{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QE3U4QFC7QFQCNBLSRSN7YEHWG","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":"0a5db8744e22c7c02561fdb4b7ba84003c2a89b26b696e67629f27469da97309","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T23:38:25Z","title_canon_sha256":"60acb3adda6ca3503a557487293b2f10f917cca0696c2a6831cadbb0ae4c8b44"},"schema_version":"1.0","source":{"id":"2607.01538","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01538","created_at":"2026-07-03T00:17:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01538v1","created_at":"2026-07-03T00:17:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01538","created_at":"2026-07-03T00:17:03Z"},{"alias_kind":"pith_short_12","alias_value":"QE3U4QFC7QFQ","created_at":"2026-07-03T00:17:03Z"},{"alias_kind":"pith_short_16","alias_value":"QE3U4QFC7QFQCNBL","created_at":"2026-07-03T00:17:03Z"},{"alias_kind":"pith_short_8","alias_value":"QE3U4QFC","created_at":"2026-07-03T00:17:03Z"}],"graph_snapshots":[{"event_id":"sha256:44af276de42c60a79ee5da2096c3955b5281ff829a006bc6a5e5c7cec267bc01","target":"graph","created_at":"2026-07-03T00:17:03Z","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/2607.01538/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models (LMs) raise an intriguing alternative to vector-based retrieval: conditioning on an in-context corpus and directly generating a relevant answer. However, prior work has largely focused on proprietary systems or the smaller-scale reranking task, leaving corpus-scale in-context retrieval largely unexplored. In this work, we present the first systematic study of in-context retrieval on two scales practical retrievers demand: million-token corpora and length-generalization far beyond training-time sizes. We first introduce BlockSearch, a 0.6B LM retriever whose architectural and tr","authors_text":"Nilesh Gupta, Prasann Singhal, Sewon Min, Siddharth Gollapudi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T23:38:25Z","title":"Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01538","kind":"arxiv","version":1},"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:ac4a504c3aea44dde3ac81618a69bc68da37116c2ae024435b2ce25bd57bc630","target":"record","created_at":"2026-07-03T00:17:03Z","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":"0a5db8744e22c7c02561fdb4b7ba84003c2a89b26b696e67629f27469da97309","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T23:38:25Z","title_canon_sha256":"60acb3adda6ca3503a557487293b2f10f917cca0696c2a6831cadbb0ae4c8b44"},"schema_version":"1.0","source":{"id":"2607.01538","kind":"arxiv","version":1}},"canonical_sha256":"81374e40a2fc0b01342b9464dfe087b1a324b2e28ff1adfec8bf42f5288151f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81374e40a2fc0b01342b9464dfe087b1a324b2e28ff1adfec8bf42f5288151f2","first_computed_at":"2026-07-03T00:17:03.475962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T00:17:03.475962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VO39y0yYhuAken20A/QoNPED2AmfEjgkbqJuLIyz2gllTwgzd0YuoIobmwHlke52LK31SkfP0EX1fwdopsyyBA==","signature_status":"signed_v1","signed_at":"2026-07-03T00:17:03.476429Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01538","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac4a504c3aea44dde3ac81618a69bc68da37116c2ae024435b2ce25bd57bc630","sha256:44af276de42c60a79ee5da2096c3955b5281ff829a006bc6a5e5c7cec267bc01"],"state_sha256":"12abe30a594e08106ecea6466a3cab50e167440e72a68e0791f0f9638228ee8b"}