{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NB6NEJ2ELIO4R7C4INR6LOCLU5","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":"c8a84a69cd26d8a8b6ce53af3bc18f47be8d7456b10e69b668f5f31a23662c49","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-21T22:26:01Z","title_canon_sha256":"b24ae81f10ba21b6c75ec72e267f6ba6342afa16eb9eec605f26732bad3620e4"},"schema_version":"1.0","source":{"id":"2405.13226","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.13226","created_at":"2026-07-05T09:57:42Z"},{"alias_kind":"arxiv_version","alias_value":"2405.13226v2","created_at":"2026-07-05T09:57:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13226","created_at":"2026-07-05T09:57:42Z"},{"alias_kind":"pith_short_12","alias_value":"NB6NEJ2ELIO4","created_at":"2026-07-05T09:57:42Z"},{"alias_kind":"pith_short_16","alias_value":"NB6NEJ2ELIO4R7C4","created_at":"2026-07-05T09:57:42Z"},{"alias_kind":"pith_short_8","alias_value":"NB6NEJ2E","created_at":"2026-07-05T09:57:42Z"}],"graph_snapshots":[{"event_id":"sha256:f83f29a9fc492f4944adafe16fffda1d444f310048ae83d759b24e3bbeddcd6d","target":"graph","created_at":"2026-07-05T09:57:42Z","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/2405.13226/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are commonly trained on datasets consisting of fixed-length token sequences. These datasets are created by randomly concatenating documents of various lengths and then chunking them into sequences of a predetermined target length (concat-and-chunk). Recent attention implementations mask cross-document attention, reducing the effective length of a chunk of tokens. Additionally, training on long sequences becomes computationally prohibitive due to the quadratic cost of attention. In this study, we introduce dataset decomposition, a novel variable sequence length trai","authors_text":"Cem Koc, Chun-Liang Li, Hadi Pouransari, Jen-Hao Rick Chang, Oncel Tuzel, Pavan Kumar Anasosalu Vasu, Vaishaal Shankar","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-21T22:26:01Z","title":"Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13226","kind":"arxiv","version":2},"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:ebc619fc95a6bc8c352af50ed62576281cc8bf3ef7ec18b209faf075e4271483","target":"record","created_at":"2026-07-05T09:57:42Z","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":"c8a84a69cd26d8a8b6ce53af3bc18f47be8d7456b10e69b668f5f31a23662c49","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-21T22:26:01Z","title_canon_sha256":"b24ae81f10ba21b6c75ec72e267f6ba6342afa16eb9eec605f26732bad3620e4"},"schema_version":"1.0","source":{"id":"2405.13226","kind":"arxiv","version":2}},"canonical_sha256":"687cd227445a1dc8fc5c4363e5b84ba7668ffae009063d4564d6d7e00e5f19c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"687cd227445a1dc8fc5c4363e5b84ba7668ffae009063d4564d6d7e00e5f19c4","first_computed_at":"2026-07-05T09:57:42.833219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:42.833219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UBbNAgyMAwGTtPWGQcnFkvPGPRzbFq+qVd7KvfHnt+Kgkc7eLlFvIhC93I2wdPuOGM8NJQhFBq/MT+VhHK7vBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:42.833727Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.13226","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebc619fc95a6bc8c352af50ed62576281cc8bf3ef7ec18b209faf075e4271483","sha256:f83f29a9fc492f4944adafe16fffda1d444f310048ae83d759b24e3bbeddcd6d"],"state_sha256":"7e8b3e10133547aa9ea2a146856afa9208713acb0c8de3dd100c502c9482fb64"}