{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PS7PSZVQ4LJDJYOMNVAYAEMK3M","short_pith_number":"pith:PS7PSZVQ","canonical_record":{"source":{"id":"2404.08345","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-12T09:21:29Z","cross_cats_sorted":[],"title_canon_sha256":"decc22157a70dcaa17e0ceb2a01e434b9e78b7c26bb49fec603603ddc5b63242","abstract_canon_sha256":"ec22c9159a4f45d13b016fc7914da479e286001b9f99beebf68f0a313bb725f4"},"schema_version":"1.0"},"canonical_sha256":"7cbef966b0e2d234e1cc6d4180118adb21d23b922a1b87d78f45f375f62fd22f","source":{"kind":"arxiv","id":"2404.08345","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.08345","created_at":"2026-07-05T08:07:20Z"},{"alias_kind":"arxiv_version","alias_value":"2404.08345v1","created_at":"2026-07-05T08:07:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08345","created_at":"2026-07-05T08:07:20Z"},{"alias_kind":"pith_short_12","alias_value":"PS7PSZVQ4LJD","created_at":"2026-07-05T08:07:20Z"},{"alias_kind":"pith_short_16","alias_value":"PS7PSZVQ4LJDJYOM","created_at":"2026-07-05T08:07:20Z"},{"alias_kind":"pith_short_8","alias_value":"PS7PSZVQ","created_at":"2026-07-05T08:07:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PS7PSZVQ4LJDJYOMNVAYAEMK3M","target":"record","payload":{"canonical_record":{"source":{"id":"2404.08345","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-12T09:21:29Z","cross_cats_sorted":[],"title_canon_sha256":"decc22157a70dcaa17e0ceb2a01e434b9e78b7c26bb49fec603603ddc5b63242","abstract_canon_sha256":"ec22c9159a4f45d13b016fc7914da479e286001b9f99beebf68f0a313bb725f4"},"schema_version":"1.0"},"canonical_sha256":"7cbef966b0e2d234e1cc6d4180118adb21d23b922a1b87d78f45f375f62fd22f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:20.892868Z","signature_b64":"G/qwCSw31UgZIHgEiUckS2/8VSurM3N3OHImvRDXmgNZtURI16ox4G9HoZUxn1KmmV2bf8n7AfKWdyBzI3FCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cbef966b0e2d234e1cc6d4180118adb21d23b922a1b87d78f45f375f62fd22f","last_reissued_at":"2026-07-05T08:07:20.892510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:20.892510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.08345","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":"2026-07-05T08:07:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DzpBPI+jbD216rmfhmKpvBPXSTtLykxbMzPdoaAZ8PHChaZHGOP6Lp2t1gzzKrbd52mCpnj9CQN75qDDBY6sAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T23:09:46.743087Z"},"content_sha256":"fd32be6fa843054406315b5b68dc3ab39ec78c59a6078fb02a65418cdc7c4efb","schema_version":"1.0","event_id":"sha256:fd32be6fa843054406315b5b68dc3ab39ec78c59a6078fb02a65418cdc7c4efb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PS7PSZVQ4LJDJYOMNVAYAEMK3M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FastSpell: the LangId Magic Spell","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gema Ram\\'irez-S\\'anchez, Jaume Zaragoza-Bernabeu, Marta Ba\\~n\\'on, Sergio Ortiz-Rojas","submitted_at":"2024-04-12T09:21:29Z","abstract_excerpt":"Language identification is a crucial component in the automated production of language resources, particularly in multilingual and big data contexts. However, commonly used language identifiers struggle to differentiate between similar or closely-related languages. This paper introduces FastSpell, a language identifier that combines fastText (a pre-trained language identifier tool) and Hunspell (a spell checker) with the aim of having a refined second-opinion before deciding which language should be assigned to a text. We provide a description of the FastSpell algorithm along with an explanati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08345","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/2404.08345/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":"2026-07-05T08:07:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xWmUs3N+sgcBuzYrbKr5y80Ciot5ugzb7GDRzJPphzYm9s5YrxnDo5rwoFfRaleGkBkOBgeTFe9iTNwOr2iXAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T23:09:46.743993Z"},"content_sha256":"b15dea15713ed7f796e1235370578008b9fdc43948ecadf36205697d024af2b3","schema_version":"1.0","event_id":"sha256:b15dea15713ed7f796e1235370578008b9fdc43948ecadf36205697d024af2b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PS7PSZVQ4LJDJYOMNVAYAEMK3M/bundle.json","state_url":"https://pith.science/pith/PS7PSZVQ4LJDJYOMNVAYAEMK3M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PS7PSZVQ4LJDJYOMNVAYAEMK3M/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":"2026-08-13T23:09:46Z","links":{"resolver":"https://pith.science/pith/PS7PSZVQ4LJDJYOMNVAYAEMK3M","bundle":"https://pith.science/pith/PS7PSZVQ4LJDJYOMNVAYAEMK3M/bundle.json","state":"https://pith.science/pith/PS7PSZVQ4LJDJYOMNVAYAEMK3M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PS7PSZVQ4LJDJYOMNVAYAEMK3M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PS7PSZVQ4LJDJYOMNVAYAEMK3M","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":"ec22c9159a4f45d13b016fc7914da479e286001b9f99beebf68f0a313bb725f4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-12T09:21:29Z","title_canon_sha256":"decc22157a70dcaa17e0ceb2a01e434b9e78b7c26bb49fec603603ddc5b63242"},"schema_version":"1.0","source":{"id":"2404.08345","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.08345","created_at":"2026-07-05T08:07:20Z"},{"alias_kind":"arxiv_version","alias_value":"2404.08345v1","created_at":"2026-07-05T08:07:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08345","created_at":"2026-07-05T08:07:20Z"},{"alias_kind":"pith_short_12","alias_value":"PS7PSZVQ4LJD","created_at":"2026-07-05T08:07:20Z"},{"alias_kind":"pith_short_16","alias_value":"PS7PSZVQ4LJDJYOM","created_at":"2026-07-05T08:07:20Z"},{"alias_kind":"pith_short_8","alias_value":"PS7PSZVQ","created_at":"2026-07-05T08:07:20Z"}],"graph_snapshots":[{"event_id":"sha256:b15dea15713ed7f796e1235370578008b9fdc43948ecadf36205697d024af2b3","target":"graph","created_at":"2026-07-05T08:07:20Z","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/2404.08345/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language identification is a crucial component in the automated production of language resources, particularly in multilingual and big data contexts. However, commonly used language identifiers struggle to differentiate between similar or closely-related languages. This paper introduces FastSpell, a language identifier that combines fastText (a pre-trained language identifier tool) and Hunspell (a spell checker) with the aim of having a refined second-opinion before deciding which language should be assigned to a text. We provide a description of the FastSpell algorithm along with an explanati","authors_text":"Gema Ram\\'irez-S\\'anchez, Jaume Zaragoza-Bernabeu, Marta Ba\\~n\\'on, Sergio Ortiz-Rojas","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-12T09:21:29Z","title":"FastSpell: the LangId Magic Spell"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08345","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:fd32be6fa843054406315b5b68dc3ab39ec78c59a6078fb02a65418cdc7c4efb","target":"record","created_at":"2026-07-05T08:07:20Z","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":"ec22c9159a4f45d13b016fc7914da479e286001b9f99beebf68f0a313bb725f4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-12T09:21:29Z","title_canon_sha256":"decc22157a70dcaa17e0ceb2a01e434b9e78b7c26bb49fec603603ddc5b63242"},"schema_version":"1.0","source":{"id":"2404.08345","kind":"arxiv","version":1}},"canonical_sha256":"7cbef966b0e2d234e1cc6d4180118adb21d23b922a1b87d78f45f375f62fd22f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cbef966b0e2d234e1cc6d4180118adb21d23b922a1b87d78f45f375f62fd22f","first_computed_at":"2026-07-05T08:07:20.892510Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:20.892510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G/qwCSw31UgZIHgEiUckS2/8VSurM3N3OHImvRDXmgNZtURI16ox4G9HoZUxn1KmmV2bf8n7AfKWdyBzI3FCDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:20.892868Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.08345","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd32be6fa843054406315b5b68dc3ab39ec78c59a6078fb02a65418cdc7c4efb","sha256:b15dea15713ed7f796e1235370578008b9fdc43948ecadf36205697d024af2b3"],"state_sha256":"c362f95fe180eb284ae9b88765af130c06bf2e1d015268639661ab89642739dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LRkvnwWl7WUSVburuMMPoCDlV2dCIpeTIQkejiTz3Cjj7rw8Janb3NADmrWyTQ45aDhrww3A6AUEdaLbYrgmBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T23:09:46.767040Z","bundle_sha256":"a55b76d6e4f25b82ee3f87d38d05d6a0a4a0fdfe2eace021a915eaf83014fcde"}}