{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:UM3ELP5JPFOUI4ZLEHFIFH7HXF","short_pith_number":"pith:UM3ELP5J","canonical_record":{"source":{"id":"2109.07765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-16T07:22:28Z","cross_cats_sorted":[],"title_canon_sha256":"27fae5621c89c0fb5305ee5e5880516c0233fd57d5ff031d7fa32403c3f7225d","abstract_canon_sha256":"d9ccd7d40202168806f24cb7c84d9abb2fa27230b33ead78daefe73b037273bb"},"schema_version":"1.0"},"canonical_sha256":"a33645bfa9795d44732b21ca829fe7b9676b19660ed5f5e38909166abe066349","source":{"kind":"arxiv","id":"2109.07765","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.07765","created_at":"2026-07-05T03:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2109.07765v1","created_at":"2026-07-05T03:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.07765","created_at":"2026-07-05T03:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"UM3ELP5JPFOU","created_at":"2026-07-05T03:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"UM3ELP5JPFOUI4ZL","created_at":"2026-07-05T03:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"UM3ELP5J","created_at":"2026-07-05T03:15:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:UM3ELP5JPFOUI4ZLEHFIFH7HXF","target":"record","payload":{"canonical_record":{"source":{"id":"2109.07765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-16T07:22:28Z","cross_cats_sorted":[],"title_canon_sha256":"27fae5621c89c0fb5305ee5e5880516c0233fd57d5ff031d7fa32403c3f7225d","abstract_canon_sha256":"d9ccd7d40202168806f24cb7c84d9abb2fa27230b33ead78daefe73b037273bb"},"schema_version":"1.0"},"canonical_sha256":"a33645bfa9795d44732b21ca829fe7b9676b19660ed5f5e38909166abe066349","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:00.955568Z","signature_b64":"RKpL7DNpeoq7llv3On9MpvMwPKfwFVDd/JNzXzu86rSbFzdX9WxihVeveb/iAFrXzkRXR/TWnsh26kcvbztcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a33645bfa9795d44732b21ca829fe7b9676b19660ed5f5e38909166abe066349","last_reissued_at":"2026-07-05T03:15:00.955156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:00.955156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.07765","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":"2026-07-05T03:15:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"93S6yuQC8walBZC0FfEeNztIYDCqUnAafMtUNlw7Sl9NzpCv48aMCeAAyoTlh4wYthetUGLJ0dlCop2SOoETBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T04:09:48.245101Z"},"content_sha256":"d85c5606799c5f60f34896e80720d55ab03d82dbb2e719bf0ba7bcb7e6f5b386","schema_version":"1.0","event_id":"sha256:d85c5606799c5f60f34896e80720d55ab03d82dbb2e719bf0ba7bcb7e6f5b386"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:UM3ELP5JPFOUI4ZLEHFIFH7HXF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spanish Biomedical Crawled Corpus: A Large, Diverse Dataset for Spanish Biomedical Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aitor Gonzalez-Agirre, Asier Guti\\'errez-Fandi\\~no, Casimiro Pio Carrino, Jordi Armengol-Estap\\'e, Marta Villegas, Martin Krallinger, Ona de Gibert Bonet","submitted_at":"2021-09-16T07:22:28Z","abstract_excerpt":"We introduce CoWeSe (the Corpus Web Salud Espa\\~nol), the largest Spanish biomedical corpus to date, consisting of 4.5GB (about 750M tokens) of clean plain text. CoWeSe is the result of a massive crawler on 3000 Spanish domains executed in 2020. The corpus is openly available and already preprocessed. CoWeSe is an important resource for biomedical and health NLP in Spanish and has already been employed to train domain-specific language models and to produce word embbedings. We released the CoWeSe corpus under a Creative Commons Attribution 4.0 International license, both in Zenodo (\\url{https:"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.07765","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/2109.07765/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":"2026-07-05T03:15:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"28REThpDZVvI626unSMdCNf5+VwGCM6HTiPIvwo2A5Xe/hIjfvAzNiN4OJecfKrQVdHpi5aEHX+f1PZW1CS3Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T04:09:48.245494Z"},"content_sha256":"02b012e84a3afd9aeb608e375ab568c86f5883e529d4a727f0d197170a379687","schema_version":"1.0","event_id":"sha256:02b012e84a3afd9aeb608e375ab568c86f5883e529d4a727f0d197170a379687"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UM3ELP5JPFOUI4ZLEHFIFH7HXF/bundle.json","state_url":"https://pith.science/pith/UM3ELP5JPFOUI4ZLEHFIFH7HXF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UM3ELP5JPFOUI4ZLEHFIFH7HXF/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":"2026-07-18T04:09:48Z","links":{"resolver":"https://pith.science/pith/UM3ELP5JPFOUI4ZLEHFIFH7HXF","bundle":"https://pith.science/pith/UM3ELP5JPFOUI4ZLEHFIFH7HXF/bundle.json","state":"https://pith.science/pith/UM3ELP5JPFOUI4ZLEHFIFH7HXF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UM3ELP5JPFOUI4ZLEHFIFH7HXF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UM3ELP5JPFOUI4ZLEHFIFH7HXF","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":"d9ccd7d40202168806f24cb7c84d9abb2fa27230b33ead78daefe73b037273bb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-16T07:22:28Z","title_canon_sha256":"27fae5621c89c0fb5305ee5e5880516c0233fd57d5ff031d7fa32403c3f7225d"},"schema_version":"1.0","source":{"id":"2109.07765","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.07765","created_at":"2026-07-05T03:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2109.07765v1","created_at":"2026-07-05T03:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.07765","created_at":"2026-07-05T03:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"UM3ELP5JPFOU","created_at":"2026-07-05T03:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"UM3ELP5JPFOUI4ZL","created_at":"2026-07-05T03:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"UM3ELP5J","created_at":"2026-07-05T03:15:00Z"}],"graph_snapshots":[{"event_id":"sha256:02b012e84a3afd9aeb608e375ab568c86f5883e529d4a727f0d197170a379687","target":"graph","created_at":"2026-07-05T03:15:00Z","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/2109.07765/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce CoWeSe (the Corpus Web Salud Espa\\~nol), the largest Spanish biomedical corpus to date, consisting of 4.5GB (about 750M tokens) of clean plain text. CoWeSe is the result of a massive crawler on 3000 Spanish domains executed in 2020. The corpus is openly available and already preprocessed. CoWeSe is an important resource for biomedical and health NLP in Spanish and has already been employed to train domain-specific language models and to produce word embbedings. We released the CoWeSe corpus under a Creative Commons Attribution 4.0 International license, both in Zenodo (\\url{https:","authors_text":"Aitor Gonzalez-Agirre, Asier Guti\\'errez-Fandi\\~no, Casimiro Pio Carrino, Jordi Armengol-Estap\\'e, Marta Villegas, Martin Krallinger, Ona de Gibert Bonet","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-16T07:22:28Z","title":"Spanish Biomedical Crawled Corpus: A Large, Diverse Dataset for Spanish Biomedical Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.07765","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:d85c5606799c5f60f34896e80720d55ab03d82dbb2e719bf0ba7bcb7e6f5b386","target":"record","created_at":"2026-07-05T03:15:00Z","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":"d9ccd7d40202168806f24cb7c84d9abb2fa27230b33ead78daefe73b037273bb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-16T07:22:28Z","title_canon_sha256":"27fae5621c89c0fb5305ee5e5880516c0233fd57d5ff031d7fa32403c3f7225d"},"schema_version":"1.0","source":{"id":"2109.07765","kind":"arxiv","version":1}},"canonical_sha256":"a33645bfa9795d44732b21ca829fe7b9676b19660ed5f5e38909166abe066349","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a33645bfa9795d44732b21ca829fe7b9676b19660ed5f5e38909166abe066349","first_computed_at":"2026-07-05T03:15:00.955156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:00.955156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RKpL7DNpeoq7llv3On9MpvMwPKfwFVDd/JNzXzu86rSbFzdX9WxihVeveb/iAFrXzkRXR/TWnsh26kcvbztcBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:00.955568Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.07765","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d85c5606799c5f60f34896e80720d55ab03d82dbb2e719bf0ba7bcb7e6f5b386","sha256:02b012e84a3afd9aeb608e375ab568c86f5883e529d4a727f0d197170a379687"],"state_sha256":"489e8012e672879364f3c92af0dc1bbf159760ec9cb002c923466fe4f45b0763"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LJluV/9TKOfUfGZc6IZq3IbSpdIQJOWj5YzoTIOiAOrpAqNxNVypng4GoA3zrH4hLdwO6ILj5lypId4qOfU/AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T04:09:48.247691Z","bundle_sha256":"3a80291ebd0937ad6b242b234188354881c172192f7c852a4e62c26ddc6d760c"}}