{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:UGDO5LDNPBMG6HCAMJOMDBPDPC","short_pith_number":"pith:UGDO5LDN","canonical_record":{"source":{"id":"2004.02929","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-06T18:41:43Z","cross_cats_sorted":[],"title_canon_sha256":"9600d73fc0e40b608f171fa6fa5ce822e5f1479295e7bee0aba0da021cf59314","abstract_canon_sha256":"4e180fcfb46da23d71e21f2c9e7dacd3c7ad6da5751c6a81b99bf7624437d327"},"schema_version":"1.0"},"canonical_sha256":"a186eeac6d78586f1c40625cc185e378b66aaeff842dacd148f3cb3deddd6492","source":{"kind":"arxiv","id":"2004.02929","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.02929","created_at":"2026-07-05T00:53:21Z"},{"alias_kind":"arxiv_version","alias_value":"2004.02929v1","created_at":"2026-07-05T00:53:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02929","created_at":"2026-07-05T00:53:21Z"},{"alias_kind":"pith_short_12","alias_value":"UGDO5LDNPBMG","created_at":"2026-07-05T00:53:21Z"},{"alias_kind":"pith_short_16","alias_value":"UGDO5LDNPBMG6HCA","created_at":"2026-07-05T00:53:21Z"},{"alias_kind":"pith_short_8","alias_value":"UGDO5LDN","created_at":"2026-07-05T00:53:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:UGDO5LDNPBMG6HCAMJOMDBPDPC","target":"record","payload":{"canonical_record":{"source":{"id":"2004.02929","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-06T18:41:43Z","cross_cats_sorted":[],"title_canon_sha256":"9600d73fc0e40b608f171fa6fa5ce822e5f1479295e7bee0aba0da021cf59314","abstract_canon_sha256":"4e180fcfb46da23d71e21f2c9e7dacd3c7ad6da5751c6a81b99bf7624437d327"},"schema_version":"1.0"},"canonical_sha256":"a186eeac6d78586f1c40625cc185e378b66aaeff842dacd148f3cb3deddd6492","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:21.649471Z","signature_b64":"NLPI7UP185/m3lYcdNpRB5yWzXhL20G0L3lQHNyvH8cSJ1T54N2iKzvf222lPtxyh2K207qdpztlHZS2KniiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a186eeac6d78586f1c40625cc185e378b66aaeff842dacd148f3cb3deddd6492","last_reissued_at":"2026-07-05T00:53:21.649069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:21.649069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.02929","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":"2026-07-05T00:53:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ocXpQ/Ju++58iG9onn+q3GH37x0RqwtvvBUyEgNYg6eghbPyROdJ0ctwBHpUlszQctsLs1n6ZYhKQhs/lkpjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T15:34:09.572049Z"},"content_sha256":"8b2f50b4df72a6522e280e5e5e375fa7c481f7cce0a093b43923e7fa4c66845f","schema_version":"1.0","event_id":"sha256:8b2f50b4df72a6522e280e5e5e375fa7c481f7cce0a093b43923e7fa4c66845f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:UGDO5LDNPBMG6HCAMJOMDBPDPC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Annotated Corpus of Emerging Anglicisms in Spanish Newspaper Headlines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Elena \\'Alvarez-Mellado","submitted_at":"2020-04-06T18:41:43Z","abstract_excerpt":"The extraction of anglicisms (lexical borrowings from English) is relevant both for lexicographic purposes and for NLP downstream tasks. We introduce a corpus of European Spanish newspaper headlines annotated with anglicisms and a baseline model for anglicism extraction. In this paper we present: (1) a corpus of 21,570 newspaper headlines written in European Spanish annotated with emergent anglicisms and (2) a conditional random field baseline model with handcrafted features for anglicism extraction. We present the newspaper headlines corpus, describe the annotation tagset and guidelines and i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02929","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/2004.02929/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":"2026-07-05T00:53:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"asDQnN8sNoYA0wrfgU9OCBzsR/n074HOfeamrwklV//ZSbZuVTZEfb0LQeeRab7G3jlCDUUqzfpkpuySWCNpBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T15:34:09.572380Z"},"content_sha256":"d19e7fa59eb5d4b29a2542dff777edfb5b49a988f1d049717ff0174a553dc437","schema_version":"1.0","event_id":"sha256:d19e7fa59eb5d4b29a2542dff777edfb5b49a988f1d049717ff0174a553dc437"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UGDO5LDNPBMG6HCAMJOMDBPDPC/bundle.json","state_url":"https://pith.science/pith/UGDO5LDNPBMG6HCAMJOMDBPDPC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UGDO5LDNPBMG6HCAMJOMDBPDPC/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":"2026-08-20T15:34:09Z","links":{"resolver":"https://pith.science/pith/UGDO5LDNPBMG6HCAMJOMDBPDPC","bundle":"https://pith.science/pith/UGDO5LDNPBMG6HCAMJOMDBPDPC/bundle.json","state":"https://pith.science/pith/UGDO5LDNPBMG6HCAMJOMDBPDPC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UGDO5LDNPBMG6HCAMJOMDBPDPC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UGDO5LDNPBMG6HCAMJOMDBPDPC","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":"4e180fcfb46da23d71e21f2c9e7dacd3c7ad6da5751c6a81b99bf7624437d327","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-06T18:41:43Z","title_canon_sha256":"9600d73fc0e40b608f171fa6fa5ce822e5f1479295e7bee0aba0da021cf59314"},"schema_version":"1.0","source":{"id":"2004.02929","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.02929","created_at":"2026-07-05T00:53:21Z"},{"alias_kind":"arxiv_version","alias_value":"2004.02929v1","created_at":"2026-07-05T00:53:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02929","created_at":"2026-07-05T00:53:21Z"},{"alias_kind":"pith_short_12","alias_value":"UGDO5LDNPBMG","created_at":"2026-07-05T00:53:21Z"},{"alias_kind":"pith_short_16","alias_value":"UGDO5LDNPBMG6HCA","created_at":"2026-07-05T00:53:21Z"},{"alias_kind":"pith_short_8","alias_value":"UGDO5LDN","created_at":"2026-07-05T00:53:21Z"}],"graph_snapshots":[{"event_id":"sha256:d19e7fa59eb5d4b29a2542dff777edfb5b49a988f1d049717ff0174a553dc437","target":"graph","created_at":"2026-07-05T00:53:21Z","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/2004.02929/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The extraction of anglicisms (lexical borrowings from English) is relevant both for lexicographic purposes and for NLP downstream tasks. We introduce a corpus of European Spanish newspaper headlines annotated with anglicisms and a baseline model for anglicism extraction. In this paper we present: (1) a corpus of 21,570 newspaper headlines written in European Spanish annotated with emergent anglicisms and (2) a conditional random field baseline model with handcrafted features for anglicism extraction. We present the newspaper headlines corpus, describe the annotation tagset and guidelines and i","authors_text":"Elena \\'Alvarez-Mellado","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-06T18:41:43Z","title":"An Annotated Corpus of Emerging Anglicisms in Spanish Newspaper Headlines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02929","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":"sha256:8b2f50b4df72a6522e280e5e5e375fa7c481f7cce0a093b43923e7fa4c66845f","target":"record","created_at":"2026-07-05T00:53:21Z","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":"4e180fcfb46da23d71e21f2c9e7dacd3c7ad6da5751c6a81b99bf7624437d327","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-06T18:41:43Z","title_canon_sha256":"9600d73fc0e40b608f171fa6fa5ce822e5f1479295e7bee0aba0da021cf59314"},"schema_version":"1.0","source":{"id":"2004.02929","kind":"arxiv","version":1}},"canonical_sha256":"a186eeac6d78586f1c40625cc185e378b66aaeff842dacd148f3cb3deddd6492","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a186eeac6d78586f1c40625cc185e378b66aaeff842dacd148f3cb3deddd6492","first_computed_at":"2026-07-05T00:53:21.649069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:53:21.649069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NLPI7UP185/m3lYcdNpRB5yWzXhL20G0L3lQHNyvH8cSJ1T54N2iKzvf222lPtxyh2K207qdpztlHZS2KniiDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:53:21.649471Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.02929","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b2f50b4df72a6522e280e5e5e375fa7c481f7cce0a093b43923e7fa4c66845f","sha256:d19e7fa59eb5d4b29a2542dff777edfb5b49a988f1d049717ff0174a553dc437"],"state_sha256":"1a36a5f79662963e9552b26d0b3a302ce4795029834a8e6f409cdccfa7f2e4b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vxcva5ddJMondnxMBvt6R968UcZP+YCdTCqu/w5H33VuiDQ2uJV28d3dSAWil4FNbWNOhU3EP93idpUaa5LVCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T15:34:09.576019Z","bundle_sha256":"911d3f9f4538682651d9ab309b018566339d4fca0864e013fd936f05baf843d7"}}