{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3LJCKD4B4GIRCRBHNVFW4X4LAR","short_pith_number":"pith:3LJCKD4B","canonical_record":{"source":{"id":"2105.13626","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-28T07:03:22Z","cross_cats_sorted":[],"title_canon_sha256":"fa488a8c75a41ea0c2ebcdcee8bbb47ec79066d2e89acad0b9b8c6077725ffa6","abstract_canon_sha256":"16fa2b7cc537399de5a921ee5444ab2cdefd2d3b5cd7a8f43026267b1acfd47f"},"schema_version":"1.0"},"canonical_sha256":"dad2250f81e1911144276d4b6e5f8b0474f88df1bda3e3ae0912d9f58d7f58ed","source":{"kind":"arxiv","id":"2105.13626","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.13626","created_at":"2026-07-05T04:02:38Z"},{"alias_kind":"arxiv_version","alias_value":"2105.13626v3","created_at":"2026-07-05T04:02:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13626","created_at":"2026-07-05T04:02:38Z"},{"alias_kind":"pith_short_12","alias_value":"3LJCKD4B4GIR","created_at":"2026-07-05T04:02:38Z"},{"alias_kind":"pith_short_16","alias_value":"3LJCKD4B4GIRCRBH","created_at":"2026-07-05T04:02:38Z"},{"alias_kind":"pith_short_8","alias_value":"3LJCKD4B","created_at":"2026-07-05T04:02:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3LJCKD4B4GIRCRBHNVFW4X4LAR","target":"record","payload":{"canonical_record":{"source":{"id":"2105.13626","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-28T07:03:22Z","cross_cats_sorted":[],"title_canon_sha256":"fa488a8c75a41ea0c2ebcdcee8bbb47ec79066d2e89acad0b9b8c6077725ffa6","abstract_canon_sha256":"16fa2b7cc537399de5a921ee5444ab2cdefd2d3b5cd7a8f43026267b1acfd47f"},"schema_version":"1.0"},"canonical_sha256":"dad2250f81e1911144276d4b6e5f8b0474f88df1bda3e3ae0912d9f58d7f58ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:38.893430Z","signature_b64":"dAt5NdmBNAyAZkEwkKQmC2LkabG123iOXm7GfjGuY86x0HPEv2irAnuWCY+wVDxhOIuYn2mmeurSQ192zCN6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dad2250f81e1911144276d4b6e5f8b0474f88df1bda3e3ae0912d9f58d7f58ed","last_reissued_at":"2026-07-05T04:02:38.892936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:38.892936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.13626","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:02:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CJ0XkWJ4XQOFw89Eb0wOe9YSUvTSR2dwl+tA4xlSKx8Z4GkgYeV6md7pgSA8ErHzonYvuVZW3GTt6xKD9r/FDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:37:40.648978Z"},"content_sha256":"e8da3ea813158b38141dfc2ab0858917785727c36cfc3aff33b6133158f3ae87","schema_version":"1.0","event_id":"sha256:e8da3ea813158b38141dfc2ab0858917785727c36cfc3aff33b6133158f3ae87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3LJCKD4B4GIRCRBHNVFW4X4LAR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Roberts, Aditya Barua, Colin Raffel, Linting Xue, Mihir Kale, Noah Constant, Rami Al-Rfou, Sharan Narang","submitted_at":"2021-05-28T07:03:22Z","abstract_excerpt":"Most widely-used pre-trained language models operate on sequences of tokens corresponding to word or subword units. By comparison, token-free models that operate directly on raw text (bytes or characters) have many benefits: they can process text in any language out of the box, they are more robust to noise, and they minimize technical debt by removing complex and error-prone text preprocessing pipelines. Since byte or character sequences are longer than token sequences, past work on token-free models has often introduced new model architectures designed to amortize the cost of operating direc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13626","kind":"arxiv","version":3},"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/2105.13626/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":"2026-07-05T04:02:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V0HY+2Sv9icjay/auw3lsasz9LpSrrmMGMo2+O7AINJSpkrvcDke5MZQguWN7slRN1f5BLVwRxyGuJUgKzMyCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:37:40.649473Z"},"content_sha256":"37c09e11735f13eb561228fdcda9a7fd9b34b51c6b44c66425e1325d123e5594","schema_version":"1.0","event_id":"sha256:37c09e11735f13eb561228fdcda9a7fd9b34b51c6b44c66425e1325d123e5594"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3LJCKD4B4GIRCRBHNVFW4X4LAR/bundle.json","state_url":"https://pith.science/pith/3LJCKD4B4GIRCRBHNVFW4X4LAR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3LJCKD4B4GIRCRBHNVFW4X4LAR/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":"2026-08-09T14:37:40Z","links":{"resolver":"https://pith.science/pith/3LJCKD4B4GIRCRBHNVFW4X4LAR","bundle":"https://pith.science/pith/3LJCKD4B4GIRCRBHNVFW4X4LAR/bundle.json","state":"https://pith.science/pith/3LJCKD4B4GIRCRBHNVFW4X4LAR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3LJCKD4B4GIRCRBHNVFW4X4LAR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3LJCKD4B4GIRCRBHNVFW4X4LAR","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":"16fa2b7cc537399de5a921ee5444ab2cdefd2d3b5cd7a8f43026267b1acfd47f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-28T07:03:22Z","title_canon_sha256":"fa488a8c75a41ea0c2ebcdcee8bbb47ec79066d2e89acad0b9b8c6077725ffa6"},"schema_version":"1.0","source":{"id":"2105.13626","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.13626","created_at":"2026-07-05T04:02:38Z"},{"alias_kind":"arxiv_version","alias_value":"2105.13626v3","created_at":"2026-07-05T04:02:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13626","created_at":"2026-07-05T04:02:38Z"},{"alias_kind":"pith_short_12","alias_value":"3LJCKD4B4GIR","created_at":"2026-07-05T04:02:38Z"},{"alias_kind":"pith_short_16","alias_value":"3LJCKD4B4GIRCRBH","created_at":"2026-07-05T04:02:38Z"},{"alias_kind":"pith_short_8","alias_value":"3LJCKD4B","created_at":"2026-07-05T04:02:38Z"}],"graph_snapshots":[{"event_id":"sha256:37c09e11735f13eb561228fdcda9a7fd9b34b51c6b44c66425e1325d123e5594","target":"graph","created_at":"2026-07-05T04:02:38Z","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/2105.13626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most widely-used pre-trained language models operate on sequences of tokens corresponding to word or subword units. By comparison, token-free models that operate directly on raw text (bytes or characters) have many benefits: they can process text in any language out of the box, they are more robust to noise, and they minimize technical debt by removing complex and error-prone text preprocessing pipelines. Since byte or character sequences are longer than token sequences, past work on token-free models has often introduced new model architectures designed to amortize the cost of operating direc","authors_text":"Adam Roberts, Aditya Barua, Colin Raffel, Linting Xue, Mihir Kale, Noah Constant, Rami Al-Rfou, Sharan Narang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-28T07:03:22Z","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13626","kind":"arxiv","version":3},"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:e8da3ea813158b38141dfc2ab0858917785727c36cfc3aff33b6133158f3ae87","target":"record","created_at":"2026-07-05T04:02:38Z","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":"16fa2b7cc537399de5a921ee5444ab2cdefd2d3b5cd7a8f43026267b1acfd47f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-28T07:03:22Z","title_canon_sha256":"fa488a8c75a41ea0c2ebcdcee8bbb47ec79066d2e89acad0b9b8c6077725ffa6"},"schema_version":"1.0","source":{"id":"2105.13626","kind":"arxiv","version":3}},"canonical_sha256":"dad2250f81e1911144276d4b6e5f8b0474f88df1bda3e3ae0912d9f58d7f58ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dad2250f81e1911144276d4b6e5f8b0474f88df1bda3e3ae0912d9f58d7f58ed","first_computed_at":"2026-07-05T04:02:38.892936Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:02:38.892936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dAt5NdmBNAyAZkEwkKQmC2LkabG123iOXm7GfjGuY86x0HPEv2irAnuWCY+wVDxhOIuYn2mmeurSQ192zCN6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:02:38.893430Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.13626","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8da3ea813158b38141dfc2ab0858917785727c36cfc3aff33b6133158f3ae87","sha256:37c09e11735f13eb561228fdcda9a7fd9b34b51c6b44c66425e1325d123e5594"],"state_sha256":"ed4dd75da3283a22e0df3a91d143afb08f382dfc9f896a243e020778c507e7e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tCwy8iL9s7tUJROkjIcIwLkAymAhvJ8Y2NtBsexAxq6yHnLkfT8EZm0npf8bIoTjKpbflkR69nxsF5TfGJm8DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:37:40.654417Z","bundle_sha256":"60bfc0a91fc1e9f3c68f6f37c68650ede0dfc3d90e98c701d39e894e50f82f9d"}}