{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3VAD5VONTFZ2TGSBTH4FFX7PYG","short_pith_number":"pith:3VAD5VON","canonical_record":{"source":{"id":"2107.07253","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-15T11:23:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0edd69eea4066f9c40d5c6e9f9965c7aa89a648eab0709fd9434449f50f7dedb","abstract_canon_sha256":"f48de4bb36d7e91d23afc3e6b63f62b97537b06278834ef0208f7ef76aff7dfc"},"schema_version":"1.0"},"canonical_sha256":"dd403ed5cd9973a99a4199f852dfefc18034e139d1bb4bc0a6712b75d193ed8f","source":{"kind":"arxiv","id":"2107.07253","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.07253","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"arxiv_version","alias_value":"2107.07253v5","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.07253","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"pith_short_12","alias_value":"3VAD5VONTFZ2","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"pith_short_16","alias_value":"3VAD5VONTFZ2TGSB","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"pith_short_8","alias_value":"3VAD5VON","created_at":"2026-07-05T04:11:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3VAD5VONTFZ2TGSBTH4FFX7PYG","target":"record","payload":{"canonical_record":{"source":{"id":"2107.07253","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-15T11:23:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0edd69eea4066f9c40d5c6e9f9965c7aa89a648eab0709fd9434449f50f7dedb","abstract_canon_sha256":"f48de4bb36d7e91d23afc3e6b63f62b97537b06278834ef0208f7ef76aff7dfc"},"schema_version":"1.0"},"canonical_sha256":"dd403ed5cd9973a99a4199f852dfefc18034e139d1bb4bc0a6712b75d193ed8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:25.384634Z","signature_b64":"3PXDy+0qCF5HiMvBW01N7GdYsX8fuQq0n10xE12G1Oa/OSIcxwKw55R7lKfrViFpIYFRxBjlndmzx0mBhawaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd403ed5cd9973a99a4199f852dfefc18034e139d1bb4bc0a6712b75d193ed8f","last_reissued_at":"2026-07-05T04:11:25.384248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:25.384248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.07253","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:11:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BYzCwxHIEJokL04YAkqotaMia47c6Sdd5tDTwk/2wUFJWlV74Iutdghg4ZzLRB3GxzBMm5Jvh95Plb6zi6i8Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T18:58:12.904180Z"},"content_sha256":"37d661ad4de636963bdeb997c136186a9ed283a7f7b719fb7f8d31d47fe8b0ad","schema_version":"1.0","event_id":"sha256:37d661ad4de636963bdeb997c136186a9ed283a7f7b719fb7f8d31d47fe8b0ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3VAD5VONTFZ2TGSBTH4FFX7PYG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MarIA: Spanish Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aitor Gonzalez-Agirre, Asier Guti\\'errez-Fandi\\~no, Carlos Rodriguez-Penagos, Carme Armentano-Oller, Casimiro Pio Carrino, Joan Llop-Palao, Joaqu\\'in Silveira-Ocampo, Jordi Armengol-Estap\\'e, Marc P\\`amies, Marta Villegas","submitted_at":"2021-07-15T11:23:05Z","abstract_excerpt":"This work presents MarIA, a family of Spanish language models and associated resources made available to the industry and the research community. Currently, MarIA includes RoBERTa-base, RoBERTa-large, GPT2 and GPT2-large Spanish language models, which can arguably be presented as the largest and most proficient language models in Spanish. The models were pretrained using a massive corpus of 570GB of clean and deduplicated texts with 135 billion words extracted from the Spanish Web Archive crawled by the National Library of Spain between 2009 and 2019. We assessed the performance of the models "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.07253","kind":"arxiv","version":5},"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/2107.07253/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":"2026-07-05T04:11:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5jqdNttC+mMYfiCoZV+97xJGGtVeu3FyqxuO88PsUMUzmodDdYebRHAsdNRGZtZBwwW9olpytVPnbVY9HsSlBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T18:58:12.904575Z"},"content_sha256":"d38f9f912b1c072cb0759e1e9c5ac18c19b8ce26654992d89a97c03d3b25bb26","schema_version":"1.0","event_id":"sha256:d38f9f912b1c072cb0759e1e9c5ac18c19b8ce26654992d89a97c03d3b25bb26"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3VAD5VONTFZ2TGSBTH4FFX7PYG/bundle.json","state_url":"https://pith.science/pith/3VAD5VONTFZ2TGSBTH4FFX7PYG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3VAD5VONTFZ2TGSBTH4FFX7PYG/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":"2026-07-11T18:58:12Z","links":{"resolver":"https://pith.science/pith/3VAD5VONTFZ2TGSBTH4FFX7PYG","bundle":"https://pith.science/pith/3VAD5VONTFZ2TGSBTH4FFX7PYG/bundle.json","state":"https://pith.science/pith/3VAD5VONTFZ2TGSBTH4FFX7PYG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3VAD5VONTFZ2TGSBTH4FFX7PYG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3VAD5VONTFZ2TGSBTH4FFX7PYG","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":"f48de4bb36d7e91d23afc3e6b63f62b97537b06278834ef0208f7ef76aff7dfc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-15T11:23:05Z","title_canon_sha256":"0edd69eea4066f9c40d5c6e9f9965c7aa89a648eab0709fd9434449f50f7dedb"},"schema_version":"1.0","source":{"id":"2107.07253","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.07253","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"arxiv_version","alias_value":"2107.07253v5","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.07253","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"pith_short_12","alias_value":"3VAD5VONTFZ2","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"pith_short_16","alias_value":"3VAD5VONTFZ2TGSB","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"pith_short_8","alias_value":"3VAD5VON","created_at":"2026-07-05T04:11:25Z"}],"graph_snapshots":[{"event_id":"sha256:d38f9f912b1c072cb0759e1e9c5ac18c19b8ce26654992d89a97c03d3b25bb26","target":"graph","created_at":"2026-07-05T04:11:25Z","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/2107.07253/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work presents MarIA, a family of Spanish language models and associated resources made available to the industry and the research community. Currently, MarIA includes RoBERTa-base, RoBERTa-large, GPT2 and GPT2-large Spanish language models, which can arguably be presented as the largest and most proficient language models in Spanish. The models were pretrained using a massive corpus of 570GB of clean and deduplicated texts with 135 billion words extracted from the Spanish Web Archive crawled by the National Library of Spain between 2009 and 2019. We assessed the performance of the models ","authors_text":"Aitor Gonzalez-Agirre, Asier Guti\\'errez-Fandi\\~no, Carlos Rodriguez-Penagos, Carme Armentano-Oller, Casimiro Pio Carrino, Joan Llop-Palao, Joaqu\\'in Silveira-Ocampo, Jordi Armengol-Estap\\'e, Marc P\\`amies, Marta Villegas","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-15T11:23:05Z","title":"MarIA: Spanish Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.07253","kind":"arxiv","version":5},"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":"sha256:37d661ad4de636963bdeb997c136186a9ed283a7f7b719fb7f8d31d47fe8b0ad","target":"record","created_at":"2026-07-05T04:11:25Z","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":"f48de4bb36d7e91d23afc3e6b63f62b97537b06278834ef0208f7ef76aff7dfc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-15T11:23:05Z","title_canon_sha256":"0edd69eea4066f9c40d5c6e9f9965c7aa89a648eab0709fd9434449f50f7dedb"},"schema_version":"1.0","source":{"id":"2107.07253","kind":"arxiv","version":5}},"canonical_sha256":"dd403ed5cd9973a99a4199f852dfefc18034e139d1bb4bc0a6712b75d193ed8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd403ed5cd9973a99a4199f852dfefc18034e139d1bb4bc0a6712b75d193ed8f","first_computed_at":"2026-07-05T04:11:25.384248Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:11:25.384248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3PXDy+0qCF5HiMvBW01N7GdYsX8fuQq0n10xE12G1Oa/OSIcxwKw55R7lKfrViFpIYFRxBjlndmzx0mBhawaBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:11:25.384634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.07253","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37d661ad4de636963bdeb997c136186a9ed283a7f7b719fb7f8d31d47fe8b0ad","sha256:d38f9f912b1c072cb0759e1e9c5ac18c19b8ce26654992d89a97c03d3b25bb26"],"state_sha256":"ceb15ed8548aee1589935b6b2e1f546ca4d0097af8e501896547632925124140"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zXHpKnj1GaWWRkC5QZDqlLLKaFeNwbWWJ28D7POPV8LLh9T2Kci+SU9U2syGU9DwxzJ9/tB/dvJCDxvDlfXzDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T18:58:12.906834Z","bundle_sha256":"31eb8c23fac76ed13ac6eeb11b9abfc0457ab73038a48b070d651a35917aac09"}}