{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:55GVQLEEFLD3RA5C66XIMXD2FB","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":"e3ebf3be09ef0d9d058bc35b99b2000a304b90f3854e16f8e1c5aa1015cb10da","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-01T01:10:59Z","title_canon_sha256":"b0eff8bcfa52c4a0867e918888f3548481a888b0ca8e118069ac1f8a7485ade0"},"schema_version":"1.0","source":{"id":"2501.00692","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00692","created_at":"2026-07-05T09:56:09Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00692v1","created_at":"2026-07-05T09:56:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00692","created_at":"2026-07-05T09:56:09Z"},{"alias_kind":"pith_short_12","alias_value":"55GVQLEEFLD3","created_at":"2026-07-05T09:56:09Z"},{"alias_kind":"pith_short_16","alias_value":"55GVQLEEFLD3RA5C","created_at":"2026-07-05T09:56:09Z"},{"alias_kind":"pith_short_8","alias_value":"55GVQLEE","created_at":"2026-07-05T09:56:09Z"}],"graph_snapshots":[{"event_id":"sha256:2ce09ec47f2998e5b46f3cbacdc75368eaf48b50b35351c51d1a88aad31ab1ae","target":"graph","created_at":"2026-07-05T09:56:09Z","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/2501.00692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite very fast progress, efficiently training large language models (LLMs) in very long contexts remains challenging. Existing methods fall back to training LLMs with short contexts (a maximum of a few thousands tokens in training) and use inference time techniques when evaluating on long contexts (above 1M tokens context window at inference). As opposed to long-context-inference, training on very long context input prompts is quickly limited by GPU memory availability and by the prohibitively long training times it requires on state-of-the-art hardware. Meanwhile, many real-life applicatio","authors_text":"Amir Tavanaei, Karim Bouyarmane, Kavosh Asadi, Xingzi Xu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-01T01:10:59Z","title":"Adjoint sharding for very long context training of state space models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00692","kind":"arxiv","version":1},"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":"sha256:4118ee2f25cd2241cef46efc920cf4e6aa0316b9b89afc5d78a612654ece5848","target":"record","created_at":"2026-07-05T09:56:09Z","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":"e3ebf3be09ef0d9d058bc35b99b2000a304b90f3854e16f8e1c5aa1015cb10da","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-01T01:10:59Z","title_canon_sha256":"b0eff8bcfa52c4a0867e918888f3548481a888b0ca8e118069ac1f8a7485ade0"},"schema_version":"1.0","source":{"id":"2501.00692","kind":"arxiv","version":1}},"canonical_sha256":"ef4d582c842ac7b883a2f7ae865c7a2855cbe346df067f0e9d0e065f3f131e7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef4d582c842ac7b883a2f7ae865c7a2855cbe346df067f0e9d0e065f3f131e7b","first_computed_at":"2026-07-05T09:56:09.077376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:09.077376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ceJ/D79aDQD58O71bllevSw79zFoLc0KMIdma4artMBuLKKWtW/0Dp/pz81AWPcpnmIiICP406sXxSDs226jBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:09.077848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00692","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4118ee2f25cd2241cef46efc920cf4e6aa0316b9b89afc5d78a612654ece5848","sha256:2ce09ec47f2998e5b46f3cbacdc75368eaf48b50b35351c51d1a88aad31ab1ae"],"state_sha256":"52da23258951e295bab546aef67538e6e79e97b88775dc675218238daa6e6a35"}