{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:T2NW6BLO6NWDYZNKIE66MBBOMX","short_pith_number":"pith:T2NW6BLO","canonical_record":{"source":{"id":"2206.15147","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-30T09:29:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"82a658752e23bb1287392b22f4fb8ebe2bbd82ab1150679793747e4973c6d008","abstract_canon_sha256":"8847915a79047ac31197859afe91f4b4e8db7fb45057e608b189b514b5ec760c"},"schema_version":"1.0"},"canonical_sha256":"9e9b6f056ef36c3c65aa413de6042e65d2fe1f84f07bcd52bf14edfecb55d732","source":{"kind":"arxiv","id":"2206.15147","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.15147","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"arxiv_version","alias_value":"2206.15147v2","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15147","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"pith_short_12","alias_value":"T2NW6BLO6NWD","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"pith_short_16","alias_value":"T2NW6BLO6NWDYZNK","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"pith_short_8","alias_value":"T2NW6BLO","created_at":"2026-07-05T04:36:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:T2NW6BLO6NWDYZNKIE66MBBOMX","target":"record","payload":{"canonical_record":{"source":{"id":"2206.15147","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-30T09:29:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"82a658752e23bb1287392b22f4fb8ebe2bbd82ab1150679793747e4973c6d008","abstract_canon_sha256":"8847915a79047ac31197859afe91f4b4e8db7fb45057e608b189b514b5ec760c"},"schema_version":"1.0"},"canonical_sha256":"9e9b6f056ef36c3c65aa413de6042e65d2fe1f84f07bcd52bf14edfecb55d732","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:37.933022Z","signature_b64":"D+N6tsYL9ffgn3xPcqiCfezp2b6iulIUEl07y+Tgem6l3s3tMGfDrIDQrYFURpyhbzo0+ttjK6FHEVqxH6RqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e9b6f056ef36c3c65aa413de6042e65d2fe1f84f07bcd52bf14edfecb55d732","last_reissued_at":"2026-07-05T04:36:37.932523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:37.932523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.15147","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":"2026-07-05T04:36:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"18WiEs4whdL76Q0msYcd8YR4uz6IJm+IGxY4iy6TNbmI5XMAaR9Pf+Sp4rczCEVvNrhxj8nsHwAiHie+3p06Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T05:54:30.699370Z"},"content_sha256":"141aca19dec9ac6cb642c1cecf21ee818205508d7bcb9e5be9f10a8deb85dc6a","schema_version":"1.0","event_id":"sha256:141aca19dec9ac6cb642c1cecf21ee818205508d7bcb9e5be9f10a8deb85dc6a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:T2NW6BLO6NWDYZNKIE66MBBOMX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"esCorpius: A Massive Spanish Crawling Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Asier Guti\\'errez-Fandi\\~no, David Griol, David P\\'erez-Fern\\'andez, Jordi Armengol-Estap\\'e, Zoraida Callejas","submitted_at":"2022-06-30T09:29:18Z","abstract_excerpt":"In the recent years, transformer-based models have lead to significant advances in language modelling for natural language processing. However, they require a vast amount of data to be (pre-)trained and there is a lack of corpora in languages other than English. Recently, several initiatives have presented multilingual datasets obtained from automatic web crawling. However, the results in Spanish present important shortcomings, as they are either too small in comparison with other languages, or present a low quality derived from sub-optimal cleaning and deduplication. In this paper, we introdu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15147","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/2206.15147/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":"2026-07-05T04:36:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cxv9nmYYWpZ8AVsLKC02sEaP9Z48B54cpOlpv3CdtN/yYMljbx/GFmwaL85Qcd4/69roAjeOLbAzYNOAm7FJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T05:54:30.700002Z"},"content_sha256":"0c5433accec566fd3b16db17d4c9b7d68a93aa1bed4537c1ac5d03a545619d3a","schema_version":"1.0","event_id":"sha256:0c5433accec566fd3b16db17d4c9b7d68a93aa1bed4537c1ac5d03a545619d3a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T2NW6BLO6NWDYZNKIE66MBBOMX/bundle.json","state_url":"https://pith.science/pith/T2NW6BLO6NWDYZNKIE66MBBOMX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T2NW6BLO6NWDYZNKIE66MBBOMX/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":"2026-08-23T05:54:30Z","links":{"resolver":"https://pith.science/pith/T2NW6BLO6NWDYZNKIE66MBBOMX","bundle":"https://pith.science/pith/T2NW6BLO6NWDYZNKIE66MBBOMX/bundle.json","state":"https://pith.science/pith/T2NW6BLO6NWDYZNKIE66MBBOMX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T2NW6BLO6NWDYZNKIE66MBBOMX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:T2NW6BLO6NWDYZNKIE66MBBOMX","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":"8847915a79047ac31197859afe91f4b4e8db7fb45057e608b189b514b5ec760c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-30T09:29:18Z","title_canon_sha256":"82a658752e23bb1287392b22f4fb8ebe2bbd82ab1150679793747e4973c6d008"},"schema_version":"1.0","source":{"id":"2206.15147","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.15147","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"arxiv_version","alias_value":"2206.15147v2","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15147","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"pith_short_12","alias_value":"T2NW6BLO6NWD","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"pith_short_16","alias_value":"T2NW6BLO6NWDYZNK","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"pith_short_8","alias_value":"T2NW6BLO","created_at":"2026-07-05T04:36:37Z"}],"graph_snapshots":[{"event_id":"sha256:0c5433accec566fd3b16db17d4c9b7d68a93aa1bed4537c1ac5d03a545619d3a","target":"graph","created_at":"2026-07-05T04:36:37Z","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/2206.15147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the recent years, transformer-based models have lead to significant advances in language modelling for natural language processing. However, they require a vast amount of data to be (pre-)trained and there is a lack of corpora in languages other than English. Recently, several initiatives have presented multilingual datasets obtained from automatic web crawling. However, the results in Spanish present important shortcomings, as they are either too small in comparison with other languages, or present a low quality derived from sub-optimal cleaning and deduplication. In this paper, we introdu","authors_text":"Asier Guti\\'errez-Fandi\\~no, David Griol, David P\\'erez-Fern\\'andez, Jordi Armengol-Estap\\'e, Zoraida Callejas","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-30T09:29:18Z","title":"esCorpius: A Massive Spanish Crawling Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15147","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":"sha256:141aca19dec9ac6cb642c1cecf21ee818205508d7bcb9e5be9f10a8deb85dc6a","target":"record","created_at":"2026-07-05T04:36:37Z","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":"8847915a79047ac31197859afe91f4b4e8db7fb45057e608b189b514b5ec760c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-30T09:29:18Z","title_canon_sha256":"82a658752e23bb1287392b22f4fb8ebe2bbd82ab1150679793747e4973c6d008"},"schema_version":"1.0","source":{"id":"2206.15147","kind":"arxiv","version":2}},"canonical_sha256":"9e9b6f056ef36c3c65aa413de6042e65d2fe1f84f07bcd52bf14edfecb55d732","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e9b6f056ef36c3c65aa413de6042e65d2fe1f84f07bcd52bf14edfecb55d732","first_computed_at":"2026-07-05T04:36:37.932523Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:36:37.932523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D+N6tsYL9ffgn3xPcqiCfezp2b6iulIUEl07y+Tgem6l3s3tMGfDrIDQrYFURpyhbzo0+ttjK6FHEVqxH6RqDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:36:37.933022Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.15147","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:141aca19dec9ac6cb642c1cecf21ee818205508d7bcb9e5be9f10a8deb85dc6a","sha256:0c5433accec566fd3b16db17d4c9b7d68a93aa1bed4537c1ac5d03a545619d3a"],"state_sha256":"ce74791147aa0cc97074abb290a2587a312a91d9325805197f9d50e60ecfaac2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hm5068gMDfnmBTivQ4JuXE2OeyYgbUqh5WKI40dCqYwVTNj429Sho3kZe88UhNeXXV05JElxRRv0JM4JV6akBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T05:54:30.706244Z","bundle_sha256":"8e620597c700a7f797c3c7661631c2ef92cd1cb0547e57eae35c34ec9431a9d9"}}