{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WHW7OT2BOUMGBKM7X5QWSV6V4X","short_pith_number":"pith:WHW7OT2B","canonical_record":{"source":{"id":"2307.01680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-04T12:22:40Z","cross_cats_sorted":[],"title_canon_sha256":"95b5bb6d62bd41e42ea539b74c37b8647e632af351b3cc37591d6d3b7daf4f04","abstract_canon_sha256":"e6bdba8ff13d0b6cc5954ee5406505d10dd29172cd6d1f6c7abe5146c1379cdd"},"schema_version":"1.0"},"canonical_sha256":"b1edf74f41751860a99fbf616957d5e5f4b1c0ba404a9e85364af1d3b8224188","source":{"kind":"arxiv","id":"2307.01680","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.01680","created_at":"2026-07-05T06:27:59Z"},{"alias_kind":"arxiv_version","alias_value":"2307.01680v1","created_at":"2026-07-05T06:27:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01680","created_at":"2026-07-05T06:27:59Z"},{"alias_kind":"pith_short_12","alias_value":"WHW7OT2BOUMG","created_at":"2026-07-05T06:27:59Z"},{"alias_kind":"pith_short_16","alias_value":"WHW7OT2BOUMGBKM7","created_at":"2026-07-05T06:27:59Z"},{"alias_kind":"pith_short_8","alias_value":"WHW7OT2B","created_at":"2026-07-05T06:27:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WHW7OT2BOUMGBKM7X5QWSV6V4X","target":"record","payload":{"canonical_record":{"source":{"id":"2307.01680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-04T12:22:40Z","cross_cats_sorted":[],"title_canon_sha256":"95b5bb6d62bd41e42ea539b74c37b8647e632af351b3cc37591d6d3b7daf4f04","abstract_canon_sha256":"e6bdba8ff13d0b6cc5954ee5406505d10dd29172cd6d1f6c7abe5146c1379cdd"},"schema_version":"1.0"},"canonical_sha256":"b1edf74f41751860a99fbf616957d5e5f4b1c0ba404a9e85364af1d3b8224188","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:59.539591Z","signature_b64":"EaKGzIFu4Lz/SYj0VVRSwABX8WYUl1uALcMKK66rlVKhmMOJCd+ZVZ/b8QokovJ2oN0Ffd1y5nmf5oZNxp/yCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1edf74f41751860a99fbf616957d5e5f4b1c0ba404a9e85364af1d3b8224188","last_reissued_at":"2026-07-05T06:27:59.539195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:59.539195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.01680","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":"2026-07-05T06:27:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S1VD2Ofz5kmYznQtYd8rUXGK8KRP7/J4L9XLJTeuXi4MWS4nYqDWm5vjLCNRoFIlox0goLGaakfkxBYMOGIfBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:33:39.509775Z"},"content_sha256":"d8f375b34f186af2f73fa295ba03f556f08a4e5dedfca136a34773e9ae1a0575","schema_version":"1.0","event_id":"sha256:d8f375b34f186af2f73fa295ba03f556f08a4e5dedfca136a34773e9ae1a0575"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WHW7OT2BOUMGBKM7X5QWSV6V4X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Hate Speech Detection in Social Media: A Cross-Dataset Empirical Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dimosthenis Antypas, Jose Camacho-Collados","submitted_at":"2023-07-04T12:22:40Z","abstract_excerpt":"The automatic detection of hate speech online is an active research area in NLP. Most of the studies to date are based on social media datasets that contribute to the creation of hate speech detection models trained on them. However, data creation processes contain their own biases, and models inherently learn from these dataset-specific biases. In this paper, we perform a large-scale cross-dataset comparison where we fine-tune language models on different hate speech detection datasets. This analysis shows how some datasets are more generalisable than others when used as training data. Crucia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01680","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/2307.01680/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":"2026-07-05T06:27:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EX2IvwwxKuyoQFEOeYiyMPuRQVx68VbXZsWNPqvj9Y40Xhrs862Z23/B2jECF+kBxMXgDo+uWjnEx4Ci21XDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:33:39.510147Z"},"content_sha256":"b692eea272c671d13e7e51003bd275a657846c450317af6823048e8de4899770","schema_version":"1.0","event_id":"sha256:b692eea272c671d13e7e51003bd275a657846c450317af6823048e8de4899770"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WHW7OT2BOUMGBKM7X5QWSV6V4X/bundle.json","state_url":"https://pith.science/pith/WHW7OT2BOUMGBKM7X5QWSV6V4X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WHW7OT2BOUMGBKM7X5QWSV6V4X/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":"2026-08-19T14:33:39Z","links":{"resolver":"https://pith.science/pith/WHW7OT2BOUMGBKM7X5QWSV6V4X","bundle":"https://pith.science/pith/WHW7OT2BOUMGBKM7X5QWSV6V4X/bundle.json","state":"https://pith.science/pith/WHW7OT2BOUMGBKM7X5QWSV6V4X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WHW7OT2BOUMGBKM7X5QWSV6V4X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WHW7OT2BOUMGBKM7X5QWSV6V4X","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":"e6bdba8ff13d0b6cc5954ee5406505d10dd29172cd6d1f6c7abe5146c1379cdd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-04T12:22:40Z","title_canon_sha256":"95b5bb6d62bd41e42ea539b74c37b8647e632af351b3cc37591d6d3b7daf4f04"},"schema_version":"1.0","source":{"id":"2307.01680","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.01680","created_at":"2026-07-05T06:27:59Z"},{"alias_kind":"arxiv_version","alias_value":"2307.01680v1","created_at":"2026-07-05T06:27:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01680","created_at":"2026-07-05T06:27:59Z"},{"alias_kind":"pith_short_12","alias_value":"WHW7OT2BOUMG","created_at":"2026-07-05T06:27:59Z"},{"alias_kind":"pith_short_16","alias_value":"WHW7OT2BOUMGBKM7","created_at":"2026-07-05T06:27:59Z"},{"alias_kind":"pith_short_8","alias_value":"WHW7OT2B","created_at":"2026-07-05T06:27:59Z"}],"graph_snapshots":[{"event_id":"sha256:b692eea272c671d13e7e51003bd275a657846c450317af6823048e8de4899770","target":"graph","created_at":"2026-07-05T06:27:59Z","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/2307.01680/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The automatic detection of hate speech online is an active research area in NLP. Most of the studies to date are based on social media datasets that contribute to the creation of hate speech detection models trained on them. However, data creation processes contain their own biases, and models inherently learn from these dataset-specific biases. In this paper, we perform a large-scale cross-dataset comparison where we fine-tune language models on different hate speech detection datasets. This analysis shows how some datasets are more generalisable than others when used as training data. Crucia","authors_text":"Dimosthenis Antypas, Jose Camacho-Collados","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-04T12:22:40Z","title":"Robust Hate Speech Detection in Social Media: A Cross-Dataset Empirical Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01680","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:d8f375b34f186af2f73fa295ba03f556f08a4e5dedfca136a34773e9ae1a0575","target":"record","created_at":"2026-07-05T06:27:59Z","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":"e6bdba8ff13d0b6cc5954ee5406505d10dd29172cd6d1f6c7abe5146c1379cdd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-04T12:22:40Z","title_canon_sha256":"95b5bb6d62bd41e42ea539b74c37b8647e632af351b3cc37591d6d3b7daf4f04"},"schema_version":"1.0","source":{"id":"2307.01680","kind":"arxiv","version":1}},"canonical_sha256":"b1edf74f41751860a99fbf616957d5e5f4b1c0ba404a9e85364af1d3b8224188","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1edf74f41751860a99fbf616957d5e5f4b1c0ba404a9e85364af1d3b8224188","first_computed_at":"2026-07-05T06:27:59.539195Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:27:59.539195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EaKGzIFu4Lz/SYj0VVRSwABX8WYUl1uALcMKK66rlVKhmMOJCd+ZVZ/b8QokovJ2oN0Ffd1y5nmf5oZNxp/yCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:27:59.539591Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.01680","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8f375b34f186af2f73fa295ba03f556f08a4e5dedfca136a34773e9ae1a0575","sha256:b692eea272c671d13e7e51003bd275a657846c450317af6823048e8de4899770"],"state_sha256":"0d089de0640fab21d6346a62eb000ac7159ad7ec8dd52c4fabd784ddddf892cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dEitmXcBSavf3S2HWyUKkGZcZQSqGP7VtNrVM06x3BuTkaMy8Z5qAqal0myzd/YAEawrNmt1RfV6H+ndtEAZCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T14:33:39.512712Z","bundle_sha256":"f82a96aeb8b46e15b92a7ca8585af9d53a3f2cbe4736c37f12b506274413b96f"}}