{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JOPUK6AUFYFAJ2YZ7PGXKODGPM","short_pith_number":"pith:JOPUK6AU","canonical_record":{"source":{"id":"2412.02056","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T00:28:31Z","cross_cats_sorted":[],"title_canon_sha256":"7a6f0877d59d9b08c09e63a7a7d2a5fc9ee5b0df6d74359b5d711673753a0fcf","abstract_canon_sha256":"f73f5fe037456e7b6d6686157ec7db99b5fe3690d68303d069c36bbacab95c4d"},"schema_version":"1.0"},"canonical_sha256":"4b9f4578142e0a04eb19fbcd7538667b3bc0a2b06489c61082a1a630d5442310","source":{"kind":"arxiv","id":"2412.02056","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.02056","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"2412.02056v2","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02056","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"JOPUK6AUFYFA","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"pith_short_16","alias_value":"JOPUK6AUFYFAJ2YZ","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"pith_short_8","alias_value":"JOPUK6AU","created_at":"2026-07-05T10:01:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JOPUK6AUFYFAJ2YZ7PGXKODGPM","target":"record","payload":{"canonical_record":{"source":{"id":"2412.02056","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T00:28:31Z","cross_cats_sorted":[],"title_canon_sha256":"7a6f0877d59d9b08c09e63a7a7d2a5fc9ee5b0df6d74359b5d711673753a0fcf","abstract_canon_sha256":"f73f5fe037456e7b6d6686157ec7db99b5fe3690d68303d069c36bbacab95c4d"},"schema_version":"1.0"},"canonical_sha256":"4b9f4578142e0a04eb19fbcd7538667b3bc0a2b06489c61082a1a630d5442310","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:01.063409Z","signature_b64":"0uZ0MiLXgyLGMu5f1WLKCaC7inZd4/DU1ca3jGBB+6cVyDikmayyl1tW3pLTANy5Erqa6jxApXo75AdrjY6mAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b9f4578142e0a04eb19fbcd7538667b3bc0a2b06489c61082a1a630d5442310","last_reissued_at":"2026-07-05T10:01:01.063052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:01.063052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.02056","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BP0bZ+J7LYmc/mZR2ezuzAlC8MJQ4ZEk0uHuyy13Wv4ObfBTm5tP/oIHCSx0IsTrXOWZBVqnYy1DQ7lqEM/IBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T01:19:52.479862Z"},"content_sha256":"30c7d9b849e9451f16f66473a9419a83f0969a41eaa9df5cc06102840a0375eb","schema_version":"1.0","event_id":"sha256:30c7d9b849e9451f16f66473a9419a83f0969a41eaa9df5cc06102840a0375eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JOPUK6AUFYFAJ2YZ7PGXKODGPM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Multi-way Parallel Named Entity Annotated Corpus for English, Tamil and Sinhala","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Asanka Ranasinghea, Ayodya Dandeniyaa, Janaka Shamala, Malithi Samaraweeraa, Rashmi Galappaththia, Surangika Ranathunga","submitted_at":"2024-12-03T00:28:31Z","abstract_excerpt":"This paper presents a multi-way parallel English-Tamil-Sinhala corpus annotated with Named Entities (NEs), where Sinhala and Tamil are low-resource languages. Using pre-trained multilingual Language Models (mLMs), we establish new benchmark Named Entity Recognition (NER) results on this dataset for Sinhala and Tamil. We also carry out a detailed investigation on the NER capabilities of different types of mLMs. Finally, we demonstrate the utility of our NER system on a low-resource Neural Machine Translation (NMT) task. Our dataset is publicly released: https://github.com/suralk/multiNER."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02056","kind":"arxiv","version":2},"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/2412.02056/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":"2026-07-05T10:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jDuKF08s5lp8W+MTAmKOmm76LCW2xMw8nYIX4ErERRtSAPmylwFefNB1IBwN/1YlxJ7VnHvArIiN3FkSGfZYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T01:19:52.480544Z"},"content_sha256":"aa9dcedb003ec96fbce45edae0daed3c2def9b517e1f0546cd99e0a07b1f2e75","schema_version":"1.0","event_id":"sha256:aa9dcedb003ec96fbce45edae0daed3c2def9b517e1f0546cd99e0a07b1f2e75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JOPUK6AUFYFAJ2YZ7PGXKODGPM/bundle.json","state_url":"https://pith.science/pith/JOPUK6AUFYFAJ2YZ7PGXKODGPM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JOPUK6AUFYFAJ2YZ7PGXKODGPM/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":"2026-08-24T01:19:52Z","links":{"resolver":"https://pith.science/pith/JOPUK6AUFYFAJ2YZ7PGXKODGPM","bundle":"https://pith.science/pith/JOPUK6AUFYFAJ2YZ7PGXKODGPM/bundle.json","state":"https://pith.science/pith/JOPUK6AUFYFAJ2YZ7PGXKODGPM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JOPUK6AUFYFAJ2YZ7PGXKODGPM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JOPUK6AUFYFAJ2YZ7PGXKODGPM","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":"f73f5fe037456e7b6d6686157ec7db99b5fe3690d68303d069c36bbacab95c4d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T00:28:31Z","title_canon_sha256":"7a6f0877d59d9b08c09e63a7a7d2a5fc9ee5b0df6d74359b5d711673753a0fcf"},"schema_version":"1.0","source":{"id":"2412.02056","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.02056","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"2412.02056v2","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02056","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"JOPUK6AUFYFA","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"pith_short_16","alias_value":"JOPUK6AUFYFAJ2YZ","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"pith_short_8","alias_value":"JOPUK6AU","created_at":"2026-07-05T10:01:01Z"}],"graph_snapshots":[{"event_id":"sha256:aa9dcedb003ec96fbce45edae0daed3c2def9b517e1f0546cd99e0a07b1f2e75","target":"graph","created_at":"2026-07-05T10:01:01Z","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/2412.02056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a multi-way parallel English-Tamil-Sinhala corpus annotated with Named Entities (NEs), where Sinhala and Tamil are low-resource languages. Using pre-trained multilingual Language Models (mLMs), we establish new benchmark Named Entity Recognition (NER) results on this dataset for Sinhala and Tamil. We also carry out a detailed investigation on the NER capabilities of different types of mLMs. Finally, we demonstrate the utility of our NER system on a low-resource Neural Machine Translation (NMT) task. Our dataset is publicly released: https://github.com/suralk/multiNER.","authors_text":"Asanka Ranasinghea, Ayodya Dandeniyaa, Janaka Shamala, Malithi Samaraweeraa, Rashmi Galappaththia, Surangika Ranathunga","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T00:28:31Z","title":"A Multi-way Parallel Named Entity Annotated Corpus for English, Tamil and Sinhala"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02056","kind":"arxiv","version":2},"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":"sha256:30c7d9b849e9451f16f66473a9419a83f0969a41eaa9df5cc06102840a0375eb","target":"record","created_at":"2026-07-05T10:01:01Z","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":"f73f5fe037456e7b6d6686157ec7db99b5fe3690d68303d069c36bbacab95c4d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T00:28:31Z","title_canon_sha256":"7a6f0877d59d9b08c09e63a7a7d2a5fc9ee5b0df6d74359b5d711673753a0fcf"},"schema_version":"1.0","source":{"id":"2412.02056","kind":"arxiv","version":2}},"canonical_sha256":"4b9f4578142e0a04eb19fbcd7538667b3bc0a2b06489c61082a1a630d5442310","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b9f4578142e0a04eb19fbcd7538667b3bc0a2b06489c61082a1a630d5442310","first_computed_at":"2026-07-05T10:01:01.063052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:01:01.063052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0uZ0MiLXgyLGMu5f1WLKCaC7inZd4/DU1ca3jGBB+6cVyDikmayyl1tW3pLTANy5Erqa6jxApXo75AdrjY6mAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:01:01.063409Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.02056","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30c7d9b849e9451f16f66473a9419a83f0969a41eaa9df5cc06102840a0375eb","sha256:aa9dcedb003ec96fbce45edae0daed3c2def9b517e1f0546cd99e0a07b1f2e75"],"state_sha256":"996aac1e6753fc164627d4dbb4bc602283cfa7422b5d2b036a585f9f5bcb42de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ftsnzrTffDdkFuJlkwqGf1nBiC5vgglNi8nwPXQZTwQTWGsuSzc6BkyVLtNzq/wBmvua8LVKwWYXA/bdxpynAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T01:19:52.488477Z","bundle_sha256":"9f037142c0f121cbc332cbb1ba14546bc7d2f81ac428a447d3337352cbf2758f"}}