{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GL7A3YIBZI2J6BS5ZIFBVURQUA","short_pith_number":"pith:GL7A3YIB","schema_version":"1.0","canonical_sha256":"32fe0de101ca349f065dca0a1ad230a0281f45337b6088cee808b967a1ca8a96","source":{"kind":"arxiv","id":"2607.03660","version":1},"attestation_state":"computed","paper":{"title":"Sequential Correlations Change In-Context Learning: Effective Context Length and Architectural Mismatch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Cengiz Pehlevan, Jacob Zavatone-Veth, Mary Letey, Yue M. Lu","submitted_at":"2026-07-04T01:47:29Z","abstract_excerpt":"Modern sequence models have a striking capacity for in-context learning (ICL); they can perform new tasks based only on examples given in the prompt. Understanding how this ability emerges requires theory that captures important properties of natural data. Linear regression has served as a useful sandbox for ICL theory, but existing work has largely focused on prompts with independent examples. In this work, we extend this setting to sequentially correlated data, a basic feature of real sequences. We present a solvable model based on linear attention and test our predictions on realistic trans"},"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":"2607.03660","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-07-04T01:47:29Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"1562bceab458c3e5feb15eea84c979839794085aa5115849d7205049a292807e","abstract_canon_sha256":"f9ac4eac494f6b50df77ed0fe79f12baf5b1a62ae0529c6c7a7b404151bda8f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:17:59.893324Z","signature_b64":"SnpG9mTJrfusGHWuc7/pfnum1eHfuoPY3MLmtq2ropCeA1vun2uoPacb/NdFwP3sn55Idxf1p5vRlSdgM8zZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32fe0de101ca349f065dca0a1ad230a0281f45337b6088cee808b967a1ca8a96","last_reissued_at":"2026-07-07T02:17:59.892670Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:17:59.892670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequential Correlations Change In-Context Learning: Effective Context Length and Architectural Mismatch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Cengiz Pehlevan, Jacob Zavatone-Veth, Mary Letey, Yue M. Lu","submitted_at":"2026-07-04T01:47:29Z","abstract_excerpt":"Modern sequence models have a striking capacity for in-context learning (ICL); they can perform new tasks based only on examples given in the prompt. Understanding how this ability emerges requires theory that captures important properties of natural data. Linear regression has served as a useful sandbox for ICL theory, but existing work has largely focused on prompts with independent examples. In this work, we extend this setting to sequentially correlated data, a basic feature of real sequences. We present a solvable model based on linear attention and test our predictions on realistic trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03660","kind":"arxiv","version":1},"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/2607.03660/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":"2607.03660","created_at":"2026-07-07T02:17:59.892767+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.03660v1","created_at":"2026-07-07T02:17:59.892767+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03660","created_at":"2026-07-07T02:17:59.892767+00:00"},{"alias_kind":"pith_short_12","alias_value":"GL7A3YIBZI2J","created_at":"2026-07-07T02:17:59.892767+00:00"},{"alias_kind":"pith_short_16","alias_value":"GL7A3YIBZI2J6BS5","created_at":"2026-07-07T02:17:59.892767+00:00"},{"alias_kind":"pith_short_8","alias_value":"GL7A3YIB","created_at":"2026-07-07T02:17:59.892767+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GL7A3YIBZI2J6BS5ZIFBVURQUA","json":"https://pith.science/pith/GL7A3YIBZI2J6BS5ZIFBVURQUA.json","graph_json":"https://pith.science/api/pith-number/GL7A3YIBZI2J6BS5ZIFBVURQUA/graph.json","events_json":"https://pith.science/api/pith-number/GL7A3YIBZI2J6BS5ZIFBVURQUA/events.json","paper":"https://pith.science/paper/GL7A3YIB"},"agent_actions":{"view_html":"https://pith.science/pith/GL7A3YIBZI2J6BS5ZIFBVURQUA","download_json":"https://pith.science/pith/GL7A3YIBZI2J6BS5ZIFBVURQUA.json","view_paper":"https://pith.science/paper/GL7A3YIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.03660&json=true","fetch_graph":"https://pith.science/api/pith-number/GL7A3YIBZI2J6BS5ZIFBVURQUA/graph.json","fetch_events":"https://pith.science/api/pith-number/GL7A3YIBZI2J6BS5ZIFBVURQUA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GL7A3YIBZI2J6BS5ZIFBVURQUA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GL7A3YIBZI2J6BS5ZIFBVURQUA/action/storage_attestation","attest_author":"https://pith.science/pith/GL7A3YIBZI2J6BS5ZIFBVURQUA/action/author_attestation","sign_citation":"https://pith.science/pith/GL7A3YIBZI2J6BS5ZIFBVURQUA/action/citation_signature","submit_replication":"https://pith.science/pith/GL7A3YIBZI2J6BS5ZIFBVURQUA/action/replication_record"}},"created_at":"2026-07-07T02:17:59.892767+00:00","updated_at":"2026-07-07T02:17:59.892767+00:00"}