{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:O3XHHAPMKFDADDDJS4FXL5Q524","short_pith_number":"pith:O3XHHAPM","schema_version":"1.0","canonical_sha256":"76ee7381ec5146018c69970b75f61dd71d36db812e47f8111f4eafe731b082c6","source":{"kind":"arxiv","id":"2301.11125","version":1},"attestation_state":"computed","paper":{"title":"A benchmark for toxic comment classification on Civil Comments dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Corentin Duchene, Henri Jamet, Pierre Guillaume, Reda Dehak","submitted_at":"2023-01-26T14:25:09Z","abstract_excerpt":"Toxic comment detection on social media has proven to be essential for content moderation. This paper compares a wide set of different models on a highly skewed multi-label hate speech dataset. We consider inference time and several metrics to measure performance and bias in our comparison. We show that all BERTs have similar performance regardless of the size, optimizations or language used to pre-train the models. RNNs are much faster at inference than any of the BERT. BiLSTM remains a good compromise between performance and inference time. RoBERTa with Focal Loss offers the best performance"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2301.11125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-26T14:25:09Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"b5fad08c9b345814754cf0df6c2138a47833f3abc904a007fc471bbd4321e162","abstract_canon_sha256":"92b1b6648ad7b3abadf7978764bb79bebca58a331245d91357ccc26b5633118a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:10.722284Z","signature_b64":"LwSKrzd9eb3eAR7rgDzcFlohK6LJ20OXGDIN5giGt24e/yPnf7hckx7RmDq271a11AWVX9IZYBNqsim69tkiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76ee7381ec5146018c69970b75f61dd71d36db812e47f8111f4eafe731b082c6","last_reissued_at":"2026-07-05T05:36:10.721884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:10.721884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A benchmark for toxic comment classification on Civil Comments dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Corentin Duchene, Henri Jamet, Pierre Guillaume, Reda Dehak","submitted_at":"2023-01-26T14:25:09Z","abstract_excerpt":"Toxic comment detection on social media has proven to be essential for content moderation. This paper compares a wide set of different models on a highly skewed multi-label hate speech dataset. We consider inference time and several metrics to measure performance and bias in our comparison. We show that all BERTs have similar performance regardless of the size, optimizations or language used to pre-train the models. RNNs are much faster at inference than any of the BERT. BiLSTM remains a good compromise between performance and inference time. RoBERTa with Focal Loss offers the best performance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11125","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/2301.11125/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2301.11125","created_at":"2026-07-05T05:36:10.721952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.11125v1","created_at":"2026-07-05T05:36:10.721952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11125","created_at":"2026-07-05T05:36:10.721952+00:00"},{"alias_kind":"pith_short_12","alias_value":"O3XHHAPMKFDA","created_at":"2026-07-05T05:36:10.721952+00:00"},{"alias_kind":"pith_short_16","alias_value":"O3XHHAPMKFDADDDJ","created_at":"2026-07-05T05:36:10.721952+00:00"},{"alias_kind":"pith_short_8","alias_value":"O3XHHAPM","created_at":"2026-07-05T05:36:10.721952+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02072","citing_title":"ASCenD-BDS: Adaptable, Stochastic and Context-aware framework for Detection of Bias, Discrimination and Stereotyping","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O3XHHAPMKFDADDDJS4FXL5Q524","json":"https://pith.science/pith/O3XHHAPMKFDADDDJS4FXL5Q524.json","graph_json":"https://pith.science/api/pith-number/O3XHHAPMKFDADDDJS4FXL5Q524/graph.json","events_json":"https://pith.science/api/pith-number/O3XHHAPMKFDADDDJS4FXL5Q524/events.json","paper":"https://pith.science/paper/O3XHHAPM"},"agent_actions":{"view_html":"https://pith.science/pith/O3XHHAPMKFDADDDJS4FXL5Q524","download_json":"https://pith.science/pith/O3XHHAPMKFDADDDJS4FXL5Q524.json","view_paper":"https://pith.science/paper/O3XHHAPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.11125&json=true","fetch_graph":"https://pith.science/api/pith-number/O3XHHAPMKFDADDDJS4FXL5Q524/graph.json","fetch_events":"https://pith.science/api/pith-number/O3XHHAPMKFDADDDJS4FXL5Q524/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O3XHHAPMKFDADDDJS4FXL5Q524/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O3XHHAPMKFDADDDJS4FXL5Q524/action/storage_attestation","attest_author":"https://pith.science/pith/O3XHHAPMKFDADDDJS4FXL5Q524/action/author_attestation","sign_citation":"https://pith.science/pith/O3XHHAPMKFDADDDJS4FXL5Q524/action/citation_signature","submit_replication":"https://pith.science/pith/O3XHHAPMKFDADDDJS4FXL5Q524/action/replication_record"}},"created_at":"2026-07-05T05:36:10.721952+00:00","updated_at":"2026-07-05T05:36:10.721952+00:00"}