{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ORFBKY6PYBGTMS4BHRUQPBWEU7","short_pith_number":"pith:ORFBKY6P","schema_version":"1.0","canonical_sha256":"744a1563cfc04d364b813c690786c4a7e9635c0847a8e5f2b0fd7ef5a616cc58","source":{"kind":"arxiv","id":"2409.00997","version":2},"attestation_state":"computed","paper":{"title":"DataSculpt: Crafting Data Landscapes for Long-Context LLMs through Multi-Objective Partitioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Cui, Da Pan, Guosheng Dong, Keer Lu, Keshi Zhao, Shusen Zhang, Weipeng Chen, Wentao Zhang, Xiaonan Nie, Zenan Zhou, Zheng Liang","submitted_at":"2024-09-02T07:23:13Z","abstract_excerpt":"In recent years, Large Language Models (LLMs) have demonstrated significant improvements across a variety of tasks, one of which is the long-context capability. The key to improving long-context performance lies in effective data organization and management strategies that integrate data from multiple domains and optimize the context window during training. Through extensive experimental analysis, we identified three key challenges in designing effective data management strategies that enable the model to achieve long-context capability without sacrificing performance in other tasks: (1) a sho"},"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":"2409.00997","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-02T07:23:13Z","cross_cats_sorted":[],"title_canon_sha256":"82798f9d91ac9412cc14976a277acd16a6da01a15f2307aad6c5ea9ab376f00f","abstract_canon_sha256":"fafa8493b1748a2923a4636c137b5d28bd663e55216dc07ea03abb6b888bec79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:37.772582Z","signature_b64":"kVo3Zj3jHZTEgHrhu9jWl9F1lb0XYCIPDMcZNBU/Ey3xIyUc9f2OgyBYZD7bxRisg3AqD7yKAjPm1NINdngXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"744a1563cfc04d364b813c690786c4a7e9635c0847a8e5f2b0fd7ef5a616cc58","last_reissued_at":"2026-07-05T09:14:37.772076Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:37.772076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DataSculpt: Crafting Data Landscapes for Long-Context LLMs through Multi-Objective Partitioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Cui, Da Pan, Guosheng Dong, Keer Lu, Keshi Zhao, Shusen Zhang, Weipeng Chen, Wentao Zhang, Xiaonan Nie, Zenan Zhou, Zheng Liang","submitted_at":"2024-09-02T07:23:13Z","abstract_excerpt":"In recent years, Large Language Models (LLMs) have demonstrated significant improvements across a variety of tasks, one of which is the long-context capability. The key to improving long-context performance lies in effective data organization and management strategies that integrate data from multiple domains and optimize the context window during training. Through extensive experimental analysis, we identified three key challenges in designing effective data management strategies that enable the model to achieve long-context capability without sacrificing performance in other tasks: (1) a sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00997","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/2409.00997/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":"2409.00997","created_at":"2026-07-05T09:14:37.772135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00997v2","created_at":"2026-07-05T09:14:37.772135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00997","created_at":"2026-07-05T09:14:37.772135+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORFBKY6PYBGT","created_at":"2026-07-05T09:14:37.772135+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORFBKY6PYBGTMS4B","created_at":"2026-07-05T09:14:37.772135+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORFBKY6P","created_at":"2026-07-05T09:14:37.772135+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/ORFBKY6PYBGTMS4BHRUQPBWEU7","json":"https://pith.science/pith/ORFBKY6PYBGTMS4BHRUQPBWEU7.json","graph_json":"https://pith.science/api/pith-number/ORFBKY6PYBGTMS4BHRUQPBWEU7/graph.json","events_json":"https://pith.science/api/pith-number/ORFBKY6PYBGTMS4BHRUQPBWEU7/events.json","paper":"https://pith.science/paper/ORFBKY6P"},"agent_actions":{"view_html":"https://pith.science/pith/ORFBKY6PYBGTMS4BHRUQPBWEU7","download_json":"https://pith.science/pith/ORFBKY6PYBGTMS4BHRUQPBWEU7.json","view_paper":"https://pith.science/paper/ORFBKY6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00997&json=true","fetch_graph":"https://pith.science/api/pith-number/ORFBKY6PYBGTMS4BHRUQPBWEU7/graph.json","fetch_events":"https://pith.science/api/pith-number/ORFBKY6PYBGTMS4BHRUQPBWEU7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORFBKY6PYBGTMS4BHRUQPBWEU7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORFBKY6PYBGTMS4BHRUQPBWEU7/action/storage_attestation","attest_author":"https://pith.science/pith/ORFBKY6PYBGTMS4BHRUQPBWEU7/action/author_attestation","sign_citation":"https://pith.science/pith/ORFBKY6PYBGTMS4BHRUQPBWEU7/action/citation_signature","submit_replication":"https://pith.science/pith/ORFBKY6PYBGTMS4BHRUQPBWEU7/action/replication_record"}},"created_at":"2026-07-05T09:14:37.772135+00:00","updated_at":"2026-07-05T09:14:37.772135+00:00"}