{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5NQ53LM2OVDOS7TF27PJMELFB5","short_pith_number":"pith:5NQ53LM2","canonical_record":{"source":{"id":"2605.30080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T15:26:34Z","cross_cats_sorted":[],"title_canon_sha256":"2967217f605ba9da028ca28cc9b1f85954dcb43d3de73a5d7b495b7b2dba3ade","abstract_canon_sha256":"172647105f845e94194633d77c1d3c797603f003fbd51ade1830d51cc7a8f7a8"},"schema_version":"1.0"},"canonical_sha256":"eb61ddad9a7546e97e65d7de9611650f4dbb5f35a7a6c6b58a049d380e05ce84","source":{"kind":"arxiv","id":"2605.30080","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30080","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30080v1","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30080","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"5NQ53LM2OVDO","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"5NQ53LM2OVDOS7TF","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"5NQ53LM2","created_at":"2026-05-29T02:06:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5NQ53LM2OVDOS7TF27PJMELFB5","target":"record","payload":{"canonical_record":{"source":{"id":"2605.30080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T15:26:34Z","cross_cats_sorted":[],"title_canon_sha256":"2967217f605ba9da028ca28cc9b1f85954dcb43d3de73a5d7b495b7b2dba3ade","abstract_canon_sha256":"172647105f845e94194633d77c1d3c797603f003fbd51ade1830d51cc7a8f7a8"},"schema_version":"1.0"},"canonical_sha256":"eb61ddad9a7546e97e65d7de9611650f4dbb5f35a7a6c6b58a049d380e05ce84","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:09.441738Z","signature_b64":"KXj7fzCT2SlaHGoYs6tuZG48mRgnbMc0yPLiXz0DpF2wagU+JfyEmmhdBZic7WdRycjjs9m1ZCgxcreu/wfzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb61ddad9a7546e97e65d7de9611650f4dbb5f35a7a6c6b58a049d380e05ce84","last_reissued_at":"2026-05-29T02:06:09.441370Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:09.441370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.30080","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T02:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ljRoqUha9xsEACTbZp4+Hf+Jfb7KUPG1VZ49qS4g/HqmbJXC2/2vyv064D/839ntZCny+XDmy82o25QKlGFCAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T11:46:31.717306Z"},"content_sha256":"4d06caf56b34f610473eb46f3f943095587915da4ba380b268d957c79b190477","schema_version":"1.0","event_id":"sha256:4d06caf56b34f610473eb46f3f943095587915da4ba380b268d957c79b190477"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5NQ53LM2OVDOS7TF27PJMELFB5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Targeted Dynamic Chunking for Tokenization-Free Hierarchical Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akira Nakagawa, Kenichi Kobayashi, Koichi Shirahata, Thang Dang","submitted_at":"2026-05-28T15:26:34Z","abstract_excerpt":"Tokenization-free hierarchical models are emerging as a promising alternative to traditional Large Language Models (LLMs), addressing inherent preprocessing issues such as vocabulary design complexity, out-of-vocabulary (OOV) errors, and language-specific constraints. However, a significant challenge in these byte-level methods is the optimization of the compression ratio, a critical factor that dictates model performance for processing bytes data via chunks. In this paper, we propose Adaptive Targeted Dynamic Chunking (ATDC), a novel byte-compression control mechanism designed to enhance the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30080","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.30080/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T02:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NZtqNv07R45AbzO2CnnLiYLUfr4KQfjuP3VgNkC15pv72ePkDGVXnFP6GwadD+/+YqSNijtdMXkY8re7jTP7AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T11:46:31.718094Z"},"content_sha256":"87d079f14aadef5757ced621af1b600ccdee1088beef8a490e2c150a4db3963a","schema_version":"1.0","event_id":"sha256:87d079f14aadef5757ced621af1b600ccdee1088beef8a490e2c150a4db3963a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5NQ53LM2OVDOS7TF27PJMELFB5/bundle.json","state_url":"https://pith.science/pith/5NQ53LM2OVDOS7TF27PJMELFB5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5NQ53LM2OVDOS7TF27PJMELFB5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T11:46:31Z","links":{"resolver":"https://pith.science/pith/5NQ53LM2OVDOS7TF27PJMELFB5","bundle":"https://pith.science/pith/5NQ53LM2OVDOS7TF27PJMELFB5/bundle.json","state":"https://pith.science/pith/5NQ53LM2OVDOS7TF27PJMELFB5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5NQ53LM2OVDOS7TF27PJMELFB5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5NQ53LM2OVDOS7TF27PJMELFB5","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":"172647105f845e94194633d77c1d3c797603f003fbd51ade1830d51cc7a8f7a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T15:26:34Z","title_canon_sha256":"2967217f605ba9da028ca28cc9b1f85954dcb43d3de73a5d7b495b7b2dba3ade"},"schema_version":"1.0","source":{"id":"2605.30080","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30080","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30080v1","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30080","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"5NQ53LM2OVDO","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"5NQ53LM2OVDOS7TF","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"5NQ53LM2","created_at":"2026-05-29T02:06:09Z"}],"graph_snapshots":[{"event_id":"sha256:87d079f14aadef5757ced621af1b600ccdee1088beef8a490e2c150a4db3963a","target":"graph","created_at":"2026-05-29T02:06:09Z","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/2605.30080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenization-free hierarchical models are emerging as a promising alternative to traditional Large Language Models (LLMs), addressing inherent preprocessing issues such as vocabulary design complexity, out-of-vocabulary (OOV) errors, and language-specific constraints. However, a significant challenge in these byte-level methods is the optimization of the compression ratio, a critical factor that dictates model performance for processing bytes data via chunks. In this paper, we propose Adaptive Targeted Dynamic Chunking (ATDC), a novel byte-compression control mechanism designed to enhance the ","authors_text":"Akira Nakagawa, Kenichi Kobayashi, Koichi Shirahata, Thang Dang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T15:26:34Z","title":"Adaptive Targeted Dynamic Chunking for Tokenization-Free Hierarchical Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30080","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":"sha256:4d06caf56b34f610473eb46f3f943095587915da4ba380b268d957c79b190477","target":"record","created_at":"2026-05-29T02:06:09Z","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":"172647105f845e94194633d77c1d3c797603f003fbd51ade1830d51cc7a8f7a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T15:26:34Z","title_canon_sha256":"2967217f605ba9da028ca28cc9b1f85954dcb43d3de73a5d7b495b7b2dba3ade"},"schema_version":"1.0","source":{"id":"2605.30080","kind":"arxiv","version":1}},"canonical_sha256":"eb61ddad9a7546e97e65d7de9611650f4dbb5f35a7a6c6b58a049d380e05ce84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb61ddad9a7546e97e65d7de9611650f4dbb5f35a7a6c6b58a049d380e05ce84","first_computed_at":"2026-05-29T02:06:09.441370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:09.441370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KXj7fzCT2SlaHGoYs6tuZG48mRgnbMc0yPLiXz0DpF2wagU+JfyEmmhdBZic7WdRycjjs9m1ZCgxcreu/wfzCA==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:09.441738Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30080","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d06caf56b34f610473eb46f3f943095587915da4ba380b268d957c79b190477","sha256:87d079f14aadef5757ced621af1b600ccdee1088beef8a490e2c150a4db3963a"],"state_sha256":"d0cfa4aa9110fbe511f466795f3d8bfdc60a46f6a421b0650341a01a56ffbf25"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TSQArRWdMS1YBE91FAeKgEgariC/lHnIWRfRCruUP+5EwCD7f2hBcV+BrWRGzerhjgp0SMbtyLp/r02Sg3LwDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T11:46:31.721771Z","bundle_sha256":"67cbd179a93db9dbce98d235804d1880236530722d0ce21ac79a25d41b0a7677"}}