{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:IXTIU63HGRVW5GTWRDYKK5WTF3","short_pith_number":"pith:IXTIU63H","canonical_record":{"source":{"id":"2005.07297","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-14T23:46:10Z","cross_cats_sorted":[],"title_canon_sha256":"e6a4cc5c7150164c091690eee94dd0275a26f1c92a94404f12ea44f9d3122c51","abstract_canon_sha256":"544009fad033278880265831e037b7f54c7ec1947956ed3a4984129125840a23"},"schema_version":"1.0"},"canonical_sha256":"45e68a7b67346b6e9a7688f0a576d32ee48a8deb52b00b2f8644167ba9bc2d27","source":{"kind":"arxiv","id":"2005.07297","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.07297","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"arxiv_version","alias_value":"2005.07297v1","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.07297","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"pith_short_12","alias_value":"IXTIU63HGRVW","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"pith_short_16","alias_value":"IXTIU63HGRVW5GTW","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"pith_short_8","alias_value":"IXTIU63H","created_at":"2026-07-05T01:03:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:IXTIU63HGRVW5GTWRDYKK5WTF3","target":"record","payload":{"canonical_record":{"source":{"id":"2005.07297","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-14T23:46:10Z","cross_cats_sorted":[],"title_canon_sha256":"e6a4cc5c7150164c091690eee94dd0275a26f1c92a94404f12ea44f9d3122c51","abstract_canon_sha256":"544009fad033278880265831e037b7f54c7ec1947956ed3a4984129125840a23"},"schema_version":"1.0"},"canonical_sha256":"45e68a7b67346b6e9a7688f0a576d32ee48a8deb52b00b2f8644167ba9bc2d27","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:01.103903Z","signature_b64":"H5RE8lI1nU+KDjdSkfECly6/d7l9KbjgPzQvPu/DZmTrVqI6ciPQXCXc8FY07hPmnhmMg/cnP1YzXATspoPdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45e68a7b67346b6e9a7688f0a576d32ee48a8deb52b00b2f8644167ba9bc2d27","last_reissued_at":"2026-07-05T01:03:01.103478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:01.103478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.07297","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":"2026-07-05T01:03:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"abbGSMc0TqsXLkhchxIW8rZ7Ej0n/CFOS7a+kX8IBBu8zxw8hbXFOKTo+xWwDDE6YlN0Ksjwol+aNRsyBALIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:51:39.445319Z"},"content_sha256":"f0b53aa51f17747c4b0d03d6726f8753399b8368f6e11ad8d572eb866d095d69","schema_version":"1.0","event_id":"sha256:f0b53aa51f17747c4b0d03d6726f8753399b8368f6e11ad8d572eb866d095d69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:IXTIU63HGRVW5GTWRDYKK5WTF3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OSACT4 Shared Task on Offensive Language Detection: Intensive Preprocessing-Based Approach","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fatemah Husain","submitted_at":"2020-05-14T23:46:10Z","abstract_excerpt":"The preprocessing phase is one of the key phases within the text classification pipeline. This study aims at investigating the impact of the preprocessing phase on text classification, specifically on offensive language and hate speech classification for Arabic text. The Arabic language used in social media is informal and written using Arabic dialects, which makes the text classification task very complex. Preprocessing helps in dimensionality reduction and removing useless content. We apply intensive preprocessing techniques to the dataset before processing it further and feeding it into the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.07297","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/2005.07297/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":"2026-07-05T01:03:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GTldGMvbmeVfHNWP7UB2BIO9ThiOKB9qBc1HZAcJQ4k7PX1cfXi2ZYqXIV0JCSwb+hMadYsMC5QGgqXUBBzCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:51:39.445822Z"},"content_sha256":"3b553620e220fe8cfef4f37e05431c2b1b68cebf60e0de2c0620de2035daa443","schema_version":"1.0","event_id":"sha256:3b553620e220fe8cfef4f37e05431c2b1b68cebf60e0de2c0620de2035daa443"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IXTIU63HGRVW5GTWRDYKK5WTF3/bundle.json","state_url":"https://pith.science/pith/IXTIU63HGRVW5GTWRDYKK5WTF3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IXTIU63HGRVW5GTWRDYKK5WTF3/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":"2026-08-10T09:51:39Z","links":{"resolver":"https://pith.science/pith/IXTIU63HGRVW5GTWRDYKK5WTF3","bundle":"https://pith.science/pith/IXTIU63HGRVW5GTWRDYKK5WTF3/bundle.json","state":"https://pith.science/pith/IXTIU63HGRVW5GTWRDYKK5WTF3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IXTIU63HGRVW5GTWRDYKK5WTF3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IXTIU63HGRVW5GTWRDYKK5WTF3","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":"544009fad033278880265831e037b7f54c7ec1947956ed3a4984129125840a23","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-14T23:46:10Z","title_canon_sha256":"e6a4cc5c7150164c091690eee94dd0275a26f1c92a94404f12ea44f9d3122c51"},"schema_version":"1.0","source":{"id":"2005.07297","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.07297","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"arxiv_version","alias_value":"2005.07297v1","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.07297","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"pith_short_12","alias_value":"IXTIU63HGRVW","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"pith_short_16","alias_value":"IXTIU63HGRVW5GTW","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"pith_short_8","alias_value":"IXTIU63H","created_at":"2026-07-05T01:03:01Z"}],"graph_snapshots":[{"event_id":"sha256:3b553620e220fe8cfef4f37e05431c2b1b68cebf60e0de2c0620de2035daa443","target":"graph","created_at":"2026-07-05T01:03:01Z","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/2005.07297/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The preprocessing phase is one of the key phases within the text classification pipeline. This study aims at investigating the impact of the preprocessing phase on text classification, specifically on offensive language and hate speech classification for Arabic text. The Arabic language used in social media is informal and written using Arabic dialects, which makes the text classification task very complex. Preprocessing helps in dimensionality reduction and removing useless content. We apply intensive preprocessing techniques to the dataset before processing it further and feeding it into the","authors_text":"Fatemah Husain","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-14T23:46:10Z","title":"OSACT4 Shared Task on Offensive Language Detection: Intensive Preprocessing-Based Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.07297","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:f0b53aa51f17747c4b0d03d6726f8753399b8368f6e11ad8d572eb866d095d69","target":"record","created_at":"2026-07-05T01:03:01Z","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":"544009fad033278880265831e037b7f54c7ec1947956ed3a4984129125840a23","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-14T23:46:10Z","title_canon_sha256":"e6a4cc5c7150164c091690eee94dd0275a26f1c92a94404f12ea44f9d3122c51"},"schema_version":"1.0","source":{"id":"2005.07297","kind":"arxiv","version":1}},"canonical_sha256":"45e68a7b67346b6e9a7688f0a576d32ee48a8deb52b00b2f8644167ba9bc2d27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45e68a7b67346b6e9a7688f0a576d32ee48a8deb52b00b2f8644167ba9bc2d27","first_computed_at":"2026-07-05T01:03:01.103478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:03:01.103478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H5RE8lI1nU+KDjdSkfECly6/d7l9KbjgPzQvPu/DZmTrVqI6ciPQXCXc8FY07hPmnhmMg/cnP1YzXATspoPdBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:03:01.103903Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.07297","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0b53aa51f17747c4b0d03d6726f8753399b8368f6e11ad8d572eb866d095d69","sha256:3b553620e220fe8cfef4f37e05431c2b1b68cebf60e0de2c0620de2035daa443"],"state_sha256":"aed547a6b9f210a9d4854ddf287b4cf43e3275f451df0965607e7e9749c2e1a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LPWyBBeQdo0T3dOWMrorMs6iHIWxfJEhnN7xBoTMWVVbTzX8pAflsBDOItdLRZaX8uUlqtbf+Hc6M7zo719gDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:51:39.449771Z","bundle_sha256":"dd6918226bf2cc04d83bafed86dccfaee332b2e8b94a81015def8eea503fcc52"}}