{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OGHMFRCRRGCPTW723O7SACREW5","short_pith_number":"pith:OGHMFRCR","schema_version":"1.0","canonical_sha256":"718ec2c4518984f9dbfadbbf200a24b76c4b084dd3a9c189837b582c9ed492e5","source":{"kind":"arxiv","id":"2407.16695","version":2},"attestation_state":"computed","paper":{"title":"Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Qinyuan Ye, Xiang Ren, Xiaoyue Xu","submitted_at":"2024-07-23T17:57:41Z","abstract_excerpt":"We introduce Lifelong ICL, a problem setting that challenges long-context language models (LMs) to learn a sequence of language tasks through in-context learning (ICL). We further introduce Task Haystack, an evaluation suite dedicated to assessing and diagnosing how long-context LMs utilizes contexts in Lifelong ICL. When given a task instruction and test inputs, long-context LMs are expected to leverage the relevant demonstrations in the Lifelong ICL prompt, avoid distraction and interference from other tasks, and achieve test accuracies that are not significantly worse than those of the Sing"},"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":"2407.16695","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T17:57:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"268ddba84e30d586c330d29f33c79611182d310a81730830a7e2615c69eaae58","abstract_canon_sha256":"e8d8262fe07559fbe60ccc767ee539adda4b24f2d75951f0710df1e23976845d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:31.942120Z","signature_b64":"QkHPw0juZLQ+vNba+kNPcj7YDyfMs7PrdGdTkaxGQLNJt/DZn528fJJUCCOLONNuN2piDVhudPFnWO1dfWdcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"718ec2c4518984f9dbfadbbf200a24b76c4b084dd3a9c189837b582c9ed492e5","last_reissued_at":"2026-07-05T09:43:31.941620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:31.941620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Qinyuan Ye, Xiang Ren, Xiaoyue Xu","submitted_at":"2024-07-23T17:57:41Z","abstract_excerpt":"We introduce Lifelong ICL, a problem setting that challenges long-context language models (LMs) to learn a sequence of language tasks through in-context learning (ICL). We further introduce Task Haystack, an evaluation suite dedicated to assessing and diagnosing how long-context LMs utilizes contexts in Lifelong ICL. When given a task instruction and test inputs, long-context LMs are expected to leverage the relevant demonstrations in the Lifelong ICL prompt, avoid distraction and interference from other tasks, and achieve test accuracies that are not significantly worse than those of the Sing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16695","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/2407.16695/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":"2407.16695","created_at":"2026-07-05T09:43:31.941687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16695v2","created_at":"2026-07-05T09:43:31.941687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16695","created_at":"2026-07-05T09:43:31.941687+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGHMFRCRRGCP","created_at":"2026-07-05T09:43:31.941687+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGHMFRCRRGCPTW72","created_at":"2026-07-05T09:43:31.941687+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGHMFRCR","created_at":"2026-07-05T09:43:31.941687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.06654","citing_title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OGHMFRCRRGCPTW723O7SACREW5","json":"https://pith.science/pith/OGHMFRCRRGCPTW723O7SACREW5.json","graph_json":"https://pith.science/api/pith-number/OGHMFRCRRGCPTW723O7SACREW5/graph.json","events_json":"https://pith.science/api/pith-number/OGHMFRCRRGCPTW723O7SACREW5/events.json","paper":"https://pith.science/paper/OGHMFRCR"},"agent_actions":{"view_html":"https://pith.science/pith/OGHMFRCRRGCPTW723O7SACREW5","download_json":"https://pith.science/pith/OGHMFRCRRGCPTW723O7SACREW5.json","view_paper":"https://pith.science/paper/OGHMFRCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16695&json=true","fetch_graph":"https://pith.science/api/pith-number/OGHMFRCRRGCPTW723O7SACREW5/graph.json","fetch_events":"https://pith.science/api/pith-number/OGHMFRCRRGCPTW723O7SACREW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGHMFRCRRGCPTW723O7SACREW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGHMFRCRRGCPTW723O7SACREW5/action/storage_attestation","attest_author":"https://pith.science/pith/OGHMFRCRRGCPTW723O7SACREW5/action/author_attestation","sign_citation":"https://pith.science/pith/OGHMFRCRRGCPTW723O7SACREW5/action/citation_signature","submit_replication":"https://pith.science/pith/OGHMFRCRRGCPTW723O7SACREW5/action/replication_record"}},"created_at":"2026-07-05T09:43:31.941687+00:00","updated_at":"2026-07-05T09:43:31.941687+00:00"}