{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GWW2LNLUTCJMDDM3X6P53IC3UB","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":"f4958cbad3f30475cfb2f0f552bc0dab7ac00c2e8d78cb1adbbb6980e46cd2a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T17:39:37Z","title_canon_sha256":"b16515100df1eae92459da2e907bae3722ce79a0c30c4ad8443d8d3bf242a63b"},"schema_version":"1.0","source":{"id":"2507.07955","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07955","created_at":"2026-07-05T11:37:25Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07955v2","created_at":"2026-07-05T11:37:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07955","created_at":"2026-07-05T11:37:25Z"},{"alias_kind":"pith_short_12","alias_value":"GWW2LNLUTCJM","created_at":"2026-07-05T11:37:25Z"},{"alias_kind":"pith_short_16","alias_value":"GWW2LNLUTCJMDDM3","created_at":"2026-07-05T11:37:25Z"},{"alias_kind":"pith_short_8","alias_value":"GWW2LNLU","created_at":"2026-07-05T11:37:25Z"}],"graph_snapshots":[{"event_id":"sha256:18bbfa0b15e78540e83bf359f9e3f0e7501e478fec4d2ee27ad29508cb9ab3ca","target":"graph","created_at":"2026-07-05T11:37:25Z","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/2507.07955/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Major progress on language models (LMs) in recent years has largely resulted from moving away from specialized models designed for specific tasks, to general models based on powerful architectures (e.g. the Transformer) that learn everything from raw data. Despite this trend, pre-processing steps such as tokenization remain a barrier to true end-to-end foundation models. We introduce a collection of new techniques that enable a dynamic chunking mechanism which automatically learns content- and context- dependent segmentation strategies learned jointly with the rest of the model. Incorporating ","authors_text":"Albert Gu, Brandon Wang, Sukjun Hwang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T17:39:37Z","title":"Dynamic Chunking for End-to-End Hierarchical Sequence Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07955","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":"sha256:5d32a6b750d9737898800184bb5ab217fff816608009aa48a41b4adcea130b54","target":"record","created_at":"2026-07-05T11:37:25Z","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":"f4958cbad3f30475cfb2f0f552bc0dab7ac00c2e8d78cb1adbbb6980e46cd2a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T17:39:37Z","title_canon_sha256":"b16515100df1eae92459da2e907bae3722ce79a0c30c4ad8443d8d3bf242a63b"},"schema_version":"1.0","source":{"id":"2507.07955","kind":"arxiv","version":2}},"canonical_sha256":"35ada5b5749892c18d9bbf9fdda05ba04933aea667412f985887b223172d4ecb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35ada5b5749892c18d9bbf9fdda05ba04933aea667412f985887b223172d4ecb","first_computed_at":"2026-07-05T11:37:25.796028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:25.796028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UPplbw6vGgsaY8u1c+b5nXihx4bFx6dVxflv+7tCAS1qrQS3zG3YC2v8rAAp7Rr29PuzpBFx42j6M2YS6Nw0AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:25.796599Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07955","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d32a6b750d9737898800184bb5ab217fff816608009aa48a41b4adcea130b54","sha256:18bbfa0b15e78540e83bf359f9e3f0e7501e478fec4d2ee27ad29508cb9ab3ca"],"state_sha256":"a1041b74a4ffa8c6b4ee64c6a3df62303da58cfd4692c5e143ace29579645240"}