{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SGRGSYOPDEWZKN63EWX7CIY7M5","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":"dc51c5a8cc30833cf6ef211b689748af4674413b1cb367fb6f9fdbaa4390641e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T08:56:47Z","title_canon_sha256":"76d8822a23b9f36a7fb0db2ceae9c04102997ab283923f9c937c834e81a544f7"},"schema_version":"1.0","source":{"id":"2311.07161","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07161","created_at":"2026-07-05T07:12:08Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07161v1","created_at":"2026-07-05T07:12:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07161","created_at":"2026-07-05T07:12:08Z"},{"alias_kind":"pith_short_12","alias_value":"SGRGSYOPDEWZ","created_at":"2026-07-05T07:12:08Z"},{"alias_kind":"pith_short_16","alias_value":"SGRGSYOPDEWZKN63","created_at":"2026-07-05T07:12:08Z"},{"alias_kind":"pith_short_8","alias_value":"SGRGSYOP","created_at":"2026-07-05T07:12:08Z"}],"graph_snapshots":[{"event_id":"sha256:c38413cce4496d8c865584f7a20a837cdaea00a1000781bba293c10019420111","target":"graph","created_at":"2026-07-05T07:12:08Z","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/2311.07161/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the development of a Named Entity Recognition (NER) dataset for Tagalog. This corpus helps fill the resource gap present in Philippine languages today, where NER resources are scarce. The texts were obtained from a pretraining corpora containing news reports, and were labeled by native speakers in an iterative fashion. The resulting dataset contains ~7.8k documents across three entity types: Person, Organization, and Location. The inter-annotator agreement, as measured by Cohen's $\\kappa$, is 0.81. We also conducted extensive empirical evaluation of state-of-the-art methods across s","authors_text":"Lester James V. Miranda","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T08:56:47Z","title":"Developing a Named Entity Recognition Dataset for Tagalog"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07161","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":"sha256:723c22e508f61fd985ae7a20607c4c834bd7f90706946d758d11313da7711395","target":"record","created_at":"2026-07-05T07:12:08Z","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":"dc51c5a8cc30833cf6ef211b689748af4674413b1cb367fb6f9fdbaa4390641e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T08:56:47Z","title_canon_sha256":"76d8822a23b9f36a7fb0db2ceae9c04102997ab283923f9c937c834e81a544f7"},"schema_version":"1.0","source":{"id":"2311.07161","kind":"arxiv","version":1}},"canonical_sha256":"91a26961cf192d9537db25aff1231f674aef1106bf496ec962a355bf4e34b68c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91a26961cf192d9537db25aff1231f674aef1106bf496ec962a355bf4e34b68c","first_computed_at":"2026-07-05T07:12:08.722209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:12:08.722209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"31VGsxyuyRa3g8QRhysDrmI9nClvtfCSy23DdJ5b44xcn6dNuQ6uGPOw9gmFS1+EBCFnCMgYJH5XQrZjrjVGBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:12:08.722592Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.07161","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:723c22e508f61fd985ae7a20607c4c834bd7f90706946d758d11313da7711395","sha256:c38413cce4496d8c865584f7a20a837cdaea00a1000781bba293c10019420111"],"state_sha256":"8c71cb5d8ff6fc17887f2acefcb43f509eda4d1e6543a8eb86d95ad9000babd4"}