{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EYIGROPEF4Z3F7JKKGSVKO7G2F","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":"7ee84f07476b54206d5e9c93169bdf8d500d197ac8dd1d70ca33e2263b81d32d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T05:33:32Z","title_canon_sha256":"39903fd6b9c5d47d68b43eb21f4be23eaac7779998532d401e8c3e5804adddf4"},"schema_version":"1.0","source":{"id":"2412.09871","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09871","created_at":"2026-07-05T09:48:43Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09871v1","created_at":"2026-07-05T09:48:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09871","created_at":"2026-07-05T09:48:43Z"},{"alias_kind":"pith_short_12","alias_value":"EYIGROPEF4Z3","created_at":"2026-07-05T09:48:43Z"},{"alias_kind":"pith_short_16","alias_value":"EYIGROPEF4Z3F7JK","created_at":"2026-07-05T09:48:43Z"},{"alias_kind":"pith_short_8","alias_value":"EYIGROPE","created_at":"2026-07-05T09:48:43Z"}],"graph_snapshots":[{"event_id":"sha256:a654e291c3b1621e26e9384e927eff0e666a47c5be9764a86055059a6305fe1c","target":"graph","created_at":"2026-07-05T09:48:43Z","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/2412.09871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce the Byte Latent Transformer (BLT), a new byte-level LLM architecture that, for the first time, matches tokenization-based LLM performance at scale with significant improvements in inference efficiency and robustness. BLT encodes bytes into dynamically sized patches, which serve as the primary units of computation. Patches are segmented based on the entropy of the next byte, allocating more compute and model capacity where increased data complexity demands it. We present the first FLOP controlled scaling study of byte-level models up to 8B parameters and 4T training bytes. Our resu","authors_text":"Ari Holtzman, Artidoro Pagnoni, Benjamin Muller, Chunting Zhou, Gargi Ghosh, Jason Weston, John Nguyen, Lili Yu, Luke Zettlemoyer, Margaret Li, Mike Lewis, Pedro Rodriguez, Ram Pasunuru, Srinivasan Iyer","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T05:33:32Z","title":"Byte Latent Transformer: Patches Scale Better Than Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09871","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:a817c9fad43682b439bc039c5ceac5b783a0759d2df2f8304da2d13ff6d72e19","target":"record","created_at":"2026-07-05T09:48:43Z","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":"7ee84f07476b54206d5e9c93169bdf8d500d197ac8dd1d70ca33e2263b81d32d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T05:33:32Z","title_canon_sha256":"39903fd6b9c5d47d68b43eb21f4be23eaac7779998532d401e8c3e5804adddf4"},"schema_version":"1.0","source":{"id":"2412.09871","kind":"arxiv","version":1}},"canonical_sha256":"261068b9e42f33b2fd2a51a5553be6d178197fff1d3b780168ac799c749b7383","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"261068b9e42f33b2fd2a51a5553be6d178197fff1d3b780168ac799c749b7383","first_computed_at":"2026-07-05T09:48:43.086337Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:43.086337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C899/LCsEwtYM71C1Q6q1yK8kyr2/44OiyPWYvZe5SDgytu1XIDgQrYNydHfG0KBqtE/Qx8pSLGQuh1Qq/S4Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:43.086831Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09871","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a817c9fad43682b439bc039c5ceac5b783a0759d2df2f8304da2d13ff6d72e19","sha256:a654e291c3b1621e26e9384e927eff0e666a47c5be9764a86055059a6305fe1c"],"state_sha256":"b51d687f6f0e494f69369007ac9360055e76209bc803459c19540bfeb84e20b1"}