{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YZXPGCLV6LMB5SMM5HF3R6TFKO","short_pith_number":"pith:YZXPGCLV","schema_version":"1.0","canonical_sha256":"c66ef30975f2d81ec98ce9cbb8fa6553950e2b1a16a072f04e3d2ebd7ba7e74b","source":{"kind":"arxiv","id":"2501.11960","version":2},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.11960","created_at":"2026-07-05T11:08:15.415419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11960v2","created_at":"2026-07-05T11:08:15.415419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11960","created_at":"2026-07-05T11:08:15.415419+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZXPGCLV6LMB","created_at":"2026-07-05T11:08:15.415419+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZXPGCLV6LMB5SMM","created_at":"2026-07-05T11:08:15.415419+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZXPGCLV","created_at":"2026-07-05T11:08:15.415419+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20019","citing_title":"Anomaly Detection in Human Language via Meta-Learning: A Few-Shot Approach","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YZXPGCLV6LMB5SMM5HF3R6TFKO","json":"https://pith.science/pith/YZXPGCLV6LMB5SMM5HF3R6TFKO.json","graph_json":"https://pith.science/api/pith-number/YZXPGCLV6LMB5SMM5HF3R6TFKO/graph.json","events_json":"https://pith.science/api/pith-number/YZXPGCLV6LMB5SMM5HF3R6TFKO/events.json","paper":"https://pith.science/paper/YZXPGCLV"},"agent_actions":{"view_html":"https://pith.science/pith/YZXPGCLV6LMB5SMM5HF3R6TFKO","download_json":"https://pith.science/pith/YZXPGCLV6LMB5SMM5HF3R6TFKO.json","view_paper":"https://pith.science/paper/YZXPGCLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11960&json=true","fetch_graph":"https://pith.science/api/pith-number/YZXPGCLV6LMB5SMM5HF3R6TFKO/graph.json","fetch_events":"https://pith.science/api/pith-number/YZXPGCLV6LMB5SMM5HF3R6TFKO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZXPGCLV6LMB5SMM5HF3R6TFKO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZXPGCLV6LMB5SMM5HF3R6TFKO/action/storage_attestation","attest_author":"https://pith.science/pith/YZXPGCLV6LMB5SMM5HF3R6TFKO/action/author_attestation","sign_citation":"https://pith.science/pith/YZXPGCLV6LMB5SMM5HF3R6TFKO/action/citation_signature","submit_replication":"https://pith.science/pith/YZXPGCLV6LMB5SMM5HF3R6TFKO/action/replication_record"}},"created_at":"2026-07-05T11:08:15.415419+00:00","updated_at":"2026-07-05T11:08:15.415419+00:00"}