{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RWQ27DDFWH5QKBP6EQDH4CELTW","short_pith_number":"pith:RWQ27DDF","schema_version":"1.0","canonical_sha256":"8da1af8c65b1fb0505fe24067e088b9dbe76fc4a91f745334d114e4bd5debe7a","source":{"kind":"arxiv","id":"2507.22411","version":3},"attestation_state":"computed","paper":{"title":"NeedleChain: Measuring Intact Context Comprehension Capability of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Heuiseok Lim, Hyeonseok Moon","submitted_at":"2025-07-30T06:29:50Z","abstract_excerpt":"Recent reports suggest that LLMs can handle increasingly long contexts. However, many existing benchmarks for context understanding embed substantial query-irrelevant content, which shifts evaluation toward retrieving relevant snippets rather than fully integrating all provided information. Under this setting, we view that current benchmarks can overestimate true context-understanding ability of LLMs. In particular, we demonstrate that when the context consists entirely of query-relevant text, even advanced models such as GPT-4o fail to reliably integrate inputs as short as 200 tokens. To eval"},"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":"2507.22411","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-30T06:29:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7589f9f6ee5d94708ee02fb30af65ea7313475679f498126eebe3a4be3a651d9","abstract_canon_sha256":"879fd55eac5c8785c0f53272e3c083a701510a567b38f26041436f7c5f084e4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:12:32.482498Z","signature_b64":"ZVhopt9H7z2Npulm1c+tUf8KiIhNF9Dz9qx5+40yJhSV5hXrEANA5n1IKf00c/RuJjCz2KzKoAsdllwuaVtEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8da1af8c65b1fb0505fe24067e088b9dbe76fc4a91f745334d114e4bd5debe7a","last_reissued_at":"2026-06-23T02:12:32.482114Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:12:32.482114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeedleChain: Measuring Intact Context Comprehension Capability of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Heuiseok Lim, Hyeonseok Moon","submitted_at":"2025-07-30T06:29:50Z","abstract_excerpt":"Recent reports suggest that LLMs can handle increasingly long contexts. However, many existing benchmarks for context understanding embed substantial query-irrelevant content, which shifts evaluation toward retrieving relevant snippets rather than fully integrating all provided information. Under this setting, we view that current benchmarks can overestimate true context-understanding ability of LLMs. In particular, we demonstrate that when the context consists entirely of query-relevant text, even advanced models such as GPT-4o fail to reliably integrate inputs as short as 200 tokens. To eval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22411","kind":"arxiv","version":3},"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/2507.22411/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":"2507.22411","created_at":"2026-06-23T02:12:32.482165+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22411v3","created_at":"2026-06-23T02:12:32.482165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22411","created_at":"2026-06-23T02:12:32.482165+00:00"},{"alias_kind":"pith_short_12","alias_value":"RWQ27DDFWH5Q","created_at":"2026-06-23T02:12:32.482165+00:00"},{"alias_kind":"pith_short_16","alias_value":"RWQ27DDFWH5QKBP6","created_at":"2026-06-23T02:12:32.482165+00:00"},{"alias_kind":"pith_short_8","alias_value":"RWQ27DDF","created_at":"2026-06-23T02:12:32.482165+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/RWQ27DDFWH5QKBP6EQDH4CELTW","json":"https://pith.science/pith/RWQ27DDFWH5QKBP6EQDH4CELTW.json","graph_json":"https://pith.science/api/pith-number/RWQ27DDFWH5QKBP6EQDH4CELTW/graph.json","events_json":"https://pith.science/api/pith-number/RWQ27DDFWH5QKBP6EQDH4CELTW/events.json","paper":"https://pith.science/paper/RWQ27DDF"},"agent_actions":{"view_html":"https://pith.science/pith/RWQ27DDFWH5QKBP6EQDH4CELTW","download_json":"https://pith.science/pith/RWQ27DDFWH5QKBP6EQDH4CELTW.json","view_paper":"https://pith.science/paper/RWQ27DDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22411&json=true","fetch_graph":"https://pith.science/api/pith-number/RWQ27DDFWH5QKBP6EQDH4CELTW/graph.json","fetch_events":"https://pith.science/api/pith-number/RWQ27DDFWH5QKBP6EQDH4CELTW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RWQ27DDFWH5QKBP6EQDH4CELTW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RWQ27DDFWH5QKBP6EQDH4CELTW/action/storage_attestation","attest_author":"https://pith.science/pith/RWQ27DDFWH5QKBP6EQDH4CELTW/action/author_attestation","sign_citation":"https://pith.science/pith/RWQ27DDFWH5QKBP6EQDH4CELTW/action/citation_signature","submit_replication":"https://pith.science/pith/RWQ27DDFWH5QKBP6EQDH4CELTW/action/replication_record"}},"created_at":"2026-06-23T02:12:32.482165+00:00","updated_at":"2026-06-23T02:12:32.482165+00:00"}