{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SGRGSYOPDEWZKN63EWX7CIY7M5","short_pith_number":"pith:SGRGSYOP","canonical_record":{"source":{"id":"2311.07161","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T08:56:47Z","cross_cats_sorted":[],"title_canon_sha256":"76d8822a23b9f36a7fb0db2ceae9c04102997ab283923f9c937c834e81a544f7","abstract_canon_sha256":"dc51c5a8cc30833cf6ef211b689748af4674413b1cb367fb6f9fdbaa4390641e"},"schema_version":"1.0"},"canonical_sha256":"91a26961cf192d9537db25aff1231f674aef1106bf496ec962a355bf4e34b68c","source":{"kind":"arxiv","id":"2311.07161","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SGRGSYOPDEWZKN63EWX7CIY7M5","target":"record","payload":{"canonical_record":{"source":{"id":"2311.07161","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T08:56:47Z","cross_cats_sorted":[],"title_canon_sha256":"76d8822a23b9f36a7fb0db2ceae9c04102997ab283923f9c937c834e81a544f7","abstract_canon_sha256":"dc51c5a8cc30833cf6ef211b689748af4674413b1cb367fb6f9fdbaa4390641e"},"schema_version":"1.0"},"canonical_sha256":"91a26961cf192d9537db25aff1231f674aef1106bf496ec962a355bf4e34b68c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:08.722592Z","signature_b64":"31VGsxyuyRa3g8QRhysDrmI9nClvtfCSy23DdJ5b44xcn6dNuQ6uGPOw9gmFS1+EBCFnCMgYJH5XQrZjrjVGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91a26961cf192d9537db25aff1231f674aef1106bf496ec962a355bf4e34b68c","last_reissued_at":"2026-07-05T07:12:08.722209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:08.722209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.07161","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":"2026-07-05T07:12:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rTVNqc1HjRR3rOVKX36Zw9YEuLdD8A2BBHa+QxcdqWdvc9WjyWYkX6Ga8059oIyQOqDK0hEQE6/oDMdQPfiSCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T05:53:14.549671Z"},"content_sha256":"723c22e508f61fd985ae7a20607c4c834bd7f90706946d758d11313da7711395","schema_version":"1.0","event_id":"sha256:723c22e508f61fd985ae7a20607c4c834bd7f90706946d758d11313da7711395"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SGRGSYOPDEWZKN63EWX7CIY7M5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Developing a Named Entity Recognition Dataset for Tagalog","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lester James V. Miranda","submitted_at":"2023-11-13T08:56:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07161","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/2311.07161/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":"2026-07-05T07:12:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dKdg+IPXR+SPyGWK88figQ5uPfwuLT0kffc+QBTSGSIoamSdKw88rZeEqUaModxxkjw6OoQ+CaGYtBNxBY04BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T05:53:14.550594Z"},"content_sha256":"c38413cce4496d8c865584f7a20a837cdaea00a1000781bba293c10019420111","schema_version":"1.0","event_id":"sha256:c38413cce4496d8c865584f7a20a837cdaea00a1000781bba293c10019420111"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SGRGSYOPDEWZKN63EWX7CIY7M5/bundle.json","state_url":"https://pith.science/pith/SGRGSYOPDEWZKN63EWX7CIY7M5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SGRGSYOPDEWZKN63EWX7CIY7M5/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":"2026-08-16T05:53:14Z","links":{"resolver":"https://pith.science/pith/SGRGSYOPDEWZKN63EWX7CIY7M5","bundle":"https://pith.science/pith/SGRGSYOPDEWZKN63EWX7CIY7M5/bundle.json","state":"https://pith.science/pith/SGRGSYOPDEWZKN63EWX7CIY7M5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SGRGSYOPDEWZKN63EWX7CIY7M5/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"32wxqh5BaM3KYJB7t07NY/WgaSJlNwY0gaSWTxbB28mw7znDbaTlwu7n/bVonW9r3bz5/9mt4t7m442LFLdHCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T05:53:14.598882Z","bundle_sha256":"3e8439f5722371aea422d9c66b5762c767e45f553f19d69fcb83c96a8261d556"}}