions":{"view_html":"https://pith.science/pith/EUUBRITOVMIGHN4SOZKHCAEWIQ","download_json":"https://pith.science/pith/EUUBRITOVMIGHN4SOZKHCAEWIQ.json","view_paper":"https://pith.science/paper/EUUBRITO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.12832&json=true","fetch_graph":"https://pith.science/api/pith-number/EUUBRITOVMIGHN4SOZKHCAEWIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/EUUBRITOVMIGHN4SOZKHCAEWIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUUBRITOVMIGHN4SOZKHCAEWIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUUBRITOVMIGHN4SOZKHCAEWIQ/action/storage_attestation","attest_author":"https://pith.science/pith/EUUBRITOVMIGHN4SOZKHCAEWIQ/action/author_attestation","sign_citation":"https://pith.science/pith/EUUBRITOVMIGHN4SOZKHCAEWIQ/action/citation_signature","submit_replication":"https://pith.science/pith/EUUBRITOVMIGHN4SOZKHCAEWIQ/action/replication_record"}},"created_at":"2026-07-05T01:07:53.691590+00:00","updated_at":"2026-07-05T01:07:53.691590+00:00"}