{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:JOTWTTUNUL5YQRUNW53WD55B2D","short_pith_number":"pith:JOTWTTUN","canonical_record":{"source":{"id":"2208.07864","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-16T17:47:42Z","cross_cats_sorted":[],"title_canon_sha256":"0d0da837cf4b66e22c60fc10c6585dfed6124712586a8cd500600b4e0acdf796","abstract_canon_sha256":"49b9a57fa2694f31f8073eeebee07d299bb819b1a307514126f3342b4a9d3231"},"schema_version":"1.0"},"canonical_sha256":"4ba769ce8da2fb88468db77761f7a1d0c2e532cb07f2093e38f63b86cb420fa2","source":{"kind":"arxiv","id":"2208.07864","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.07864","created_at":"2026-07-05T04:49:24Z"},{"alias_kind":"arxiv_version","alias_value":"2208.07864v2","created_at":"2026-07-05T04:49:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.07864","created_at":"2026-07-05T04:49:24Z"},{"alias_kind":"pith_short_12","alias_value":"JOTWTTUNUL5Y","created_at":"2026-07-05T04:49:24Z"},{"alias_kind":"pith_short_16","alias_value":"JOTWTTUNUL5YQRUN","created_at":"2026-07-05T04:49:24Z"},{"alias_kind":"pith_short_8","alias_value":"JOTWTTUN","created_at":"2026-07-05T04:49:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:JOTWTTUNUL5YQRUNW53WD55B2D","target":"record","payload":{"canonical_record":{"source":{"id":"2208.07864","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-16T17:47:42Z","cross_cats_sorted":[],"title_canon_sha256":"0d0da837cf4b66e22c60fc10c6585dfed6124712586a8cd500600b4e0acdf796","abstract_canon_sha256":"49b9a57fa2694f31f8073eeebee07d299bb819b1a307514126f3342b4a9d3231"},"schema_version":"1.0"},"canonical_sha256":"4ba769ce8da2fb88468db77761f7a1d0c2e532cb07f2093e38f63b86cb420fa2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:49:24.142244Z","signature_b64":"2zMycYqXPiTWDXx0CXz8dOIYeFbTCnQ02JB2zBbbetZynFyXIKe6MUsutRJozHp9JNVFlz5Sw4PL+wZRNPH8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ba769ce8da2fb88468db77761f7a1d0c2e532cb07f2093e38f63b86cb420fa2","last_reissued_at":"2026-07-05T04:49:24.141834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:49:24.141834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.07864","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":"2026-07-05T04:49:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Hq759Cgpv4Zkt3ggJrZFS0nntauV2wRggNudNXY/vUEsgOUQKN4gURUygJu2dbnYumXN/b6f0bDs5/Zod8XAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:03:44.081583Z"},"content_sha256":"148cf5b190acce3a3304d20aa1447938a7a9e1b4ec7b01cad82c0837924c0b94","schema_version":"1.0","event_id":"sha256:148cf5b190acce3a3304d20aa1447938a7a9e1b4ec7b01cad82c0837924c0b94"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:JOTWTTUNUL5YQRUNW53WD55B2D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BERTifying Sinhala -- A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Piyumal Demotte, Sanath Jayasena, Surangika Ranathunga, Vinura Dhananjaya","submitted_at":"2022-08-16T17:47:42Z","abstract_excerpt":"This research provides the first comprehensive analysis of the performance of pre-trained language models for Sinhala text classification. We test on a set of different Sinhala text classification tasks and our analysis shows that out of the pre-trained multilingual models that include Sinhala (XLM-R, LaBSE, and LASER), XLM-R is the best model by far for Sinhala text classification. We also pre-train two RoBERTa-based monolingual Sinhala models, which are far superior to the existing pre-trained language models for Sinhala. We show that when fine-tuned, these pre-trained language models set a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.07864","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/2208.07864/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":"2026-07-05T04:49:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GNK0AVgW+foAcTOf56mY/EpAHKaGUzMLC3MNezakZGOmSkR3V4LL0zPT1rsISkBqV+RAUc+aEXV4tnfTWKzgDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:03:44.081930Z"},"content_sha256":"cb140fe1b2539d69a9b0b6b04e4650deeaca121fb656906646e378195a3871cc","schema_version":"1.0","event_id":"sha256:cb140fe1b2539d69a9b0b6b04e4650deeaca121fb656906646e378195a3871cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JOTWTTUNUL5YQRUNW53WD55B2D/bundle.json","state_url":"https://pith.science/pith/JOTWTTUNUL5YQRUNW53WD55B2D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JOTWTTUNUL5YQRUNW53WD55B2D/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":"2026-08-06T21:03:44Z","links":{"resolver":"https://pith.science/pith/JOTWTTUNUL5YQRUNW53WD55B2D","bundle":"https://pith.science/pith/JOTWTTUNUL5YQRUNW53WD55B2D/bundle.json","state":"https://pith.science/pith/JOTWTTUNUL5YQRUNW53WD55B2D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JOTWTTUNUL5YQRUNW53WD55B2D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JOTWTTUNUL5YQRUNW53WD55B2D","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":"49b9a57fa2694f31f8073eeebee07d299bb819b1a307514126f3342b4a9d3231","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-16T17:47:42Z","title_canon_sha256":"0d0da837cf4b66e22c60fc10c6585dfed6124712586a8cd500600b4e0acdf796"},"schema_version":"1.0","source":{"id":"2208.07864","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.07864","created_at":"2026-07-05T04:49:24Z"},{"alias_kind":"arxiv_version","alias_value":"2208.07864v2","created_at":"2026-07-05T04:49:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.07864","created_at":"2026-07-05T04:49:24Z"},{"alias_kind":"pith_short_12","alias_value":"JOTWTTUNUL5Y","created_at":"2026-07-05T04:49:24Z"},{"alias_kind":"pith_short_16","alias_value":"JOTWTTUNUL5YQRUN","created_at":"2026-07-05T04:49:24Z"},{"alias_kind":"pith_short_8","alias_value":"JOTWTTUN","created_at":"2026-07-05T04:49:24Z"}],"graph_snapshots":[{"event_id":"sha256:cb140fe1b2539d69a9b0b6b04e4650deeaca121fb656906646e378195a3871cc","target":"graph","created_at":"2026-07-05T04:49:24Z","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/2208.07864/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This research provides the first comprehensive analysis of the performance of pre-trained language models for Sinhala text classification. We test on a set of different Sinhala text classification tasks and our analysis shows that out of the pre-trained multilingual models that include Sinhala (XLM-R, LaBSE, and LASER), XLM-R is the best model by far for Sinhala text classification. We also pre-train two RoBERTa-based monolingual Sinhala models, which are far superior to the existing pre-trained language models for Sinhala. We show that when fine-tuned, these pre-trained language models set a ","authors_text":"Piyumal Demotte, Sanath Jayasena, Surangika Ranathunga, Vinura Dhananjaya","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-16T17:47:42Z","title":"BERTifying Sinhala -- A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.07864","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":"sha256:148cf5b190acce3a3304d20aa1447938a7a9e1b4ec7b01cad82c0837924c0b94","target":"record","created_at":"2026-07-05T04:49:24Z","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":"49b9a57fa2694f31f8073eeebee07d299bb819b1a307514126f3342b4a9d3231","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-16T17:47:42Z","title_canon_sha256":"0d0da837cf4b66e22c60fc10c6585dfed6124712586a8cd500600b4e0acdf796"},"schema_version":"1.0","source":{"id":"2208.07864","kind":"arxiv","version":2}},"canonical_sha256":"4ba769ce8da2fb88468db77761f7a1d0c2e532cb07f2093e38f63b86cb420fa2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ba769ce8da2fb88468db77761f7a1d0c2e532cb07f2093e38f63b86cb420fa2","first_computed_at":"2026-07-05T04:49:24.141834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:49:24.141834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2zMycYqXPiTWDXx0CXz8dOIYeFbTCnQ02JB2zBbbetZynFyXIKe6MUsutRJozHp9JNVFlz5Sw4PL+wZRNPH8AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:49:24.142244Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.07864","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:148cf5b190acce3a3304d20aa1447938a7a9e1b4ec7b01cad82c0837924c0b94","sha256:cb140fe1b2539d69a9b0b6b04e4650deeaca121fb656906646e378195a3871cc"],"state_sha256":"d74119c1c0722aefc7272cb37a28f4e23ad61e9c152b6e1a880012578c5ad467"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sfX6vIwwgnlfWCVKeIaGJLsefcsITVHPii9wEDux/V3OSA2kJ8BvHM9m9O+Sho/tDmqlIBaDL+9Ye0cGsLIXDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:03:44.086496Z","bundle_sha256":"144ecf22936ab49063e642b88e8b0bce71b36cd765c4e2a00361680efea870ad"}}