{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VLJ5Y4F3FPA5LJNPOZMDA7R2S2","short_pith_number":"pith:VLJ5Y4F3","canonical_record":{"source":{"id":"2607.16117","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-17T16:55:27Z","cross_cats_sorted":[],"title_canon_sha256":"619ef7c0aeda9ee4089882217c6b15711752c95c0e3a6213b21ecabca86b6b7d","abstract_canon_sha256":"34ebff2d672bd251bbb92c7e4cf1302992e01528cc9e53b1ad77e129b65b70d7"},"schema_version":"1.0"},"canonical_sha256":"aad3dc70bb2bc1d5a5af7658307e3a9683ce4b59c4969926b32c422792241af3","source":{"kind":"arxiv","id":"2607.16117","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16117","created_at":"2026-07-20T02:19:34Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16117v1","created_at":"2026-07-20T02:19:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16117","created_at":"2026-07-20T02:19:34Z"},{"alias_kind":"pith_short_12","alias_value":"VLJ5Y4F3FPA5","created_at":"2026-07-20T02:19:34Z"},{"alias_kind":"pith_short_16","alias_value":"VLJ5Y4F3FPA5LJNP","created_at":"2026-07-20T02:19:34Z"},{"alias_kind":"pith_short_8","alias_value":"VLJ5Y4F3","created_at":"2026-07-20T02:19:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VLJ5Y4F3FPA5LJNPOZMDA7R2S2","target":"record","payload":{"canonical_record":{"source":{"id":"2607.16117","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-17T16:55:27Z","cross_cats_sorted":[],"title_canon_sha256":"619ef7c0aeda9ee4089882217c6b15711752c95c0e3a6213b21ecabca86b6b7d","abstract_canon_sha256":"34ebff2d672bd251bbb92c7e4cf1302992e01528cc9e53b1ad77e129b65b70d7"},"schema_version":"1.0"},"canonical_sha256":"aad3dc70bb2bc1d5a5af7658307e3a9683ce4b59c4969926b32c422792241af3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T02:19:34.341906Z","signature_b64":"8OYm42mc4cqorzKv2u6zmeyO67MzqpWqhCmo7XnKjot8RUHay33rCMNCBPK1P2PBsJlnCHXuxth+WosYNCuxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aad3dc70bb2bc1d5a5af7658307e3a9683ce4b59c4969926b32c422792241af3","last_reissued_at":"2026-07-20T02:19:34.341061Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T02:19:34.341061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.16117","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":"2026-07-20T02:19:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lPb4EmhncMY+hMdKASoTtfjg40KZ/uevrVouitxaUUv9ad4RMwm/FLeisj021KBhGW64ArV1CxQPtNf2KKgFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:48:52.542967Z"},"content_sha256":"98d5d3b517a2c5adf01358eb772bb42481d4595f55d7e8fdbeaa2edfb5857512","schema_version":"1.0","event_id":"sha256:98d5d3b517a2c5adf01358eb772bb42481d4595f55d7e8fdbeaa2edfb5857512"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VLJ5Y4F3FPA5LJNPOZMDA7R2S2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Desmond Elliott, Ingo Ziegler, Martin Krebs","submitted_at":"2026-07-17T16:55:27Z","abstract_excerpt":"Language models encode text as subword tokens, raw bytes, or rendered pixels, but these encodings are usually compared under modeling constraints that expose different amounts of linguistic content to models across different languages. We instead ask what each encoding preserves when both the content and the downstream capacity are controlled. Using verified parallel sentences across thirteen languages and five scripts, we compare tokens, bytes, and pixels through a shared bottleneck whose width is swept to trace rate-utility frontiers. This separates three quantities that are often conflated:"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16117","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/2607.16117/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":"2026-07-20T02:19:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pH4Cnxev7AJd2QhipsmuQbh3kA4+BlnUbBk+1wqDN+XBWXrGJLjKWIX7j/W8svcFY7GqgVRBncqqdcgotKkWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:48:52.543548Z"},"content_sha256":"a69e63898038d974f582e98617c90d52a28bba1703424ae02fbf9e657e0e4941","schema_version":"1.0","event_id":"sha256:a69e63898038d974f582e98617c90d52a28bba1703424ae02fbf9e657e0e4941"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:VLJ5Y4F3FPA5LJNPOZMDA7R2S2","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/N19-1423) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. BERT : Pre-training of deep bidirectional transformers for language understanding. In Jill Burstein, Christy Doran, and Thamar Solorio (eds.), Proceedings of the 2019 Confere","arxiv_id":"2607.16117","detector":"doi_compliance","evidence":{"ref_index":8,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.18653/v1/","reconstructed_doi":"10.18653/v1/N19-1423"},"severity":"advisory","ref_index":8,"audited_at":"2026-08-01T21:29:35.124143Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/N19-1423","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"9129570a2e7491daf83c2441a2b3244885fa0156485d00a0eb163817dcd1aa21","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":16652,"payload_sha256":"999d5a58a65c44c2f0ba08df7d5d1d34de64dd27497b2bd63ac99f61c1b58d22","signature_b64":"SwbmauZFmJDEiHlryabeHUWLZBw5fACmN6uGPqpq2nOwbqDuD0CrgkaHfyFj6WTfnQZyyDjN7Lol0E8jiSJICg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-01T21:33:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dH3zSikaa+kfNtC5zYGv3IvFtuLzq5OotcY4eWDoo742aH0x09xvm+4y9v45tKHxAq1o8gPzEoZVlmTvD2/KDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:48:52.546087Z"},"content_sha256":"34c31bda8111a53437d5506bd8566cac78f71dfae656b6b9d8f351857c4af8e1","schema_version":"1.0","event_id":"sha256:34c31bda8111a53437d5506bd8566cac78f71dfae656b6b9d8f351857c4af8e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VLJ5Y4F3FPA5LJNPOZMDA7R2S2/bundle.json","state_url":"https://pith.science/pith/VLJ5Y4F3FPA5LJNPOZMDA7R2S2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VLJ5Y4F3FPA5LJNPOZMDA7R2S2/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":"2026-08-08T04:48:52Z","links":{"resolver":"https://pith.science/pith/VLJ5Y4F3FPA5LJNPOZMDA7R2S2","bundle":"https://pith.science/pith/VLJ5Y4F3FPA5LJNPOZMDA7R2S2/bundle.json","state":"https://pith.science/pith/VLJ5Y4F3FPA5LJNPOZMDA7R2S2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VLJ5Y4F3FPA5LJNPOZMDA7R2S2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VLJ5Y4F3FPA5LJNPOZMDA7R2S2","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"34ebff2d672bd251bbb92c7e4cf1302992e01528cc9e53b1ad77e129b65b70d7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-17T16:55:27Z","title_canon_sha256":"619ef7c0aeda9ee4089882217c6b15711752c95c0e3a6213b21ecabca86b6b7d"},"schema_version":"1.0","source":{"id":"2607.16117","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16117","created_at":"2026-07-20T02:19:34Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16117v1","created_at":"2026-07-20T02:19:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16117","created_at":"2026-07-20T02:19:34Z"},{"alias_kind":"pith_short_12","alias_value":"VLJ5Y4F3FPA5","created_at":"2026-07-20T02:19:34Z"},{"alias_kind":"pith_short_16","alias_value":"VLJ5Y4F3FPA5LJNP","created_at":"2026-07-20T02:19:34Z"},{"alias_kind":"pith_short_8","alias_value":"VLJ5Y4F3","created_at":"2026-07-20T02:19:34Z"}],"graph_snapshots":[{"event_id":"sha256:a69e63898038d974f582e98617c90d52a28bba1703424ae02fbf9e657e0e4941","target":"graph","created_at":"2026-07-20T02:19:34Z","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/2607.16117/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models encode text as subword tokens, raw bytes, or rendered pixels, but these encodings are usually compared under modeling constraints that expose different amounts of linguistic content to models across different languages. We instead ask what each encoding preserves when both the content and the downstream capacity are controlled. Using verified parallel sentences across thirteen languages and five scripts, we compare tokens, bytes, and pixels through a shared bottleneck whose width is swept to trace rate-utility frontiers. This separates three quantities that are often conflated:","authors_text":"Desmond Elliott, Ingo Ziegler, Martin Krebs","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-17T16:55:27Z","title":"Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16117","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":"sha256:98d5d3b517a2c5adf01358eb772bb42481d4595f55d7e8fdbeaa2edfb5857512","target":"record","created_at":"2026-07-20T02:19:34Z","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":"34ebff2d672bd251bbb92c7e4cf1302992e01528cc9e53b1ad77e129b65b70d7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-17T16:55:27Z","title_canon_sha256":"619ef7c0aeda9ee4089882217c6b15711752c95c0e3a6213b21ecabca86b6b7d"},"schema_version":"1.0","source":{"id":"2607.16117","kind":"arxiv","version":1}},"canonical_sha256":"aad3dc70bb2bc1d5a5af7658307e3a9683ce4b59c4969926b32c422792241af3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aad3dc70bb2bc1d5a5af7658307e3a9683ce4b59c4969926b32c422792241af3","first_computed_at":"2026-07-20T02:19:34.341061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-20T02:19:34.341061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8OYm42mc4cqorzKv2u6zmeyO67MzqpWqhCmo7XnKjot8RUHay33rCMNCBPK1P2PBsJlnCHXuxth+WosYNCuxAA==","signature_status":"signed_v1","signed_at":"2026-07-20T02:19:34.341906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16117","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98d5d3b517a2c5adf01358eb772bb42481d4595f55d7e8fdbeaa2edfb5857512","sha256:a69e63898038d974f582e98617c90d52a28bba1703424ae02fbf9e657e0e4941","sha256:34c31bda8111a53437d5506bd8566cac78f71dfae656b6b9d8f351857c4af8e1"],"state_sha256":"40381b96797121230db8ea08ac74ddbff6d949d2dcbc2416f854f40f6fe7cc3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DG8oYVvsspz3secCLmMtL19mdBTfNFH1df5ITImFDzpHTfnOu2w8DP7tAVWlaXtMMpSVSPUfXE4od2549W2KAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:48:52.548366Z","bundle_sha256":"65228425cc91026eae1084872bc8992351e354c7781177f3c6ce23a333f7f968"}}