{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IYCVNVZLORZN3Y5RWSAOMP4U5X","short_pith_number":"pith:IYCVNVZL","canonical_record":{"source":{"id":"2311.15023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-25T13:27:22Z","cross_cats_sorted":[],"title_canon_sha256":"380c86770696cdf0a9c3f29e01f1e649ce9fb4047365e5451d2e4c56483eb53a","abstract_canon_sha256":"b2938a5cee22bc965d0fe93f05cbac800f71e9c8294e4b81823aa6f65cadd947"},"schema_version":"1.0"},"canonical_sha256":"460556d72b7472dde3b1b480e63f94edcf2312bbed0e1fa573a4169c7faaaa07","source":{"kind":"arxiv","id":"2311.15023","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.15023","created_at":"2026-07-05T07:16:57Z"},{"alias_kind":"arxiv_version","alias_value":"2311.15023v1","created_at":"2026-07-05T07:16:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15023","created_at":"2026-07-05T07:16:57Z"},{"alias_kind":"pith_short_12","alias_value":"IYCVNVZLORZN","created_at":"2026-07-05T07:16:57Z"},{"alias_kind":"pith_short_16","alias_value":"IYCVNVZLORZN3Y5R","created_at":"2026-07-05T07:16:57Z"},{"alias_kind":"pith_short_8","alias_value":"IYCVNVZL","created_at":"2026-07-05T07:16:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IYCVNVZLORZN3Y5RWSAOMP4U5X","target":"record","payload":{"canonical_record":{"source":{"id":"2311.15023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-25T13:27:22Z","cross_cats_sorted":[],"title_canon_sha256":"380c86770696cdf0a9c3f29e01f1e649ce9fb4047365e5451d2e4c56483eb53a","abstract_canon_sha256":"b2938a5cee22bc965d0fe93f05cbac800f71e9c8294e4b81823aa6f65cadd947"},"schema_version":"1.0"},"canonical_sha256":"460556d72b7472dde3b1b480e63f94edcf2312bbed0e1fa573a4169c7faaaa07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:57.681806Z","signature_b64":"O6RWAn4L5OASXggWYm6Ulz6XfRxmlZj8qY/46vbx7JuXAEByHLTKil6esQ+xF3CU0rFZstedWNxkBZblJ7czDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"460556d72b7472dde3b1b480e63f94edcf2312bbed0e1fa573a4169c7faaaa07","last_reissued_at":"2026-07-05T07:16:57.681128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:57.681128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.15023","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":"2026-07-05T07:16:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0SxWajnWKfr/N27+7itO0JoAUUQdz4CmhNk2eipwpuzI07AEpDbvSFPJ4U5S5FG8Uv/tV4aZf9as4rbWs0gMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:43:31.891457Z"},"content_sha256":"039af911c9a6d96eb47aba5d90c50030d269e18ace6af95a55ded156e770fdb3","schema_version":"1.0","event_id":"sha256:039af911c9a6d96eb47aba5d90c50030d269e18ace6af95a55ded156e770fdb3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IYCVNVZLORZN3Y5RWSAOMP4U5X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offensive Language Identification in Transliterated and Code-Mixed Bangla","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anika Binte Islam, Antonios Anastasopoulos, Kai North, Marcos Zampieri, Md Nishat Raihan, Tharindu Ranasinghe, Umma Hani Tanmoy","submitted_at":"2023-11-25T13:27:22Z","abstract_excerpt":"Identifying offensive content in social media is vital for creating safe online communities. Several recent studies have addressed this problem by creating datasets for various languages. In this paper, we explore offensive language identification in texts with transliterations and code-mixing, linguistic phenomena common in multilingual societies, and a known challenge for NLP systems. We introduce TB-OLID, a transliterated Bangla offensive language dataset containing 5,000 manually annotated comments. We train and fine-tune machine learning models on TB-OLID, and we evaluate their results on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15023","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/2311.15023/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":"2026-07-05T07:16:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tk2c1WZGPX/89rUSR0XLQl2PWn1NfEz46dh8qjoafAwzYFXspW1pSsee9pLv9INesH0P6rWMw1kdD/IGve2gAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:43:31.892207Z"},"content_sha256":"5d9319db84448d099e218bcc36ae152f9ab647c78555425010bde43ea3ed0cc3","schema_version":"1.0","event_id":"sha256:5d9319db84448d099e218bcc36ae152f9ab647c78555425010bde43ea3ed0cc3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IYCVNVZLORZN3Y5RWSAOMP4U5X/bundle.json","state_url":"https://pith.science/pith/IYCVNVZLORZN3Y5RWSAOMP4U5X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IYCVNVZLORZN3Y5RWSAOMP4U5X/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":"2026-08-07T22:43:31Z","links":{"resolver":"https://pith.science/pith/IYCVNVZLORZN3Y5RWSAOMP4U5X","bundle":"https://pith.science/pith/IYCVNVZLORZN3Y5RWSAOMP4U5X/bundle.json","state":"https://pith.science/pith/IYCVNVZLORZN3Y5RWSAOMP4U5X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IYCVNVZLORZN3Y5RWSAOMP4U5X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IYCVNVZLORZN3Y5RWSAOMP4U5X","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":"b2938a5cee22bc965d0fe93f05cbac800f71e9c8294e4b81823aa6f65cadd947","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-25T13:27:22Z","title_canon_sha256":"380c86770696cdf0a9c3f29e01f1e649ce9fb4047365e5451d2e4c56483eb53a"},"schema_version":"1.0","source":{"id":"2311.15023","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.15023","created_at":"2026-07-05T07:16:57Z"},{"alias_kind":"arxiv_version","alias_value":"2311.15023v1","created_at":"2026-07-05T07:16:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15023","created_at":"2026-07-05T07:16:57Z"},{"alias_kind":"pith_short_12","alias_value":"IYCVNVZLORZN","created_at":"2026-07-05T07:16:57Z"},{"alias_kind":"pith_short_16","alias_value":"IYCVNVZLORZN3Y5R","created_at":"2026-07-05T07:16:57Z"},{"alias_kind":"pith_short_8","alias_value":"IYCVNVZL","created_at":"2026-07-05T07:16:57Z"}],"graph_snapshots":[{"event_id":"sha256:5d9319db84448d099e218bcc36ae152f9ab647c78555425010bde43ea3ed0cc3","target":"graph","created_at":"2026-07-05T07:16:57Z","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/2311.15023/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Identifying offensive content in social media is vital for creating safe online communities. Several recent studies have addressed this problem by creating datasets for various languages. In this paper, we explore offensive language identification in texts with transliterations and code-mixing, linguistic phenomena common in multilingual societies, and a known challenge for NLP systems. We introduce TB-OLID, a transliterated Bangla offensive language dataset containing 5,000 manually annotated comments. We train and fine-tune machine learning models on TB-OLID, and we evaluate their results on","authors_text":"Anika Binte Islam, Antonios Anastasopoulos, Kai North, Marcos Zampieri, Md Nishat Raihan, Tharindu Ranasinghe, Umma Hani Tanmoy","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-25T13:27:22Z","title":"Offensive Language Identification in Transliterated and Code-Mixed Bangla"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15023","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":"sha256:039af911c9a6d96eb47aba5d90c50030d269e18ace6af95a55ded156e770fdb3","target":"record","created_at":"2026-07-05T07:16:57Z","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":"b2938a5cee22bc965d0fe93f05cbac800f71e9c8294e4b81823aa6f65cadd947","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-25T13:27:22Z","title_canon_sha256":"380c86770696cdf0a9c3f29e01f1e649ce9fb4047365e5451d2e4c56483eb53a"},"schema_version":"1.0","source":{"id":"2311.15023","kind":"arxiv","version":1}},"canonical_sha256":"460556d72b7472dde3b1b480e63f94edcf2312bbed0e1fa573a4169c7faaaa07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"460556d72b7472dde3b1b480e63f94edcf2312bbed0e1fa573a4169c7faaaa07","first_computed_at":"2026-07-05T07:16:57.681128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:16:57.681128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O6RWAn4L5OASXggWYm6Ulz6XfRxmlZj8qY/46vbx7JuXAEByHLTKil6esQ+xF3CU0rFZstedWNxkBZblJ7czDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:16:57.681806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.15023","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:039af911c9a6d96eb47aba5d90c50030d269e18ace6af95a55ded156e770fdb3","sha256:5d9319db84448d099e218bcc36ae152f9ab647c78555425010bde43ea3ed0cc3"],"state_sha256":"6b69651c89a06c3676315b1e18ee079300554a63953dd088d03c6228d7563376"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/lqZUct5pd9vsXU2Uia4bH/mVccaw8995p/+23+9V6TqvF7OvzO6JIJE+WgOKmzcwCLbvyDknjqOxHNLy1SuAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:43:31.896449Z","bundle_sha256":"168d1b58a337afc7f89d3aea742025b2e3080e59f52cbedf438817b85783bde0"}}