{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:S743BM3E76M6S5KCDWDRSK4CAA","short_pith_number":"pith:S743BM3E","canonical_record":{"source":{"id":"2608.03599","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T12:51:21Z","cross_cats_sorted":[],"title_canon_sha256":"b655070da327bbfe238c721ed3fb1eea729a2222f516ad5368ee63d22069f0d8","abstract_canon_sha256":"e82a72e15665dd387885fd88324ae305affe55cdb68ce03ee70f7197438d9c52"},"schema_version":"1.0"},"canonical_sha256":"97f9b0b364ff99e975421d87192b82000b6364832cd38697c7591aeb9e92e004","source":{"kind":"arxiv","id":"2608.03599","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03599","created_at":"2026-08-05T01:36:44Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03599v1","created_at":"2026-08-05T01:36:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03599","created_at":"2026-08-05T01:36:44Z"},{"alias_kind":"pith_short_12","alias_value":"S743BM3E76M6","created_at":"2026-08-05T01:36:44Z"},{"alias_kind":"pith_short_16","alias_value":"S743BM3E76M6S5KC","created_at":"2026-08-05T01:36:44Z"},{"alias_kind":"pith_short_8","alias_value":"S743BM3E","created_at":"2026-08-05T01:36:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:S743BM3E76M6S5KCDWDRSK4CAA","target":"record","payload":{"canonical_record":{"source":{"id":"2608.03599","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T12:51:21Z","cross_cats_sorted":[],"title_canon_sha256":"b655070da327bbfe238c721ed3fb1eea729a2222f516ad5368ee63d22069f0d8","abstract_canon_sha256":"e82a72e15665dd387885fd88324ae305affe55cdb68ce03ee70f7197438d9c52"},"schema_version":"1.0"},"canonical_sha256":"97f9b0b364ff99e975421d87192b82000b6364832cd38697c7591aeb9e92e004","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:36:44.280185Z","signature_b64":"xzJ9v2LSoQiERRp1MObmLHne9rS6y3mgLfvCdYvCeHgoWq7GyReqE5d8aPyQfrFY5lU39o/x/cJ3urd9Ds3XAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97f9b0b364ff99e975421d87192b82000b6364832cd38697c7591aeb9e92e004","last_reissued_at":"2026-08-05T01:36:44.278724Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:36:44.278724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.03599","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":"2026-08-05T01:36:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"smxOZzd39xrvqh9y8dMz+Qpj2DvD5zdJEFSvXMgiQw7ihd7qwLptzHrDdnJm4iWF9nsVeRgWz1itp3h5PhDQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:46:53.474755Z"},"content_sha256":"049e26d641ba9df56d819d18ea7b3e0eebe368931ee17938758c75db1a1e4ec6","schema_version":"1.0","event_id":"sha256:049e26d641ba9df56d819d18ea7b3e0eebe368931ee17938758c75db1a1e4ec6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:S743BM3E76M6S5KCDWDRSK4CAA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Disentangling Language Modeling and Boundaries","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mykola Haltiuk","submitted_at":"2026-08-04T12:51:21Z","abstract_excerpt":"Byte-level language models are usually argued for on the grounds of robustness, multilingual fairness, and character-level skills. We point to a different, structural advantage: because they read and write bytes, any two of them share an output space, so knowledge transfer between them is exact and independent of how either was originally tokenized. We hypothesize that the two distributions a byte-level model produces, one over the next byte, one over where its patch boundaries fall, can be disentangled and changed almost independently. A model could absorb a teacher's capability while keeping"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03599","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/2608.03599/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":"2026-08-05T01:36:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+FIOzcQk2DL7mXzW68z4VcFYZXR/avuoHe9pGIgoZVIgZZDWTZb+/141DcHMRsDvExG6nEMJbXgX/x8wY0z7CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:46:53.475259Z"},"content_sha256":"d7704f2d849fadb45990eadafe18e0fd60ec45d20e2eaee734363a847cfbe99c","schema_version":"1.0","event_id":"sha256:d7704f2d849fadb45990eadafe18e0fd60ec45d20e2eaee734363a847cfbe99c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S743BM3E76M6S5KCDWDRSK4CAA/bundle.json","state_url":"https://pith.science/pith/S743BM3E76M6S5KCDWDRSK4CAA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S743BM3E76M6S5KCDWDRSK4CAA/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":"2026-08-06T04:46:53Z","links":{"resolver":"https://pith.science/pith/S743BM3E76M6S5KCDWDRSK4CAA","bundle":"https://pith.science/pith/S743BM3E76M6S5KCDWDRSK4CAA/bundle.json","state":"https://pith.science/pith/S743BM3E76M6S5KCDWDRSK4CAA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S743BM3E76M6S5KCDWDRSK4CAA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:S743BM3E76M6S5KCDWDRSK4CAA","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":"e82a72e15665dd387885fd88324ae305affe55cdb68ce03ee70f7197438d9c52","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T12:51:21Z","title_canon_sha256":"b655070da327bbfe238c721ed3fb1eea729a2222f516ad5368ee63d22069f0d8"},"schema_version":"1.0","source":{"id":"2608.03599","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03599","created_at":"2026-08-05T01:36:44Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03599v1","created_at":"2026-08-05T01:36:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03599","created_at":"2026-08-05T01:36:44Z"},{"alias_kind":"pith_short_12","alias_value":"S743BM3E76M6","created_at":"2026-08-05T01:36:44Z"},{"alias_kind":"pith_short_16","alias_value":"S743BM3E76M6S5KC","created_at":"2026-08-05T01:36:44Z"},{"alias_kind":"pith_short_8","alias_value":"S743BM3E","created_at":"2026-08-05T01:36:44Z"}],"graph_snapshots":[{"event_id":"sha256:d7704f2d849fadb45990eadafe18e0fd60ec45d20e2eaee734363a847cfbe99c","target":"graph","created_at":"2026-08-05T01:36:44Z","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/2608.03599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Byte-level language models are usually argued for on the grounds of robustness, multilingual fairness, and character-level skills. We point to a different, structural advantage: because they read and write bytes, any two of them share an output space, so knowledge transfer between them is exact and independent of how either was originally tokenized. We hypothesize that the two distributions a byte-level model produces, one over the next byte, one over where its patch boundaries fall, can be disentangled and changed almost independently. A model could absorb a teacher's capability while keeping","authors_text":"Mykola Haltiuk","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T12:51:21Z","title":"Disentangling Language Modeling and Boundaries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03599","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":"sha256:049e26d641ba9df56d819d18ea7b3e0eebe368931ee17938758c75db1a1e4ec6","target":"record","created_at":"2026-08-05T01:36:44Z","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":"e82a72e15665dd387885fd88324ae305affe55cdb68ce03ee70f7197438d9c52","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T12:51:21Z","title_canon_sha256":"b655070da327bbfe238c721ed3fb1eea729a2222f516ad5368ee63d22069f0d8"},"schema_version":"1.0","source":{"id":"2608.03599","kind":"arxiv","version":1}},"canonical_sha256":"97f9b0b364ff99e975421d87192b82000b6364832cd38697c7591aeb9e92e004","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97f9b0b364ff99e975421d87192b82000b6364832cd38697c7591aeb9e92e004","first_computed_at":"2026-08-05T01:36:44.278724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:36:44.278724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xzJ9v2LSoQiERRp1MObmLHne9rS6y3mgLfvCdYvCeHgoWq7GyReqE5d8aPyQfrFY5lU39o/x/cJ3urd9Ds3XAg==","signature_status":"signed_v1","signed_at":"2026-08-05T01:36:44.280185Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03599","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:049e26d641ba9df56d819d18ea7b3e0eebe368931ee17938758c75db1a1e4ec6","sha256:d7704f2d849fadb45990eadafe18e0fd60ec45d20e2eaee734363a847cfbe99c"],"state_sha256":"96d91527a269934f970db76edd34bdbadf466badd21381c372349051e1abf5ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tYVd63ltR+mvKOF19oEXJxrmjKArV/R3DrAWw8WOa9CQQpmqM/8uktDPPqH5zkt+lhPNbv1D09OfvP/XyGKXCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:46:53.479405Z","bundle_sha256":"14ce5b73fa0b8964f7460cb16df2aa2980437ad3ed91ac715d0972bd4cb874f5"}}