{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZZW3P6TZIJFOYAMBEMK2RUZWWN","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":"4e54422611b62e4e2b79a2a3ce935c54393b2fdaad30fc947dcecc1f289de915","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-22T01:52:30Z","title_canon_sha256":"1db49b857107fb17de483083d8687226fe96bcbcbd26549049d5af732ec05183"},"schema_version":"1.0","source":{"id":"2407.15892","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15892","created_at":"2026-07-05T09:33:35Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15892v4","created_at":"2026-07-05T09:33:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15892","created_at":"2026-07-05T09:33:35Z"},{"alias_kind":"pith_short_12","alias_value":"ZZW3P6TZIJFO","created_at":"2026-07-05T09:33:35Z"},{"alias_kind":"pith_short_16","alias_value":"ZZW3P6TZIJFOYAMB","created_at":"2026-07-05T09:33:35Z"},{"alias_kind":"pith_short_8","alias_value":"ZZW3P6TZ","created_at":"2026-07-05T09:33:35Z"}],"graph_snapshots":[{"event_id":"sha256:53b7a78a35c3423580df1c195ba271567035f5addd80e7dcbc60aa30206173a3","target":"graph","created_at":"2026-07-05T09:33:35Z","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/2407.15892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Mini-Sequence Transformer (MsT), a simple and effective methodology for highly efficient and accurate LLM training with extremely long sequences. MsT partitions input sequences and iteratively processes mini-sequences to reduce intermediate memory usage. Integrated with activation recomputation, it enables significant memory savings in both forward and backward passes. In experiments with the Llama3-8B model, with MsT, we measure no degradation in throughput or convergence even with 12x longer sequences than standard implementations. MsT is fully general, implementation-agnostic, ","authors_text":"Anima Anandkumar, Beidi Chen, Cheng Luo, Jiawei Zhao, Zhuoming Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-22T01:52:30Z","title":"Mini-Sequence Transformer: Optimizing Intermediate Memory for Long Sequences Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15892","kind":"arxiv","version":4},"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":"sha256:7cabec570e41efe9d60c3e74d1a393412de085f26ee25e48af57923354863335","target":"record","created_at":"2026-07-05T09:33:35Z","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":"4e54422611b62e4e2b79a2a3ce935c54393b2fdaad30fc947dcecc1f289de915","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-22T01:52:30Z","title_canon_sha256":"1db49b857107fb17de483083d8687226fe96bcbcbd26549049d5af732ec05183"},"schema_version":"1.0","source":{"id":"2407.15892","kind":"arxiv","version":4}},"canonical_sha256":"ce6db7fa79424aec01812315a8d336b354eedf9d14e9aa23823261de35e72464","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce6db7fa79424aec01812315a8d336b354eedf9d14e9aa23823261de35e72464","first_computed_at":"2026-07-05T09:33:35.550288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:35.550288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cYM1qgPOIMbIW6ydosRSkH4SKP01+a6Q3VvEroLqQ4EKR252VceeziiffHh/aYl7wLQ5Obk1QWhVEzHbasWQAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:35.550784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.15892","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cabec570e41efe9d60c3e74d1a393412de085f26ee25e48af57923354863335","sha256:53b7a78a35c3423580df1c195ba271567035f5addd80e7dcbc60aa30206173a3"],"state_sha256":"163e8edf03f178a195b7bf94deedbdf59daaa151b3504f7eba2a56dce8b3a6d8"}