{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TF5P5GWD4OECYVWCIA3MSQVKRG","short_pith_number":"pith:TF5P5GWD","schema_version":"1.0","canonical_sha256":"997afe9ac3e3882c56c24036c942aa89a48ad9b3256f784506d58d07e3b97797","source":{"kind":"arxiv","id":"2402.07440","version":3},"attestation_state":"computed","paper":{"title":"Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Christopher R\\'e, Daniel Y. Fu, Jon Saad-Falcon, Neel Guha, Simran Arora","submitted_at":"2024-02-12T06:43:52Z","abstract_excerpt":"Retrieval pipelines-an integral component of many machine learning systems-perform poorly in domains where documents are long (e.g., 10K tokens or more) and where identifying the relevant document requires synthesizing information across the entire text. Developing long-context retrieval encoders suitable for these domains raises three challenges: (1) how to evaluate long-context retrieval performance, (2) how to pretrain a base language model to represent both short contexts (corresponding to queries) and long contexts (corresponding to documents), and (3) how to fine-tune this model for retr"},"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":"2402.07440","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-02-12T06:43:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"907c951a243a041be8e9f7a876535b887b8eb2ee170306bd1dec03ffe4ac7e54","abstract_canon_sha256":"6152120875910acd5fe3ac0f3f6115d3c6abeb727de000ab01e10e83d397ff33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:38.655981Z","signature_b64":"7Ffkk8VpEmWio8ZV49a3XbTk3YPfWesoooEjbnHslXhIfDzxFsvWEOeU0C3wmvRWZuPPIlnudlkNzrKA4SdSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"997afe9ac3e3882c56c24036c942aa89a48ad9b3256f784506d58d07e3b97797","last_reissued_at":"2026-07-05T09:36:38.655486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:38.655486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Christopher R\\'e, Daniel Y. Fu, Jon Saad-Falcon, Neel Guha, Simran Arora","submitted_at":"2024-02-12T06:43:52Z","abstract_excerpt":"Retrieval pipelines-an integral component of many machine learning systems-perform poorly in domains where documents are long (e.g., 10K tokens or more) and where identifying the relevant document requires synthesizing information across the entire text. Developing long-context retrieval encoders suitable for these domains raises three challenges: (1) how to evaluate long-context retrieval performance, (2) how to pretrain a base language model to represent both short contexts (corresponding to queries) and long contexts (corresponding to documents), and (3) how to fine-tune this model for retr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07440","kind":"arxiv","version":3},"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/2402.07440/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":"2402.07440","created_at":"2026-07-05T09:36:38.655549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07440v3","created_at":"2026-07-05T09:36:38.655549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07440","created_at":"2026-07-05T09:36:38.655549+00:00"},{"alias_kind":"pith_short_12","alias_value":"TF5P5GWD4OEC","created_at":"2026-07-05T09:36:38.655549+00:00"},{"alias_kind":"pith_short_16","alias_value":"TF5P5GWD4OECYVWC","created_at":"2026-07-05T09:36:38.655549+00:00"},{"alias_kind":"pith_short_8","alias_value":"TF5P5GWD","created_at":"2026-07-05T09:36:38.655549+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06906","citing_title":"EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TF5P5GWD4OECYVWCIA3MSQVKRG","json":"https://pith.science/pith/TF5P5GWD4OECYVWCIA3MSQVKRG.json","graph_json":"https://pith.science/api/pith-number/TF5P5GWD4OECYVWCIA3MSQVKRG/graph.json","events_json":"https://pith.science/api/pith-number/TF5P5GWD4OECYVWCIA3MSQVKRG/events.json","paper":"https://pith.science/paper/TF5P5GWD"},"agent_actions":{"view_html":"https://pith.science/pith/TF5P5GWD4OECYVWCIA3MSQVKRG","download_json":"https://pith.science/pith/TF5P5GWD4OECYVWCIA3MSQVKRG.json","view_paper":"https://pith.science/paper/TF5P5GWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07440&json=true","fetch_graph":"https://pith.science/api/pith-number/TF5P5GWD4OECYVWCIA3MSQVKRG/graph.json","fetch_events":"https://pith.science/api/pith-number/TF5P5GWD4OECYVWCIA3MSQVKRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TF5P5GWD4OECYVWCIA3MSQVKRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TF5P5GWD4OECYVWCIA3MSQVKRG/action/storage_attestation","attest_author":"https://pith.science/pith/TF5P5GWD4OECYVWCIA3MSQVKRG/action/author_attestation","sign_citation":"https://pith.science/pith/TF5P5GWD4OECYVWCIA3MSQVKRG/action/citation_signature","submit_replication":"https://pith.science/pith/TF5P5GWD4OECYVWCIA3MSQVKRG/action/replication_record"}},"created_at":"2026-07-05T09:36:38.655549+00:00","updated_at":"2026-07-05T09:36:38.655549+00:00"}