{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TF5P5GWD4OECYVWCIA3MSQVKRG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6152120875910acd5fe3ac0f3f6115d3c6abeb727de000ab01e10e83d397ff33","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-02-12T06:43:52Z","title_canon_sha256":"907c951a243a041be8e9f7a876535b887b8eb2ee170306bd1dec03ffe4ac7e54"},"schema_version":"1.0","source":{"id":"2402.07440","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07440","created_at":"2026-07-05T09:36:38Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07440v3","created_at":"2026-07-05T09:36:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07440","created_at":"2026-07-05T09:36:38Z"},{"alias_kind":"pith_short_12","alias_value":"TF5P5GWD4OEC","created_at":"2026-07-05T09:36:38Z"},{"alias_kind":"pith_short_16","alias_value":"TF5P5GWD4OECYVWC","created_at":"2026-07-05T09:36:38Z"},{"alias_kind":"pith_short_8","alias_value":"TF5P5GWD","created_at":"2026-07-05T09:36:38Z"}],"graph_snapshots":[{"event_id":"sha256:943322aeb63e91c5b52f56857f2ff5c9056fa7ea666042372d48aa77760799d4","target":"graph","created_at":"2026-07-05T09:36:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.07440/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Christopher R\\'e, Daniel Y. Fu, Jon Saad-Falcon, Neel Guha, Simran Arora","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-02-12T06:43:52Z","title":"Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07440","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e3fa36593db7b574cbb4b167c92fdbbfc8f2f3606afe9d510255417aef000026","target":"record","created_at":"2026-07-05T09:36:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6152120875910acd5fe3ac0f3f6115d3c6abeb727de000ab01e10e83d397ff33","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-02-12T06:43:52Z","title_canon_sha256":"907c951a243a041be8e9f7a876535b887b8eb2ee170306bd1dec03ffe4ac7e54"},"schema_version":"1.0","source":{"id":"2402.07440","kind":"arxiv","version":3}},"canonical_sha256":"997afe9ac3e3882c56c24036c942aa89a48ad9b3256f784506d58d07e3b97797","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"997afe9ac3e3882c56c24036c942aa89a48ad9b3256f784506d58d07e3b97797","first_computed_at":"2026-07-05T09:36:38.655486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:38.655486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Ffkk8VpEmWio8ZV49a3XbTk3YPfWesoooEjbnHslXhIfDzxFsvWEOeU0C3wmvRWZuPPIlnudlkNzrKA4SdSDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:38.655981Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07440","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3fa36593db7b574cbb4b167c92fdbbfc8f2f3606afe9d510255417aef000026","sha256:943322aeb63e91c5b52f56857f2ff5c9056fa7ea666042372d48aa77760799d4"],"state_sha256":"d96ea0340cdee94be3abdc352c9c961230804257724ec0093cd0378ef43809ef"}