{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DPN3QAYP3CD33MLUJRJQG7HIGY","short_pith_number":"pith:DPN3QAYP","canonical_record":{"source":{"id":"2606.06088","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T12:26:19Z","cross_cats_sorted":[],"title_canon_sha256":"e190d6afe4b9b3848130b5794efa0d24b5868f82e82abb6c9de1d900f30eb897","abstract_canon_sha256":"7c9b12f3f42c86f80ba947a30cc1b7aadaf0c7a8a22152d8e4c2742488d0f47e"},"schema_version":"1.0"},"canonical_sha256":"1bdbb8030fd887bdb1744c53037ce8363fa8e17edc9c1e9078fd2d622aa9c0b5","source":{"kind":"arxiv","id":"2606.06088","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06088","created_at":"2026-06-05T01:15:32Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06088v1","created_at":"2026-06-05T01:15:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06088","created_at":"2026-06-05T01:15:32Z"},{"alias_kind":"pith_short_12","alias_value":"DPN3QAYP3CD3","created_at":"2026-06-05T01:15:32Z"},{"alias_kind":"pith_short_16","alias_value":"DPN3QAYP3CD33MLU","created_at":"2026-06-05T01:15:32Z"},{"alias_kind":"pith_short_8","alias_value":"DPN3QAYP","created_at":"2026-06-05T01:15:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DPN3QAYP3CD33MLUJRJQG7HIGY","target":"record","payload":{"canonical_record":{"source":{"id":"2606.06088","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T12:26:19Z","cross_cats_sorted":[],"title_canon_sha256":"e190d6afe4b9b3848130b5794efa0d24b5868f82e82abb6c9de1d900f30eb897","abstract_canon_sha256":"7c9b12f3f42c86f80ba947a30cc1b7aadaf0c7a8a22152d8e4c2742488d0f47e"},"schema_version":"1.0"},"canonical_sha256":"1bdbb8030fd887bdb1744c53037ce8363fa8e17edc9c1e9078fd2d622aa9c0b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:32.890874Z","signature_b64":"kyCtYAxUqXFe3BOUXRXes5fjR0+qBLZRWIrVxxR8m/gvghr1LXGk1fU3I9EsQtaBT4om4K24RpCO2DwP4r5zCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bdbb8030fd887bdb1744c53037ce8363fa8e17edc9c1e9078fd2d622aa9c0b5","last_reissued_at":"2026-06-05T01:15:32.890203Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:32.890203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.06088","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":"2026-06-05T01:15:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E1K4T77JqeTuXgJR5T1kWI2dRHmHePSyrxKDfcdf2vb4XH7xjubebdfTQtztImq2PpZiRVseA5eHf9jdmcJhAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T14:35:33.566397Z"},"content_sha256":"951b4ec4d042fe893d0321976bb062f9c0490c27bae97fe044c00f9062dad0da","schema_version":"1.0","event_id":"sha256:951b4ec4d042fe893d0321976bb062f9c0490c27bae97fe044c00f9062dad0da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DPN3QAYP3CD33MLUJRJQG7HIGY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CHALIS: A Challenge Dataset for Language Identification in Difficult Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jind\\v{r}ich Libovick\\'y, Michal Tich\\'y","submitted_at":"2026-06-04T12:26:19Z","abstract_excerpt":"We present CHALIS (Challenging Language Identification Samples), a new benchmark dataset explicitly designed to address difficult cases in language identification: cousin languages and orthographic noise. Our dataset has two parts: First, we collected sentences shared across mutually intelligible language pairs (Czech/Slovak, Spanish/Catalan, Portuguese/Galician, Danish/Norwegian). The second part tests for orthography noise: we transliterate text across multiple scripts, remove diacritics, simulate homoglyph attacks, and use Internet slang. We evaluate four widely used language identification"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06088","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/2606.06088/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":"2026-06-05T01:15:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k3HVxzAGyymwM3klA91G7mEEMKSurMQB5paqoBX05Yo1zF1D4gPR6NqM2SjNrzAJsWwfVnDFqfyraUkbMo1rCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T14:35:33.566791Z"},"content_sha256":"7a6b498073b1f30917645b081d486775e0b5f95f851079715f65b47ee482b19f","schema_version":"1.0","event_id":"sha256:7a6b498073b1f30917645b081d486775e0b5f95f851079715f65b47ee482b19f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DPN3QAYP3CD33MLUJRJQG7HIGY/bundle.json","state_url":"https://pith.science/pith/DPN3QAYP3CD33MLUJRJQG7HIGY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DPN3QAYP3CD33MLUJRJQG7HIGY/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":"2026-06-09T14:35:33Z","links":{"resolver":"https://pith.science/pith/DPN3QAYP3CD33MLUJRJQG7HIGY","bundle":"https://pith.science/pith/DPN3QAYP3CD33MLUJRJQG7HIGY/bundle.json","state":"https://pith.science/pith/DPN3QAYP3CD33MLUJRJQG7HIGY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DPN3QAYP3CD33MLUJRJQG7HIGY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DPN3QAYP3CD33MLUJRJQG7HIGY","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":"7c9b12f3f42c86f80ba947a30cc1b7aadaf0c7a8a22152d8e4c2742488d0f47e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T12:26:19Z","title_canon_sha256":"e190d6afe4b9b3848130b5794efa0d24b5868f82e82abb6c9de1d900f30eb897"},"schema_version":"1.0","source":{"id":"2606.06088","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06088","created_at":"2026-06-05T01:15:32Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06088v1","created_at":"2026-06-05T01:15:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06088","created_at":"2026-06-05T01:15:32Z"},{"alias_kind":"pith_short_12","alias_value":"DPN3QAYP3CD3","created_at":"2026-06-05T01:15:32Z"},{"alias_kind":"pith_short_16","alias_value":"DPN3QAYP3CD33MLU","created_at":"2026-06-05T01:15:32Z"},{"alias_kind":"pith_short_8","alias_value":"DPN3QAYP","created_at":"2026-06-05T01:15:32Z"}],"graph_snapshots":[{"event_id":"sha256:7a6b498073b1f30917645b081d486775e0b5f95f851079715f65b47ee482b19f","target":"graph","created_at":"2026-06-05T01:15:32Z","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/2606.06088/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present CHALIS (Challenging Language Identification Samples), a new benchmark dataset explicitly designed to address difficult cases in language identification: cousin languages and orthographic noise. Our dataset has two parts: First, we collected sentences shared across mutually intelligible language pairs (Czech/Slovak, Spanish/Catalan, Portuguese/Galician, Danish/Norwegian). The second part tests for orthography noise: we transliterate text across multiple scripts, remove diacritics, simulate homoglyph attacks, and use Internet slang. We evaluate four widely used language identification","authors_text":"Jind\\v{r}ich Libovick\\'y, Michal Tich\\'y","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T12:26:19Z","title":"CHALIS: A Challenge Dataset for Language Identification in Difficult Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06088","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":"sha256:951b4ec4d042fe893d0321976bb062f9c0490c27bae97fe044c00f9062dad0da","target":"record","created_at":"2026-06-05T01:15:32Z","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":"7c9b12f3f42c86f80ba947a30cc1b7aadaf0c7a8a22152d8e4c2742488d0f47e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T12:26:19Z","title_canon_sha256":"e190d6afe4b9b3848130b5794efa0d24b5868f82e82abb6c9de1d900f30eb897"},"schema_version":"1.0","source":{"id":"2606.06088","kind":"arxiv","version":1}},"canonical_sha256":"1bdbb8030fd887bdb1744c53037ce8363fa8e17edc9c1e9078fd2d622aa9c0b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bdbb8030fd887bdb1744c53037ce8363fa8e17edc9c1e9078fd2d622aa9c0b5","first_computed_at":"2026-06-05T01:15:32.890203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:32.890203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kyCtYAxUqXFe3BOUXRXes5fjR0+qBLZRWIrVxxR8m/gvghr1LXGk1fU3I9EsQtaBT4om4K24RpCO2DwP4r5zCQ==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:32.890874Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06088","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:951b4ec4d042fe893d0321976bb062f9c0490c27bae97fe044c00f9062dad0da","sha256:7a6b498073b1f30917645b081d486775e0b5f95f851079715f65b47ee482b19f"],"state_sha256":"3c33c683500a639db9c1369055721d6c401f226d166c7af016cbfe026f784287"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ACx/obApxBLpjmeusBLld6BRvcqsmhjStcN7Wml2lLbjhKxiN2ES5sGEqvIVjYfyphi0KzAr1I10sV0ZTAXrBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T14:35:33.569147Z","bundle_sha256":"68c3b488dfac951447f45c959e298d611859eb7361d6f35e02a9160202a9c78d"}}