{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YZXPGCLV6LMB5SMM5HF3R6TFKO","short_pith_number":"pith:YZXPGCLV","canonical_record":{"source":{"id":"2501.11960","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-21T08:13:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"43854ac72ce68e85a05775565746a14fce4a6a002a5da78364c6929990d4a1cb","abstract_canon_sha256":"39ceb9c6bb39d56f35b4bf5a86a9be0d051359c72472f3aad56a66c3be9a3c8a"},"schema_version":"1.0"},"canonical_sha256":"c66ef30975f2d81ec98ce9cbb8fa6553950e2b1a16a072f04e3d2ebd7ba7e74b","source":{"kind":"arxiv","id":"2501.11960","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11960","created_at":"2026-07-05T11:08:15Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11960v2","created_at":"2026-07-05T11:08:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11960","created_at":"2026-07-05T11:08:15Z"},{"alias_kind":"pith_short_12","alias_value":"YZXPGCLV6LMB","created_at":"2026-07-05T11:08:15Z"},{"alias_kind":"pith_short_16","alias_value":"YZXPGCLV6LMB5SMM","created_at":"2026-07-05T11:08:15Z"},{"alias_kind":"pith_short_8","alias_value":"YZXPGCLV","created_at":"2026-07-05T11:08:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YZXPGCLV6LMB5SMM5HF3R6TFKO","target":"record","payload":{"canonical_record":{"source":{"id":"2501.11960","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-21T08:13:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"43854ac72ce68e85a05775565746a14fce4a6a002a5da78364c6929990d4a1cb","abstract_canon_sha256":"39ceb9c6bb39d56f35b4bf5a86a9be0d051359c72472f3aad56a66c3be9a3c8a"},"schema_version":"1.0"},"canonical_sha256":"c66ef30975f2d81ec98ce9cbb8fa6553950e2b1a16a072f04e3d2ebd7ba7e74b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:15.415966Z","signature_b64":"N+x7kefGPae+tJUXe+whZxd5lFA3MWxeSbkH9r/9kFrlHTjA5gA36fjOfZA5UAp7NZMV/OkGRsoAxeouW3j4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c66ef30975f2d81ec98ce9cbb8fa6553950e2b1a16a072f04e3d2ebd7ba7e74b","last_reissued_at":"2026-07-05T11:08:15.415358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:15.415358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.11960","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:08:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wFPgX2d+wRzanJ1zopXQIkeP0WGB5+Xy8s5cyN9iCddPFzjO3cUS4NFlhv23JRqvGkpKgL0N9R615l+G577TCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:49:58.463233Z"},"content_sha256":"a4d96576f023bfdb6e3d573dd94c509918ff2310fc02236d76f487bed030dc5f","schema_version":"1.0","event_id":"sha256:a4d96576f023bfdb6e3d573dd94c509918ff2310fc02236d76f487bed030dc5f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YZXPGCLV6LMB5SMM5HF3R6TFKO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TAD-Bench: A Comprehensive Benchmark for Embedding-Based Text Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Liu, Chen Li, Haolong Xiang, Lianyong Qi, Ming Liu, Rongsheng Li, Sikun Yang, Yang Cao","submitted_at":"2025-01-21T08:13:10Z","abstract_excerpt":"Text anomaly detection is crucial for identifying spam, misinformation, and offensive language in natural language processing tasks. Despite the growing adoption of embedding-based methods, their effectiveness and generalizability across diverse application scenarios remain under-explored. To address this, we present TAD-Bench, a comprehensive benchmark designed to systematically evaluate embedding-based approaches for text anomaly detection. TAD-Bench integrates multiple datasets spanning different domains, combining state-of-the-art embeddings from large language models with a variety of ano"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11960","kind":"arxiv","version":2},"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/2501.11960/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":"2026-07-05T11:08:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k8/GE9Kre5QysLtlSZzZ2N0jnP7Gthq5hQ6g63W+weGkC6GMxk9A0KzfLjggC4VS3ysLGV14KNR+RMpxCuEyBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:49:58.463757Z"},"content_sha256":"896b80b4f5b8a1388c98262ca884571b93d432fb11784f3abb689edec32b27e0","schema_version":"1.0","event_id":"sha256:896b80b4f5b8a1388c98262ca884571b93d432fb11784f3abb689edec32b27e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YZXPGCLV6LMB5SMM5HF3R6TFKO/bundle.json","state_url":"https://pith.science/pith/YZXPGCLV6LMB5SMM5HF3R6TFKO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YZXPGCLV6LMB5SMM5HF3R6TFKO/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":"2026-08-08T11:49:58Z","links":{"resolver":"https://pith.science/pith/YZXPGCLV6LMB5SMM5HF3R6TFKO","bundle":"https://pith.science/pith/YZXPGCLV6LMB5SMM5HF3R6TFKO/bundle.json","state":"https://pith.science/pith/YZXPGCLV6LMB5SMM5HF3R6TFKO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YZXPGCLV6LMB5SMM5HF3R6TFKO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YZXPGCLV6LMB5SMM5HF3R6TFKO","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":"39ceb9c6bb39d56f35b4bf5a86a9be0d051359c72472f3aad56a66c3be9a3c8a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-21T08:13:10Z","title_canon_sha256":"43854ac72ce68e85a05775565746a14fce4a6a002a5da78364c6929990d4a1cb"},"schema_version":"1.0","source":{"id":"2501.11960","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11960","created_at":"2026-07-05T11:08:15Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11960v2","created_at":"2026-07-05T11:08:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11960","created_at":"2026-07-05T11:08:15Z"},{"alias_kind":"pith_short_12","alias_value":"YZXPGCLV6LMB","created_at":"2026-07-05T11:08:15Z"},{"alias_kind":"pith_short_16","alias_value":"YZXPGCLV6LMB5SMM","created_at":"2026-07-05T11:08:15Z"},{"alias_kind":"pith_short_8","alias_value":"YZXPGCLV","created_at":"2026-07-05T11:08:15Z"}],"graph_snapshots":[{"event_id":"sha256:896b80b4f5b8a1388c98262ca884571b93d432fb11784f3abb689edec32b27e0","target":"graph","created_at":"2026-07-05T11:08:15Z","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/2501.11960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text anomaly detection is crucial for identifying spam, misinformation, and offensive language in natural language processing tasks. Despite the growing adoption of embedding-based methods, their effectiveness and generalizability across diverse application scenarios remain under-explored. To address this, we present TAD-Bench, a comprehensive benchmark designed to systematically evaluate embedding-based approaches for text anomaly detection. TAD-Bench integrates multiple datasets spanning different domains, combining state-of-the-art embeddings from large language models with a variety of ano","authors_text":"Bo Liu, Chen Li, Haolong Xiang, Lianyong Qi, Ming Liu, Rongsheng Li, Sikun Yang, Yang Cao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-21T08:13:10Z","title":"TAD-Bench: A Comprehensive Benchmark for Embedding-Based Text Anomaly Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11960","kind":"arxiv","version":2},"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:a4d96576f023bfdb6e3d573dd94c509918ff2310fc02236d76f487bed030dc5f","target":"record","created_at":"2026-07-05T11:08:15Z","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":"39ceb9c6bb39d56f35b4bf5a86a9be0d051359c72472f3aad56a66c3be9a3c8a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-21T08:13:10Z","title_canon_sha256":"43854ac72ce68e85a05775565746a14fce4a6a002a5da78364c6929990d4a1cb"},"schema_version":"1.0","source":{"id":"2501.11960","kind":"arxiv","version":2}},"canonical_sha256":"c66ef30975f2d81ec98ce9cbb8fa6553950e2b1a16a072f04e3d2ebd7ba7e74b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c66ef30975f2d81ec98ce9cbb8fa6553950e2b1a16a072f04e3d2ebd7ba7e74b","first_computed_at":"2026-07-05T11:08:15.415358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:15.415358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N+x7kefGPae+tJUXe+whZxd5lFA3MWxeSbkH9r/9kFrlHTjA5gA36fjOfZA5UAp7NZMV/OkGRsoAxeouW3j4CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:15.415966Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.11960","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4d96576f023bfdb6e3d573dd94c509918ff2310fc02236d76f487bed030dc5f","sha256:896b80b4f5b8a1388c98262ca884571b93d432fb11784f3abb689edec32b27e0"],"state_sha256":"ea5fd74bf2c5656b5729c9abac37fd7f6e2a5f535c799f48c9781bad1d14573f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6JiueBcAz6Dqe9OkrvvqeCGN37qPxcuUMhHpDdBnn3EcPNZtVJL7U5+HRlUoZEh5oPYjzO+xNZlVZcP8/vE0AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:49:58.467681Z","bundle_sha256":"ed29e72df6d0df39fe4db0eb817db5a444c39d81125c5c15d3d505f1366b898b"}}