{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W6RURQOXPLLP7ENMNQGBJ262GH","short_pith_number":"pith:W6RURQOX","schema_version":"1.0","canonical_sha256":"b7a348c1d77ad6ff91ac6c0c14ebda31e54a31b24ad02f138f801c1b6d54750c","source":{"kind":"arxiv","id":"2407.00402","version":4},"attestation_state":"computed","paper":{"title":"Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alon Jacovi, Aviv Slobodkin, Aviya Maimon, Ido Dagan, Omer Goldman, Reut Tsarfaty","submitted_at":"2024-06-29T11:09:47Z","abstract_excerpt":"Improvements in language models' capabilities have pushed their applications towards longer contexts, making long-context evaluation and development an active research area. However, many disparate use-cases are grouped together under the umbrella term of \"long-context\", defined simply by the total length of the model's input, including - for example - Needle-in-a-Haystack tasks, book summarization, and information aggregation. Given their varied difficulty, in this position paper we argue that conflating different tasks by their context length is unproductive. As a community, we require a mor"},"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":"2407.00402","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T11:09:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e127c1784f44b1618ee8a6f2bde804640d7389e795986e4ec1bb933048d99b1e","abstract_canon_sha256":"61f0d46ed1fee382b496b6c352bd574409316a75bfa3d74667c57d3fe92527cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:15.936382Z","signature_b64":"mrGdrSprPsNwr8BnDxvFQqn5wrfvgrYXZ6kyoAHdlzTn/4Uzqd1cPh7Wm01EkAbzCDR6FR35+DP3nmxAZp1nAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7a348c1d77ad6ff91ac6c0c14ebda31e54a31b24ad02f138f801c1b6d54750c","last_reissued_at":"2026-07-05T11:32:15.935859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:15.935859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alon Jacovi, Aviv Slobodkin, Aviya Maimon, Ido Dagan, Omer Goldman, Reut Tsarfaty","submitted_at":"2024-06-29T11:09:47Z","abstract_excerpt":"Improvements in language models' capabilities have pushed their applications towards longer contexts, making long-context evaluation and development an active research area. However, many disparate use-cases are grouped together under the umbrella term of \"long-context\", defined simply by the total length of the model's input, including - for example - Needle-in-a-Haystack tasks, book summarization, and information aggregation. Given their varied difficulty, in this position paper we argue that conflating different tasks by their context length is unproductive. As a community, we require a mor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00402","kind":"arxiv","version":4},"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/2407.00402/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":"2407.00402","created_at":"2026-07-05T11:32:15.935912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00402v4","created_at":"2026-07-05T11:32:15.935912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00402","created_at":"2026-07-05T11:32:15.935912+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6RURQOXPLLP","created_at":"2026-07-05T11:32:15.935912+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6RURQOXPLLP7ENM","created_at":"2026-07-05T11:32:15.935912+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6RURQOX","created_at":"2026-07-05T11:32:15.935912+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":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6RURQOXPLLP7ENMNQGBJ262GH","json":"https://pith.science/pith/W6RURQOXPLLP7ENMNQGBJ262GH.json","graph_json":"https://pith.science/api/pith-number/W6RURQOXPLLP7ENMNQGBJ262GH/graph.json","events_json":"https://pith.science/api/pith-number/W6RURQOXPLLP7ENMNQGBJ262GH/events.json","paper":"https://pith.science/paper/W6RURQOX"},"agent_actions":{"view_html":"https://pith.science/pith/W6RURQOXPLLP7ENMNQGBJ262GH","download_json":"https://pith.science/pith/W6RURQOXPLLP7ENMNQGBJ262GH.json","view_paper":"https://pith.science/paper/W6RURQOX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00402&json=true","fetch_graph":"https://pith.science/api/pith-number/W6RURQOXPLLP7ENMNQGBJ262GH/graph.json","fetch_events":"https://pith.science/api/pith-number/W6RURQOXPLLP7ENMNQGBJ262GH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6RURQOXPLLP7ENMNQGBJ262GH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6RURQOXPLLP7ENMNQGBJ262GH/action/storage_attestation","attest_author":"https://pith.science/pith/W6RURQOXPLLP7ENMNQGBJ262GH/action/author_attestation","sign_citation":"https://pith.science/pith/W6RURQOXPLLP7ENMNQGBJ262GH/action/citation_signature","submit_replication":"https://pith.science/pith/W6RURQOXPLLP7ENMNQGBJ262GH/action/replication_record"}},"created_at":"2026-07-05T11:32:15.935912+00:00","updated_at":"2026-07-05T11:32:15.935912+00:00"}