{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X77LESH6A34BJBQS4HXB3YXMXU","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":"82bc1477f53cc59538e4b6f8920ef18837eccd53f053aa0da479bd381bf72273","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-17T17:55:11Z","title_canon_sha256":"1fca76a35686ecd4559b3f9e9655759add15c6786966825a19cce762a2edbf66"},"schema_version":"1.0","source":{"id":"2506.14761","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14761","created_at":"2026-07-05T11:23:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14761v1","created_at":"2026-07-05T11:23:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14761","created_at":"2026-07-05T11:23:12Z"},{"alias_kind":"pith_short_12","alias_value":"X77LESH6A34B","created_at":"2026-07-05T11:23:12Z"},{"alias_kind":"pith_short_16","alias_value":"X77LESH6A34BJBQS","created_at":"2026-07-05T11:23:12Z"},{"alias_kind":"pith_short_8","alias_value":"X77LESH6","created_at":"2026-07-05T11:23:12Z"}],"graph_snapshots":[{"event_id":"sha256:c82c456ff8e6c8fa606822ebc81809f257de8ab52102b4e8425a650d4642deec","target":"graph","created_at":"2026-07-05T11:23:12Z","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/2506.14761/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenization imposes a fixed granularity on the input text, freezing how a language model operates on data and how far in the future it predicts. Byte Pair Encoding (BPE) and similar schemes split text once, build a static vocabulary, and leave the model stuck with that choice. We relax this rigidity by introducing an autoregressive U-Net that learns to embed its own tokens as it trains. The network reads raw bytes, pools them into words, then pairs of words, then up to 4 words, giving it a multi-scale view of the sequence. At deeper stages, the model must predict further into the future -- an","authors_text":"Alessandro Leite, Badr Youbi Idrissi, David Lopez-Paz, Marc Schoenauer, Mathurin Videau, Olivier Teytaud","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-17T17:55:11Z","title":"From Bytes to Ideas: Language Modeling with Autoregressive U-Nets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14761","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":"sha256:6c5a0ba1c73b5adc4624e720a860b96e0b1781c0dba96161134d11071d0034c0","target":"record","created_at":"2026-07-05T11:23:12Z","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":"82bc1477f53cc59538e4b6f8920ef18837eccd53f053aa0da479bd381bf72273","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-17T17:55:11Z","title_canon_sha256":"1fca76a35686ecd4559b3f9e9655759add15c6786966825a19cce762a2edbf66"},"schema_version":"1.0","source":{"id":"2506.14761","kind":"arxiv","version":1}},"canonical_sha256":"bffeb248fe06f8148612e1ee1de2ecbd2f934a0472556aa67611fe3d75503f94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bffeb248fe06f8148612e1ee1de2ecbd2f934a0472556aa67611fe3d75503f94","first_computed_at":"2026-07-05T11:23:12.515524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:12.515524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vusu/lI6O5G0G5Vmi4iLX+9A6dS1bjC9bXJNuxkDaw2yCZACfsW4f0A3R1RQxp1a3cRT4UEAb6QOn+BYT1QdCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:12.516154Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14761","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c5a0ba1c73b5adc4624e720a860b96e0b1781c0dba96161134d11071d0034c0","sha256:c82c456ff8e6c8fa606822ebc81809f257de8ab52102b4e8425a650d4642deec"],"state_sha256":"fdfacf994e4fd4db7fbfb1cacf52fce31a637cecc2c82f849cfca9983deadae2"}