{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UUEN4VCJ7ZUZIOTEB5JLKYH2FV","short_pith_number":"pith:UUEN4VCJ","canonical_record":{"source":{"id":"2507.07824","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T14:53:59Z","cross_cats_sorted":[],"title_canon_sha256":"2079961cf0740df10ce0aeedc4394822cad46b81a478c84d312cb6896735104b","abstract_canon_sha256":"a24685ad19b22c034c2301736dc5f95880073365939e68d7333f5f0a6f4d7f0a"},"schema_version":"1.0"},"canonical_sha256":"a508de5449fe69943a640f52b560fa2d792d86bc2a43fec7064aea5647af3fab","source":{"kind":"arxiv","id":"2507.07824","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07824","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07824v1","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07824","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"pith_short_12","alias_value":"UUEN4VCJ7ZUZ","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"pith_short_16","alias_value":"UUEN4VCJ7ZUZIOTE","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"pith_short_8","alias_value":"UUEN4VCJ","created_at":"2026-07-05T11:35:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UUEN4VCJ7ZUZIOTEB5JLKYH2FV","target":"record","payload":{"canonical_record":{"source":{"id":"2507.07824","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T14:53:59Z","cross_cats_sorted":[],"title_canon_sha256":"2079961cf0740df10ce0aeedc4394822cad46b81a478c84d312cb6896735104b","abstract_canon_sha256":"a24685ad19b22c034c2301736dc5f95880073365939e68d7333f5f0a6f4d7f0a"},"schema_version":"1.0"},"canonical_sha256":"a508de5449fe69943a640f52b560fa2d792d86bc2a43fec7064aea5647af3fab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:05.709346Z","signature_b64":"YYSCL0cXPSRn4SM/i+YlKFgMBZ7gHvrSuCtZnFdFSQYSrE0lS0vUQX9gzfhFnGmAqp1eFwaRBKHW7YoSN1GwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a508de5449fe69943a640f52b560fa2d792d86bc2a43fec7064aea5647af3fab","last_reissued_at":"2026-07-05T11:35:05.708822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:05.708822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.07824","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":"2026-07-05T11:35:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ua+yL45IWIxR9N4/1fCJaxM+GqRsySxV0v0DI10HHdgL1DpJfiXB70EPHMw/+kIEFHBy7LH641k+kJxl3UmfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:45:16.425661Z"},"content_sha256":"cf53f748d4e20e5649c20d98b3f5c961d4cb0a95e291cd47a6024e82fb9d210d","schema_version":"1.0","event_id":"sha256:cf53f748d4e20e5649c20d98b3f5c961d4cb0a95e291cd47a6024e82fb9d210d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UUEN4VCJ7ZUZIOTEB5JLKYH2FV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conditional Unigram Tokenization with Parallel Data","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gianluca Vico, Jind\\v{r}inch Libovick\\'y","submitted_at":"2025-07-10T14:53:59Z","abstract_excerpt":"We introduce conditional unigram tokenization, a novel approach that extends unigram tokenization by conditioning target token probabilities on source-language tokens from parallel data. Given a fixed source tokenizer, our method learns a target tokenizer that maximizes cross-lingual semantic alignment. We evaluate our tokenizer on four language pairs across different families and resource levels, examining intrinsic properties and downstream performance on machine translation and language modeling. While our conditional tokenizer maintains comparable statistical properties to standard unigram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07824","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/2507.07824/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":"2026-07-05T11:35:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4SXb7KOHI0qi8r8DE32fBiRwfMTbgRNqdt1vTH/rzRs52+58gpnZVYigMObh9kFXUo83J1uVccC1f5CUAmfXBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:45:16.426159Z"},"content_sha256":"5804b9b4df14a0cbe39c0d7f935b063e39dddebb8db746c79fd9cf3135b138aa","schema_version":"1.0","event_id":"sha256:5804b9b4df14a0cbe39c0d7f935b063e39dddebb8db746c79fd9cf3135b138aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UUEN4VCJ7ZUZIOTEB5JLKYH2FV/bundle.json","state_url":"https://pith.science/pith/UUEN4VCJ7ZUZIOTEB5JLKYH2FV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UUEN4VCJ7ZUZIOTEB5JLKYH2FV/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":"2026-08-07T15:45:16Z","links":{"resolver":"https://pith.science/pith/UUEN4VCJ7ZUZIOTEB5JLKYH2FV","bundle":"https://pith.science/pith/UUEN4VCJ7ZUZIOTEB5JLKYH2FV/bundle.json","state":"https://pith.science/pith/UUEN4VCJ7ZUZIOTEB5JLKYH2FV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UUEN4VCJ7ZUZIOTEB5JLKYH2FV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UUEN4VCJ7ZUZIOTEB5JLKYH2FV","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":"a24685ad19b22c034c2301736dc5f95880073365939e68d7333f5f0a6f4d7f0a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T14:53:59Z","title_canon_sha256":"2079961cf0740df10ce0aeedc4394822cad46b81a478c84d312cb6896735104b"},"schema_version":"1.0","source":{"id":"2507.07824","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07824","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07824v1","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07824","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"pith_short_12","alias_value":"UUEN4VCJ7ZUZ","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"pith_short_16","alias_value":"UUEN4VCJ7ZUZIOTE","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"pith_short_8","alias_value":"UUEN4VCJ","created_at":"2026-07-05T11:35:05Z"}],"graph_snapshots":[{"event_id":"sha256:5804b9b4df14a0cbe39c0d7f935b063e39dddebb8db746c79fd9cf3135b138aa","target":"graph","created_at":"2026-07-05T11:35:05Z","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/2507.07824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce conditional unigram tokenization, a novel approach that extends unigram tokenization by conditioning target token probabilities on source-language tokens from parallel data. Given a fixed source tokenizer, our method learns a target tokenizer that maximizes cross-lingual semantic alignment. We evaluate our tokenizer on four language pairs across different families and resource levels, examining intrinsic properties and downstream performance on machine translation and language modeling. While our conditional tokenizer maintains comparable statistical properties to standard unigram","authors_text":"Gianluca Vico, Jind\\v{r}inch Libovick\\'y","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T14:53:59Z","title":"Conditional Unigram Tokenization with Parallel Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07824","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:cf53f748d4e20e5649c20d98b3f5c961d4cb0a95e291cd47a6024e82fb9d210d","target":"record","created_at":"2026-07-05T11:35:05Z","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":"a24685ad19b22c034c2301736dc5f95880073365939e68d7333f5f0a6f4d7f0a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T14:53:59Z","title_canon_sha256":"2079961cf0740df10ce0aeedc4394822cad46b81a478c84d312cb6896735104b"},"schema_version":"1.0","source":{"id":"2507.07824","kind":"arxiv","version":1}},"canonical_sha256":"a508de5449fe69943a640f52b560fa2d792d86bc2a43fec7064aea5647af3fab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a508de5449fe69943a640f52b560fa2d792d86bc2a43fec7064aea5647af3fab","first_computed_at":"2026-07-05T11:35:05.708822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:05.708822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YYSCL0cXPSRn4SM/i+YlKFgMBZ7gHvrSuCtZnFdFSQYSrE0lS0vUQX9gzfhFnGmAqp1eFwaRBKHW7YoSN1GwAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:05.709346Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07824","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf53f748d4e20e5649c20d98b3f5c961d4cb0a95e291cd47a6024e82fb9d210d","sha256:5804b9b4df14a0cbe39c0d7f935b063e39dddebb8db746c79fd9cf3135b138aa"],"state_sha256":"657eadee364dbfa5d382243bd0c9ba650dbc21e2c7ca0c8056fb15a21bcd7985"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"To/lGjQTuhJhBQxDkxQyaLnZGmOy+yPdzq/pYwSb/g5kwsAWXhpo+h2gmFxnO+27gdsdx0v3bBlnslRHH7wuBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:45:16.448483Z","bundle_sha256":"c5d36e8324d36134178fb376d5795b71320d0ad6284bf91e60e985b6ae696c08"}}