{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FWKXAADEB5Y56LDP7H64FPIJ7F","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":"c0b759bf37a02feec4042b36b805d3e110578a8bec9a03ee8965cea20bccdef6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-06T09:29:19Z","title_canon_sha256":"2c9088e835ff6978581019883bca0afc106b0cee10145ffcd11f868bbcc9b9c5"},"schema_version":"1.0","source":{"id":"2410.04422","kind":"arxiv","version":9}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04422","created_at":"2026-07-05T11:59:07Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04422v9","created_at":"2026-07-05T11:59:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04422","created_at":"2026-07-05T11:59:07Z"},{"alias_kind":"pith_short_12","alias_value":"FWKXAADEB5Y5","created_at":"2026-07-05T11:59:07Z"},{"alias_kind":"pith_short_16","alias_value":"FWKXAADEB5Y56LDP","created_at":"2026-07-05T11:59:07Z"},{"alias_kind":"pith_short_8","alias_value":"FWKXAADE","created_at":"2026-07-05T11:59:07Z"}],"graph_snapshots":[{"event_id":"sha256:9034cc4f60a312156496976d22844563681afb562662fe581e7fc9bc8c6dab79","target":"graph","created_at":"2026-07-05T11:59:07Z","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/2410.04422/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ji Pei, Ran Chen, Weifeng Liu, Wei Wang, Yijiong Yu, Yongfeng Huang, Zhixiao Qi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-06T09:29:19Z","title":"Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Steps"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04422","kind":"arxiv","version":9},"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":"sha256:68d2295484c6fa66d71c20c1b68563226909dc0b69479742d8ce69463da0168a","target":"record","created_at":"2026-07-05T11:59:07Z","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":"c0b759bf37a02feec4042b36b805d3e110578a8bec9a03ee8965cea20bccdef6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-06T09:29:19Z","title_canon_sha256":"2c9088e835ff6978581019883bca0afc106b0cee10145ffcd11f868bbcc9b9c5"},"schema_version":"1.0","source":{"id":"2410.04422","kind":"arxiv","version":9}},"canonical_sha256":"2d957000640f71df2c6ff9fdc2bd09f963f0d06ed2ef111eb85e1c340e085f29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d957000640f71df2c6ff9fdc2bd09f963f0d06ed2ef111eb85e1c340e085f29","first_computed_at":"2026-07-05T11:59:07.764362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:07.764362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J9LdRkHHFVi/HA/T1aMilf2g3UwDsiGnqvkcfi4xePFxITRoPiutLFuRJZEqQGqW5hgtJ2XZ06IY4CDM0ypsBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:07.764802Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04422","source_kind":"arxiv","source_version":9}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68d2295484c6fa66d71c20c1b68563226909dc0b69479742d8ce69463da0168a","sha256:9034cc4f60a312156496976d22844563681afb562662fe581e7fc9bc8c6dab79"],"state_sha256":"ef47adc5c2a68b5d94babc09d02db7b33ab022c984675ee3954a8c9dbf0fbad0"}