{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FWKXAADEB5Y56LDP7H64FPIJ7F","short_pith_number":"pith:FWKXAADE","schema_version":"1.0","canonical_sha256":"2d957000640f71df2c6ff9fdc2bd09f963f0d06ed2ef111eb85e1c340e085f29","source":{"kind":"arxiv","id":"2410.04422","version":9},"attestation_state":"computed","paper":{"title":"Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Steps","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ji Pei, Ran Chen, Weifeng Liu, Wei Wang, Yijiong Yu, Yongfeng Huang, Zhixiao Qi","submitted_at":"2024-10-06T09:29:19Z","abstract_excerpt":"Long-context language models (LCLMs), characterized by their extensive context window, are becoming popular. However, despite the fact that they are nearly perfect at standard long-context retrieval tasks, our evaluations demonstrate they fail in some basic cases. Later, we find they can be well addressed with a sufficient number of reasoning steps, guided by specific CoT prompts. This result emphasizes the potential necessity of solving specific long-context tasks using long-CoT methods, while previous long-context benchmarks always ignore the necessity of long reasoning for long-context task"},"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":"2410.04422","kind":"arxiv","version":9},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-06T09:29:19Z","cross_cats_sorted":[],"title_canon_sha256":"2c9088e835ff6978581019883bca0afc106b0cee10145ffcd11f868bbcc9b9c5","abstract_canon_sha256":"c0b759bf37a02feec4042b36b805d3e110578a8bec9a03ee8965cea20bccdef6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:07.764802Z","signature_b64":"J9LdRkHHFVi/HA/T1aMilf2g3UwDsiGnqvkcfi4xePFxITRoPiutLFuRJZEqQGqW5hgtJ2XZ06IY4CDM0ypsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d957000640f71df2c6ff9fdc2bd09f963f0d06ed2ef111eb85e1c340e085f29","last_reissued_at":"2026-07-05T11:59:07.764362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:07.764362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Steps","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ji Pei, Ran Chen, Weifeng Liu, Wei Wang, Yijiong Yu, Yongfeng Huang, Zhixiao Qi","submitted_at":"2024-10-06T09:29:19Z","abstract_excerpt":"Long-context language models (LCLMs), characterized by their extensive context window, are becoming popular. However, despite the fact that they are nearly perfect at standard long-context retrieval tasks, our evaluations demonstrate they fail in some basic cases. Later, we find they can be well addressed with a sufficient number of reasoning steps, guided by specific CoT prompts. This result emphasizes the potential necessity of solving specific long-context tasks using long-CoT methods, while previous long-context benchmarks always ignore the necessity of long reasoning for long-context task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04422","kind":"arxiv","version":9},"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/2410.04422/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":"2410.04422","created_at":"2026-07-05T11:59:07.764414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04422v9","created_at":"2026-07-05T11:59:07.764414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04422","created_at":"2026-07-05T11:59:07.764414+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWKXAADEB5Y5","created_at":"2026-07-05T11:59:07.764414+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWKXAADEB5Y56LDP","created_at":"2026-07-05T11:59:07.764414+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWKXAADE","created_at":"2026-07-05T11:59:07.764414+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/FWKXAADEB5Y56LDP7H64FPIJ7F","json":"https://pith.science/pith/FWKXAADEB5Y56LDP7H64FPIJ7F.json","graph_json":"https://pith.science/api/pith-number/FWKXAADEB5Y56LDP7H64FPIJ7F/graph.json","events_json":"https://pith.science/api/pith-number/FWKXAADEB5Y56LDP7H64FPIJ7F/events.json","paper":"https://pith.science/paper/FWKXAADE"},"agent_actions":{"view_html":"https://pith.science/pith/FWKXAADEB5Y56LDP7H64FPIJ7F","download_json":"https://pith.science/pith/FWKXAADEB5Y56LDP7H64FPIJ7F.json","view_paper":"https://pith.science/paper/FWKXAADE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04422&json=true","fetch_graph":"https://pith.science/api/pith-number/FWKXAADEB5Y56LDP7H64FPIJ7F/graph.json","fetch_events":"https://pith.science/api/pith-number/FWKXAADEB5Y56LDP7H64FPIJ7F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWKXAADEB5Y56LDP7H64FPIJ7F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWKXAADEB5Y56LDP7H64FPIJ7F/action/storage_attestation","attest_author":"https://pith.science/pith/FWKXAADEB5Y56LDP7H64FPIJ7F/action/author_attestation","sign_citation":"https://pith.science/pith/FWKXAADEB5Y56LDP7H64FPIJ7F/action/citation_signature","submit_replication":"https://pith.science/pith/FWKXAADEB5Y56LDP7H64FPIJ7F/action/replication_record"}},"created_at":"2026-07-05T11:59:07.764414+00:00","updated_at":"2026-07-05T11:59:07.764414+00:00"}