{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:FME7MKC5YXTH4SV6OWWF4PQDVO","short_pith_number":"pith:FME7MKC5","canonical_record":{"source":{"id":"2012.09686","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-17T15:53:54Z","cross_cats_sorted":[],"title_canon_sha256":"1cd2289580057dffe6f92a8c9db6637d232723c90f12bcbeb083e47086c8a75f","abstract_canon_sha256":"e3f984fc64bf3df0b5855e4a9b380fe9716da694f669b3690cb5de81499751a1"},"schema_version":"1.0"},"canonical_sha256":"2b09f6285dc5e67e4abe75ac5e3e03ab8c50a016288febc88281ad6ff5f7f64d","source":{"kind":"arxiv","id":"2012.09686","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.09686","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"arxiv_version","alias_value":"2012.09686v1","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.09686","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"pith_short_12","alias_value":"FME7MKC5YXTH","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"pith_short_16","alias_value":"FME7MKC5YXTH4SV6","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"pith_short_8","alias_value":"FME7MKC5","created_at":"2026-07-05T02:00:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:FME7MKC5YXTH4SV6OWWF4PQDVO","target":"record","payload":{"canonical_record":{"source":{"id":"2012.09686","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-17T15:53:54Z","cross_cats_sorted":[],"title_canon_sha256":"1cd2289580057dffe6f92a8c9db6637d232723c90f12bcbeb083e47086c8a75f","abstract_canon_sha256":"e3f984fc64bf3df0b5855e4a9b380fe9716da694f669b3690cb5de81499751a1"},"schema_version":"1.0"},"canonical_sha256":"2b09f6285dc5e67e4abe75ac5e3e03ab8c50a016288febc88281ad6ff5f7f64d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:20.166667Z","signature_b64":"4hQYdlYgs1l8pKPNf9tG1jeNBVow8YyqSzZTVkOttpjCR++PYN2i8gX77yfozry6os03uodYiV/ZKQ/T3+qGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b09f6285dc5e67e4abe75ac5e3e03ab8c50a016288febc88281ad6ff5f7f64d","last_reissued_at":"2026-07-05T02:00:20.166192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:20.166192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.09686","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":"2026-07-05T02:00:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3v1jQw5NaQFXml/b6CiILwrbCpGARsd0UB9/AmtptAa+OTFYy7eNrk23vCV2MrpLHPKKgfSXcL8cwjrX/34tBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:54:09.174601Z"},"content_sha256":"ff4e28b3f9b15b3fddea5e02cdaf42cdcdc47cb4e6dc8cda5648cf2c5f4d33d6","schema_version":"1.0","event_id":"sha256:ff4e28b3f9b15b3fddea5e02cdaf42cdcdc47cb4e6dc8cda5648cf2c5f4d33d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:FME7MKC5YXTH4SV6OWWF4PQDVO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hate Speech detection in the Bengali language: A dataset and its baseline evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hriteshwar Talukder, Md Saiful Islam, Mosahed Ahmed, Nauros Romim","submitted_at":"2020-12-17T15:53:54Z","abstract_excerpt":"Social media sites such as YouTube and Facebook have become an integral part of everyone's life and in the last few years, hate speech in the social media comment section has increased rapidly. Detection of hate speech on social media websites faces a variety of challenges including small imbalanced data sets, the findings of an appropriate model and also the choice of feature analysis method. further more, this problem is more severe for the Bengali speaking community due to the lack of gold standard labelled datasets. This paper presents a new dataset of 30,000 user comments tagged by crowd "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.09686","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/2012.09686/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":"2026-07-05T02:00:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WoKqDZFbMmbKkv+26vbqw751fXgoUsIagQcWjac9F2OeIYKw2/yFCgbcdIpW12Mot1lwq0HBHAKvb3mPPiCuDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:54:09.175094Z"},"content_sha256":"bbde759b2f4fd801e81515ad19a8df5b33b84a08a4a413d1a49f096e7771b062","schema_version":"1.0","event_id":"sha256:bbde759b2f4fd801e81515ad19a8df5b33b84a08a4a413d1a49f096e7771b062"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FME7MKC5YXTH4SV6OWWF4PQDVO/bundle.json","state_url":"https://pith.science/pith/FME7MKC5YXTH4SV6OWWF4PQDVO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FME7MKC5YXTH4SV6OWWF4PQDVO/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":"2026-08-08T13:54:09Z","links":{"resolver":"https://pith.science/pith/FME7MKC5YXTH4SV6OWWF4PQDVO","bundle":"https://pith.science/pith/FME7MKC5YXTH4SV6OWWF4PQDVO/bundle.json","state":"https://pith.science/pith/FME7MKC5YXTH4SV6OWWF4PQDVO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FME7MKC5YXTH4SV6OWWF4PQDVO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FME7MKC5YXTH4SV6OWWF4PQDVO","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":"e3f984fc64bf3df0b5855e4a9b380fe9716da694f669b3690cb5de81499751a1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-17T15:53:54Z","title_canon_sha256":"1cd2289580057dffe6f92a8c9db6637d232723c90f12bcbeb083e47086c8a75f"},"schema_version":"1.0","source":{"id":"2012.09686","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.09686","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"arxiv_version","alias_value":"2012.09686v1","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.09686","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"pith_short_12","alias_value":"FME7MKC5YXTH","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"pith_short_16","alias_value":"FME7MKC5YXTH4SV6","created_at":"2026-07-05T02:00:20Z"},{"alias_kind":"pith_short_8","alias_value":"FME7MKC5","created_at":"2026-07-05T02:00:20Z"}],"graph_snapshots":[{"event_id":"sha256:bbde759b2f4fd801e81515ad19a8df5b33b84a08a4a413d1a49f096e7771b062","target":"graph","created_at":"2026-07-05T02:00:20Z","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/2012.09686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Social media sites such as YouTube and Facebook have become an integral part of everyone's life and in the last few years, hate speech in the social media comment section has increased rapidly. Detection of hate speech on social media websites faces a variety of challenges including small imbalanced data sets, the findings of an appropriate model and also the choice of feature analysis method. further more, this problem is more severe for the Bengali speaking community due to the lack of gold standard labelled datasets. This paper presents a new dataset of 30,000 user comments tagged by crowd ","authors_text":"Hriteshwar Talukder, Md Saiful Islam, Mosahed Ahmed, Nauros Romim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-17T15:53:54Z","title":"Hate Speech detection in the Bengali language: A dataset and its baseline evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.09686","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:ff4e28b3f9b15b3fddea5e02cdaf42cdcdc47cb4e6dc8cda5648cf2c5f4d33d6","target":"record","created_at":"2026-07-05T02:00:20Z","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":"e3f984fc64bf3df0b5855e4a9b380fe9716da694f669b3690cb5de81499751a1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-17T15:53:54Z","title_canon_sha256":"1cd2289580057dffe6f92a8c9db6637d232723c90f12bcbeb083e47086c8a75f"},"schema_version":"1.0","source":{"id":"2012.09686","kind":"arxiv","version":1}},"canonical_sha256":"2b09f6285dc5e67e4abe75ac5e3e03ab8c50a016288febc88281ad6ff5f7f64d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b09f6285dc5e67e4abe75ac5e3e03ab8c50a016288febc88281ad6ff5f7f64d","first_computed_at":"2026-07-05T02:00:20.166192Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:00:20.166192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4hQYdlYgs1l8pKPNf9tG1jeNBVow8YyqSzZTVkOttpjCR++PYN2i8gX77yfozry6os03uodYiV/ZKQ/T3+qGDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:00:20.166667Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.09686","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff4e28b3f9b15b3fddea5e02cdaf42cdcdc47cb4e6dc8cda5648cf2c5f4d33d6","sha256:bbde759b2f4fd801e81515ad19a8df5b33b84a08a4a413d1a49f096e7771b062"],"state_sha256":"627631b77cf38b76fff8fa3bb0ef317282b1342f6e8fbf53699d6d88e97b1b50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lZD2n/zPS9zsUf2pqngtu9gwN7ygOXQjF9ewrVLFP3VDr+fIXdMedoXVVcGXwKDp/pIdiRxoaGXRiDPKiFI1Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:54:09.178956Z","bundle_sha256":"96e34c93a08fff3e9ceb84dc24a24b7af50ff31734f715ad317fc430e41a45da"}}