{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MX37NWQR6CTCTI3HHLVEMH2565","short_pith_number":"pith:MX37NWQR","canonical_record":{"source":{"id":"2111.09453","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-18T00:10:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e52945e963519395f10cf79d0ade3dc9e48d1d80850854f2bd3f54205f7adab6","abstract_canon_sha256":"33bccfb3b4f14b68be409175f8a8b41aac53cbfe182615c5e6dda12126486a2d"},"schema_version":"1.0"},"canonical_sha256":"65f7f6da11f0a629a3673aea461f5df77a58c2bc15cbba787f4b5e489bf6931f","source":{"kind":"arxiv","id":"2111.09453","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.09453","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"arxiv_version","alias_value":"2111.09453v3","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09453","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_12","alias_value":"MX37NWQR6CTC","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_16","alias_value":"MX37NWQR6CTCTI3H","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_8","alias_value":"MX37NWQR","created_at":"2026-07-05T04:20:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MX37NWQR6CTCTI3HHLVEMH2565","target":"record","payload":{"canonical_record":{"source":{"id":"2111.09453","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-18T00:10:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e52945e963519395f10cf79d0ade3dc9e48d1d80850854f2bd3f54205f7adab6","abstract_canon_sha256":"33bccfb3b4f14b68be409175f8a8b41aac53cbfe182615c5e6dda12126486a2d"},"schema_version":"1.0"},"canonical_sha256":"65f7f6da11f0a629a3673aea461f5df77a58c2bc15cbba787f4b5e489bf6931f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:17.014769Z","signature_b64":"ryG6eEP3RpoUmjm1G+enNnd4IdZOiWkdlqEWGI05KaadSo5v3koviW5eBx9FKkR217hAJ83H2F6Uta2Ig8fGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65f7f6da11f0a629a3673aea461f5df77a58c2bc15cbba787f4b5e489bf6931f","last_reissued_at":"2026-07-05T04:20:17.014268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:17.014268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.09453","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:20:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G8kpmXTeIvB8K8n7RhF9oPhGX1eGp7/kf9w71IpLxigE9fDNpRAQbD2yWhN2imEEwXWbfj9ipGRcU9z3rZOQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T11:33:48.877726Z"},"content_sha256":"243ab67491d5fdb3b1748831ff3f3856f90bfd7633f955b9eea0c67857d8ea42","schema_version":"1.0","event_id":"sha256:243ab67491d5fdb3b1748831ff3f3856f90bfd7633f955b9eea0c67857d8ea42"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MX37NWQR6CTCTI3HHLVEMH2565","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RoBERTuito: a pre-trained language model for social media text in Spanish","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dami\\'an A. Furman, Franco Luque, Juan Manuel P\\'erez, Laura Alonso Alemany","submitted_at":"2021-11-18T00:10:25Z","abstract_excerpt":"Since BERT appeared, Transformer language models and transfer learning have become state-of-the-art for Natural Language Understanding tasks. Recently, some works geared towards pre-training specially-crafted models for particular domains, such as scientific papers, medical documents, user-generated texts, among others. These domain-specific models have been shown to improve performance significantly in most tasks. However, for languages other than English such models are not widely available.\n  In this work, we present RoBERTuito, a pre-trained language model for user-generated text in Spanis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09453","kind":"arxiv","version":3},"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/2111.09453/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":"2026-07-05T04:20:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kgST/xxTAtTTYmO4h9lrNJOgG1JakDfYVHKy3f+OQpUWkZL5iBSjmbFTU1ASz/p4qsMubbKZMJQr2Swhb7S+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T11:33:48.878255Z"},"content_sha256":"f8614ee9d2da302f90ccc4b6e80638e7b855e8c1dc362b90f3497f7d97d60e0e","schema_version":"1.0","event_id":"sha256:f8614ee9d2da302f90ccc4b6e80638e7b855e8c1dc362b90f3497f7d97d60e0e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MX37NWQR6CTCTI3HHLVEMH2565/bundle.json","state_url":"https://pith.science/pith/MX37NWQR6CTCTI3HHLVEMH2565/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MX37NWQR6CTCTI3HHLVEMH2565/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":"2026-08-12T11:33:48Z","links":{"resolver":"https://pith.science/pith/MX37NWQR6CTCTI3HHLVEMH2565","bundle":"https://pith.science/pith/MX37NWQR6CTCTI3HHLVEMH2565/bundle.json","state":"https://pith.science/pith/MX37NWQR6CTCTI3HHLVEMH2565/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MX37NWQR6CTCTI3HHLVEMH2565/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MX37NWQR6CTCTI3HHLVEMH2565","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":"33bccfb3b4f14b68be409175f8a8b41aac53cbfe182615c5e6dda12126486a2d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-18T00:10:25Z","title_canon_sha256":"e52945e963519395f10cf79d0ade3dc9e48d1d80850854f2bd3f54205f7adab6"},"schema_version":"1.0","source":{"id":"2111.09453","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.09453","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"arxiv_version","alias_value":"2111.09453v3","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09453","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_12","alias_value":"MX37NWQR6CTC","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_16","alias_value":"MX37NWQR6CTCTI3H","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_8","alias_value":"MX37NWQR","created_at":"2026-07-05T04:20:17Z"}],"graph_snapshots":[{"event_id":"sha256:f8614ee9d2da302f90ccc4b6e80638e7b855e8c1dc362b90f3497f7d97d60e0e","target":"graph","created_at":"2026-07-05T04:20:17Z","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/2111.09453/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Since BERT appeared, Transformer language models and transfer learning have become state-of-the-art for Natural Language Understanding tasks. Recently, some works geared towards pre-training specially-crafted models for particular domains, such as scientific papers, medical documents, user-generated texts, among others. These domain-specific models have been shown to improve performance significantly in most tasks. However, for languages other than English such models are not widely available.\n  In this work, we present RoBERTuito, a pre-trained language model for user-generated text in Spanis","authors_text":"Dami\\'an A. Furman, Franco Luque, Juan Manuel P\\'erez, Laura Alonso Alemany","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-18T00:10:25Z","title":"RoBERTuito: a pre-trained language model for social media text in Spanish"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09453","kind":"arxiv","version":3},"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":"sha256:243ab67491d5fdb3b1748831ff3f3856f90bfd7633f955b9eea0c67857d8ea42","target":"record","created_at":"2026-07-05T04:20:17Z","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":"33bccfb3b4f14b68be409175f8a8b41aac53cbfe182615c5e6dda12126486a2d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-18T00:10:25Z","title_canon_sha256":"e52945e963519395f10cf79d0ade3dc9e48d1d80850854f2bd3f54205f7adab6"},"schema_version":"1.0","source":{"id":"2111.09453","kind":"arxiv","version":3}},"canonical_sha256":"65f7f6da11f0a629a3673aea461f5df77a58c2bc15cbba787f4b5e489bf6931f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65f7f6da11f0a629a3673aea461f5df77a58c2bc15cbba787f4b5e489bf6931f","first_computed_at":"2026-07-05T04:20:17.014268Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:20:17.014268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ryG6eEP3RpoUmjm1G+enNnd4IdZOiWkdlqEWGI05KaadSo5v3koviW5eBx9FKkR217hAJ83H2F6Uta2Ig8fGDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:20:17.014769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.09453","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:243ab67491d5fdb3b1748831ff3f3856f90bfd7633f955b9eea0c67857d8ea42","sha256:f8614ee9d2da302f90ccc4b6e80638e7b855e8c1dc362b90f3497f7d97d60e0e"],"state_sha256":"a7828cb55f9884b02c8d9824f9ac12895476f51a118fb76343a3c2722232684e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/WzN/fbu6Yhxh+F5kL6YA9E/FtW67xlpYMO8JsFuoHlgI5RskxdDI7toJODtVbJXPl6A2G4MlBnQAJdUOXtwCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T11:33:48.883240Z","bundle_sha256":"7720fa4cf8690df9f4c968f737a2b3765f0624a38d8e365f4f58ffff181ef038"}}