{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DPJBQGP7IAZNGJBIVCXOALP2VU","short_pith_number":"pith:DPJBQGP7","canonical_record":{"source":{"id":"2506.03149","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T17:59:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"94bcea0c91351337a1a823d179313b29d41c6d7ae9a9b1b40cad595ae3c397bd","abstract_canon_sha256":"eaab52ca775cb3ab00fdfdf70f83d84eeab1661316f183e2254635a4a2cd7344"},"schema_version":"1.0"},"canonical_sha256":"1bd21819ff4032d32428a8aee02dfaad0cb841499a6074ab12bdf01d7a3fab19","source":{"kind":"arxiv","id":"2506.03149","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03149","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03149v1","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03149","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"pith_short_12","alias_value":"DPJBQGP7IAZN","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"pith_short_16","alias_value":"DPJBQGP7IAZNGJBI","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"pith_short_8","alias_value":"DPJBQGP7","created_at":"2026-07-05T11:15:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DPJBQGP7IAZNGJBIVCXOALP2VU","target":"record","payload":{"canonical_record":{"source":{"id":"2506.03149","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T17:59:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"94bcea0c91351337a1a823d179313b29d41c6d7ae9a9b1b40cad595ae3c397bd","abstract_canon_sha256":"eaab52ca775cb3ab00fdfdf70f83d84eeab1661316f183e2254635a4a2cd7344"},"schema_version":"1.0"},"canonical_sha256":"1bd21819ff4032d32428a8aee02dfaad0cb841499a6074ab12bdf01d7a3fab19","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:15.732023Z","signature_b64":"VPtIy//iiwYxVilKfq9x04w7HMuHHUr80R25cNz+TiWs7b6jU6tcnWxboUkzQmDzu/bYAxqgRH3yaEiMyk4KCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bd21819ff4032d32428a8aee02dfaad0cb841499a6074ab12bdf01d7a3fab19","last_reissued_at":"2026-07-05T11:15:15.731538Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:15.731538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.03149","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":"2026-07-05T11:15:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WnCFTH7JmkPjNkI7HwLRed+EXAjPmr/nOU5KF6dRlcIb0O4EgdupcteRZc3nIyEjSYFAzgbnIw5XYjGIKPrYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:40:05.360202Z"},"content_sha256":"894781f6856f3547cfcec234b60c99ba07b0060682ae628e066d248b485b71bc","schema_version":"1.0","event_id":"sha256:894781f6856f3547cfcec234b60c99ba07b0060682ae628e066d248b485b71bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DPJBQGP7IAZNGJBIVCXOALP2VU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Causal Estimation of Tokenisation Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andreas Vlachos, Clara Meister, Pietro Lesci, Thomas Hofmann, Tiago Pimentel","submitted_at":"2025-06-03T17:59:47Z","abstract_excerpt":"Modern language models are typically trained over subword sequences, but ultimately define probabilities over character-strings. Ideally, the choice of the tokeniser -- which maps character-strings to subwords -- should not affect the probability assigned to the underlying character-string; in practice, it does. We define this mismatch as tokenisation bias. In this work, we quantify one particular type of tokenisation bias: the effect of including or not a subword (e.g., $\\langle hello \\rangle$) in a tokeniser's vocabulary on the probability a trained model assigns to the corresponding charact"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03149","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/2506.03149/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":"2026-07-05T11:15:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+ZjP7iUx3jmONy32s9h7lYADN9seJoYCO4pIqKaaC3QOZFRXpxxKy42FMgzh1YYouVu7zGZgCocLMdetCwG7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:40:05.360696Z"},"content_sha256":"bd9ed15e6f7b852e21211b9df1b301c680105e0c61f1f08978f0acf88372960b","schema_version":"1.0","event_id":"sha256:bd9ed15e6f7b852e21211b9df1b301c680105e0c61f1f08978f0acf88372960b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DPJBQGP7IAZNGJBIVCXOALP2VU/bundle.json","state_url":"https://pith.science/pith/DPJBQGP7IAZNGJBIVCXOALP2VU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DPJBQGP7IAZNGJBIVCXOALP2VU/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":"2026-08-08T06:40:05Z","links":{"resolver":"https://pith.science/pith/DPJBQGP7IAZNGJBIVCXOALP2VU","bundle":"https://pith.science/pith/DPJBQGP7IAZNGJBIVCXOALP2VU/bundle.json","state":"https://pith.science/pith/DPJBQGP7IAZNGJBIVCXOALP2VU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DPJBQGP7IAZNGJBIVCXOALP2VU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DPJBQGP7IAZNGJBIVCXOALP2VU","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":"eaab52ca775cb3ab00fdfdf70f83d84eeab1661316f183e2254635a4a2cd7344","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T17:59:47Z","title_canon_sha256":"94bcea0c91351337a1a823d179313b29d41c6d7ae9a9b1b40cad595ae3c397bd"},"schema_version":"1.0","source":{"id":"2506.03149","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03149","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03149v1","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03149","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"pith_short_12","alias_value":"DPJBQGP7IAZN","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"pith_short_16","alias_value":"DPJBQGP7IAZNGJBI","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"pith_short_8","alias_value":"DPJBQGP7","created_at":"2026-07-05T11:15:15Z"}],"graph_snapshots":[{"event_id":"sha256:bd9ed15e6f7b852e21211b9df1b301c680105e0c61f1f08978f0acf88372960b","target":"graph","created_at":"2026-07-05T11:15:15Z","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/2506.03149/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern language models are typically trained over subword sequences, but ultimately define probabilities over character-strings. Ideally, the choice of the tokeniser -- which maps character-strings to subwords -- should not affect the probability assigned to the underlying character-string; in practice, it does. We define this mismatch as tokenisation bias. In this work, we quantify one particular type of tokenisation bias: the effect of including or not a subword (e.g., $\\langle hello \\rangle$) in a tokeniser's vocabulary on the probability a trained model assigns to the corresponding charact","authors_text":"Andreas Vlachos, Clara Meister, Pietro Lesci, Thomas Hofmann, Tiago Pimentel","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T17:59:47Z","title":"Causal Estimation of Tokenisation Bias"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03149","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":"sha256:894781f6856f3547cfcec234b60c99ba07b0060682ae628e066d248b485b71bc","target":"record","created_at":"2026-07-05T11:15:15Z","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":"eaab52ca775cb3ab00fdfdf70f83d84eeab1661316f183e2254635a4a2cd7344","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T17:59:47Z","title_canon_sha256":"94bcea0c91351337a1a823d179313b29d41c6d7ae9a9b1b40cad595ae3c397bd"},"schema_version":"1.0","source":{"id":"2506.03149","kind":"arxiv","version":1}},"canonical_sha256":"1bd21819ff4032d32428a8aee02dfaad0cb841499a6074ab12bdf01d7a3fab19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bd21819ff4032d32428a8aee02dfaad0cb841499a6074ab12bdf01d7a3fab19","first_computed_at":"2026-07-05T11:15:15.731538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:15.731538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VPtIy//iiwYxVilKfq9x04w7HMuHHUr80R25cNz+TiWs7b6jU6tcnWxboUkzQmDzu/bYAxqgRH3yaEiMyk4KCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:15.732023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03149","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:894781f6856f3547cfcec234b60c99ba07b0060682ae628e066d248b485b71bc","sha256:bd9ed15e6f7b852e21211b9df1b301c680105e0c61f1f08978f0acf88372960b"],"state_sha256":"db4df952a1a604114c3e987255718556506c26f33eb6ebc76ccd93e38cfdb35a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8yGSvdi5mk0EHSWRb1ZupiOv+7O/SQ0FVnw78gn6hk3031X70DNqJEkauzyk5k4jsvQWrnaFMwWDXmrEmHX+Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:40:05.364864Z","bundle_sha256":"4c6049a79d14e0d607953e8f68facdf6458d82e61bbd7b60933080887d8359a7"}}