{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OOCKTPTLBWUGCW4QQQLXDKLYBM","short_pith_number":"pith:OOCKTPTL","canonical_record":{"source":{"id":"2602.17655","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-19T18:58:39Z","cross_cats_sorted":[],"title_canon_sha256":"cfac3cac02070e899ab314812f3d2ada03b920019f38caaed920694ade7de773","abstract_canon_sha256":"28dd4e9e81c1ea84271dfac1d9209bd96d1d570af73ef1132724723ec1043bfb"},"schema_version":"1.0"},"canonical_sha256":"7384a9be6b0da8615b90841771a9780b0117623d41400860c3c7be5301d65536","source":{"kind":"arxiv","id":"2602.17655","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.17655","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"2602.17655v2","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17655","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"OOCKTPTLBWUG","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"pith_short_16","alias_value":"OOCKTPTLBWUGCW4Q","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"pith_short_8","alias_value":"OOCKTPTL","created_at":"2026-06-23T03:14:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OOCKTPTLBWUGCW4QQQLXDKLYBM","target":"record","payload":{"canonical_record":{"source":{"id":"2602.17655","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-19T18:58:39Z","cross_cats_sorted":[],"title_canon_sha256":"cfac3cac02070e899ab314812f3d2ada03b920019f38caaed920694ade7de773","abstract_canon_sha256":"28dd4e9e81c1ea84271dfac1d9209bd96d1d570af73ef1132724723ec1043bfb"},"schema_version":"1.0"},"canonical_sha256":"7384a9be6b0da8615b90841771a9780b0117623d41400860c3c7be5301d65536","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:28.498626Z","signature_b64":"vdGgke6PO7gUY/A7Whz1lvskCKmnVo0JYQWEx6SWyOVffDyeDdpw/+HUhAI7cl0fs6iwfeqtj6NMN7nHLR0YDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7384a9be6b0da8615b90841771a9780b0117623d41400860c3c7be5301d65536","last_reissued_at":"2026-06-23T03:14:28.498104Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:28.498104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.17655","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T03:14:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BC6wsm65WgtuF+PxdfAi1zxldkmve1hfEKPuUniQd+CUfEMaCcxJpSLoDOTGw3QqkeG8PvlXtE/9+NxHAgUeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T18:09:11.426034Z"},"content_sha256":"8bd44a3f84a1b6743625f7e4226f602ef714c8114e511ac01a6ed25eae0aac42","schema_version":"1.0","event_id":"sha256:8bd44a3f84a1b6743625f7e4226f602ef714c8114e511ac01a6ed25eae0aac42"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OOCKTPTLBWUGCW4QQQLXDKLYBM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Language is This? Ask Your Tokenizer","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmetcan Yavuz, Clara Meister, Pietro Lesci, Tiago Pimentel","submitted_at":"2026-02-19T18:58:39Z","abstract_excerpt":"Language Identification (LID) is an important component of many multilingual natural language processing pipelines, where it facilitates corpus curation, training data analysis, and cross-lingual evaluation of large language models. Despite near-perfect performance on high-resource languages, existing systems remain brittle in low-resource and closely related language settings. We introduce UniLID, a simple and efficient LID method based on the UnigramLM tokenization algorithm, leveraging its probabilistic framing, parameter estimation technique and inference strategy. In short, to predict a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.17655","kind":"arxiv","version":2},"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/2602.17655/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":"2026-06-23T03:14:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kw+bolBH6EB+tIaTTgN3Bi8aiuGiTEJWlx1xlm5tHLJeVRuiLa55LxBZD2YiyAMA53CribBq8z+q+W+Cizb0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T18:09:11.426633Z"},"content_sha256":"ace45f96efedc102d5ee09221a63c3e73d91d568257381a11a1df4fc4224e425","schema_version":"1.0","event_id":"sha256:ace45f96efedc102d5ee09221a63c3e73d91d568257381a11a1df4fc4224e425"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OOCKTPTLBWUGCW4QQQLXDKLYBM/bundle.json","state_url":"https://pith.science/pith/OOCKTPTLBWUGCW4QQQLXDKLYBM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OOCKTPTLBWUGCW4QQQLXDKLYBM/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":"2026-06-27T18:09:11Z","links":{"resolver":"https://pith.science/pith/OOCKTPTLBWUGCW4QQQLXDKLYBM","bundle":"https://pith.science/pith/OOCKTPTLBWUGCW4QQQLXDKLYBM/bundle.json","state":"https://pith.science/pith/OOCKTPTLBWUGCW4QQQLXDKLYBM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OOCKTPTLBWUGCW4QQQLXDKLYBM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OOCKTPTLBWUGCW4QQQLXDKLYBM","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":"28dd4e9e81c1ea84271dfac1d9209bd96d1d570af73ef1132724723ec1043bfb","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-19T18:58:39Z","title_canon_sha256":"cfac3cac02070e899ab314812f3d2ada03b920019f38caaed920694ade7de773"},"schema_version":"1.0","source":{"id":"2602.17655","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.17655","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"2602.17655v2","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17655","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"OOCKTPTLBWUG","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"pith_short_16","alias_value":"OOCKTPTLBWUGCW4Q","created_at":"2026-06-23T03:14:28Z"},{"alias_kind":"pith_short_8","alias_value":"OOCKTPTL","created_at":"2026-06-23T03:14:28Z"}],"graph_snapshots":[{"event_id":"sha256:ace45f96efedc102d5ee09221a63c3e73d91d568257381a11a1df4fc4224e425","target":"graph","created_at":"2026-06-23T03:14:28Z","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/2602.17655/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language Identification (LID) is an important component of many multilingual natural language processing pipelines, where it facilitates corpus curation, training data analysis, and cross-lingual evaluation of large language models. Despite near-perfect performance on high-resource languages, existing systems remain brittle in low-resource and closely related language settings. We introduce UniLID, a simple and efficient LID method based on the UnigramLM tokenization algorithm, leveraging its probabilistic framing, parameter estimation technique and inference strategy. In short, to predict a s","authors_text":"Ahmetcan Yavuz, Clara Meister, Pietro Lesci, Tiago Pimentel","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-19T18:58:39Z","title":"What Language is This? Ask Your Tokenizer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.17655","kind":"arxiv","version":2},"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":"sha256:8bd44a3f84a1b6743625f7e4226f602ef714c8114e511ac01a6ed25eae0aac42","target":"record","created_at":"2026-06-23T03:14:28Z","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":"28dd4e9e81c1ea84271dfac1d9209bd96d1d570af73ef1132724723ec1043bfb","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-19T18:58:39Z","title_canon_sha256":"cfac3cac02070e899ab314812f3d2ada03b920019f38caaed920694ade7de773"},"schema_version":"1.0","source":{"id":"2602.17655","kind":"arxiv","version":2}},"canonical_sha256":"7384a9be6b0da8615b90841771a9780b0117623d41400860c3c7be5301d65536","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7384a9be6b0da8615b90841771a9780b0117623d41400860c3c7be5301d65536","first_computed_at":"2026-06-23T03:14:28.498104Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:28.498104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vdGgke6PO7gUY/A7Whz1lvskCKmnVo0JYQWEx6SWyOVffDyeDdpw/+HUhAI7cl0fs6iwfeqtj6NMN7nHLR0YDQ==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:28.498626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.17655","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bd44a3f84a1b6743625f7e4226f602ef714c8114e511ac01a6ed25eae0aac42","sha256:ace45f96efedc102d5ee09221a63c3e73d91d568257381a11a1df4fc4224e425"],"state_sha256":"08a31f6f630182e8c64d14eeca4c3225fe8988b497056549b7e38c5a65be75b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y1H2Fq8i83VUqVxwxyPVghccQB+idGu2dmxOWpYEmVUgFGesrVdFa/lp5mz+bxGn8mMJh0cQMip+p7JKEobKAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T18:09:11.429255Z","bundle_sha256":"8b1241910745d63a44bdf67651418cc28c2c06e670384603b8ede7177c0ec456"}}