{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6S2SUO3Y7P5MRKEO6MWS6IEFE7","short_pith_number":"pith:6S2SUO3Y","schema_version":"1.0","canonical_sha256":"f4b52a3b78fbfac8a88ef32d2f208527d63a6da28b89c93b9b3fa8b705df5c37","source":{"kind":"arxiv","id":"2412.04867","version":1},"attestation_state":"computed","paper":{"title":"MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objects","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongdong Fan, Donglin Di, Kai Yi, Lei Fan, Maurice Pagnucco, Yang Song, Yiwen Ding, Zhiguang Hu","submitted_at":"2024-12-06T09:01:10Z","abstract_excerpt":"We present MANTA, a visual-text anomaly detection dataset for tiny objects. The visual component comprises over 137.3K images across 38 object categories spanning five typical domains, of which 8.6K images are labeled as anomalous with pixel-level annotations. Each image is captured from five distinct viewpoints to ensure comprehensive object coverage. The text component consists of two subsets: Declarative Knowledge, including 875 words that describe common anomalies across various domains and specific categories, with detailed explanations for < what, why, how>, including causes and visual c"},"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":"2412.04867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T09:01:10Z","cross_cats_sorted":[],"title_canon_sha256":"d35ac6dd7984501ed8bee915aea4063d144ac5eaf8a710b2d6e791aa99989d6c","abstract_canon_sha256":"6f802ad0edb90b474a2bc71d61da7a6ba6b4f2c648dbdd46b95eff7697197860"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:25.117108Z","signature_b64":"J/iz3YUt412fM3kLgpbtl4m00GdTKeaow6qxDEVNAhgxHEvqyttY/31Tt3EdLU+/5A96tB7SxwilpJqWO83ADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4b52a3b78fbfac8a88ef32d2f208527d63a6da28b89c93b9b3fa8b705df5c37","last_reissued_at":"2026-07-05T09:45:25.116528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:25.116528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objects","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongdong Fan, Donglin Di, Kai Yi, Lei Fan, Maurice Pagnucco, Yang Song, Yiwen Ding, Zhiguang Hu","submitted_at":"2024-12-06T09:01:10Z","abstract_excerpt":"We present MANTA, a visual-text anomaly detection dataset for tiny objects. The visual component comprises over 137.3K images across 38 object categories spanning five typical domains, of which 8.6K images are labeled as anomalous with pixel-level annotations. Each image is captured from five distinct viewpoints to ensure comprehensive object coverage. The text component consists of two subsets: Declarative Knowledge, including 875 words that describe common anomalies across various domains and specific categories, with detailed explanations for < what, why, how>, including causes and visual c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04867","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/2412.04867/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":"2412.04867","created_at":"2026-07-05T09:45:25.116586+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04867v1","created_at":"2026-07-05T09:45:25.116586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04867","created_at":"2026-07-05T09:45:25.116586+00:00"},{"alias_kind":"pith_short_12","alias_value":"6S2SUO3Y7P5M","created_at":"2026-07-05T09:45:25.116586+00:00"},{"alias_kind":"pith_short_16","alias_value":"6S2SUO3Y7P5MRKEO","created_at":"2026-07-05T09:45:25.116586+00:00"},{"alias_kind":"pith_short_8","alias_value":"6S2SUO3Y","created_at":"2026-07-05T09:45:25.116586+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07939","citing_title":"SAGE: A Visual Language Model for Anomaly Detection via Fact Enhancement and Entropy-aware Alignment","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6S2SUO3Y7P5MRKEO6MWS6IEFE7","json":"https://pith.science/pith/6S2SUO3Y7P5MRKEO6MWS6IEFE7.json","graph_json":"https://pith.science/api/pith-number/6S2SUO3Y7P5MRKEO6MWS6IEFE7/graph.json","events_json":"https://pith.science/api/pith-number/6S2SUO3Y7P5MRKEO6MWS6IEFE7/events.json","paper":"https://pith.science/paper/6S2SUO3Y"},"agent_actions":{"view_html":"https://pith.science/pith/6S2SUO3Y7P5MRKEO6MWS6IEFE7","download_json":"https://pith.science/pith/6S2SUO3Y7P5MRKEO6MWS6IEFE7.json","view_paper":"https://pith.science/paper/6S2SUO3Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04867&json=true","fetch_graph":"https://pith.science/api/pith-number/6S2SUO3Y7P5MRKEO6MWS6IEFE7/graph.json","fetch_events":"https://pith.science/api/pith-number/6S2SUO3Y7P5MRKEO6MWS6IEFE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6S2SUO3Y7P5MRKEO6MWS6IEFE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6S2SUO3Y7P5MRKEO6MWS6IEFE7/action/storage_attestation","attest_author":"https://pith.science/pith/6S2SUO3Y7P5MRKEO6MWS6IEFE7/action/author_attestation","sign_citation":"https://pith.science/pith/6S2SUO3Y7P5MRKEO6MWS6IEFE7/action/citation_signature","submit_replication":"https://pith.science/pith/6S2SUO3Y7P5MRKEO6MWS6IEFE7/action/replication_record"}},"created_at":"2026-07-05T09:45:25.116586+00:00","updated_at":"2026-07-05T09:45:25.116586+00:00"}