{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IEXNQOSXMQ3I4VAYRJUVSKZTFD","short_pith_number":"pith:IEXNQOSX","schema_version":"1.0","canonical_sha256":"412ed83a5764368e54188a69592b3328fd2f543044a171df5b6059aa2ab7238f","source":{"kind":"arxiv","id":"2504.11914","version":1},"attestation_state":"computed","paper":{"title":"AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gangshan Wu, Jie Liu, Jie Tang, Yuhao Chao","submitted_at":"2025-04-16T09:48:41Z","abstract_excerpt":"Industrial Anomaly Detection (IAD) poses a formidable challenge due to the scarcity of defective samples, making it imperative to deploy models capable of robust generalization to detect unseen anomalies effectively. Traditional approaches, often constrained by hand-crafted features or domain-specific expert models, struggle to address this limitation, underscoring the need for a paradigm shift. We introduce AnomalyR1, a pioneering framework that leverages VLM-R1, a Multimodal Large Language Model (MLLM) renowned for its exceptional generalization and interpretability, to revolutionize IAD. By"},"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":"2504.11914","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-16T09:48:41Z","cross_cats_sorted":[],"title_canon_sha256":"30f42f9a491a3c58d9a934b60c333027d66780595cd23f3dd7933162c59081b7","abstract_canon_sha256":"66788f620ba24673354d4866a3be96382d8c26910264754425fce2de16c931d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:59.699409Z","signature_b64":"UJXVM1c/sDP+/TS1RIk49NpOgema5TTnA/zfqw20F5WgRELs/w0utjOspHJWxlnaZyLbH7WGitY4Imj22oxuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"412ed83a5764368e54188a69592b3328fd2f543044a171df5b6059aa2ab7238f","last_reissued_at":"2026-07-05T10:49:59.698933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:59.698933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gangshan Wu, Jie Liu, Jie Tang, Yuhao Chao","submitted_at":"2025-04-16T09:48:41Z","abstract_excerpt":"Industrial Anomaly Detection (IAD) poses a formidable challenge due to the scarcity of defective samples, making it imperative to deploy models capable of robust generalization to detect unseen anomalies effectively. Traditional approaches, often constrained by hand-crafted features or domain-specific expert models, struggle to address this limitation, underscoring the need for a paradigm shift. We introduce AnomalyR1, a pioneering framework that leverages VLM-R1, a Multimodal Large Language Model (MLLM) renowned for its exceptional generalization and interpretability, to revolutionize IAD. By"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11914","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/2504.11914/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":"2504.11914","created_at":"2026-07-05T10:49:59.698989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.11914v1","created_at":"2026-07-05T10:49:59.698989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11914","created_at":"2026-07-05T10:49:59.698989+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEXNQOSXMQ3I","created_at":"2026-07-05T10:49:59.698989+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEXNQOSXMQ3I4VAY","created_at":"2026-07-05T10:49:59.698989+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEXNQOSX","created_at":"2026-07-05T10:49:59.698989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":188,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30140","citing_title":"AnomalyAgent: Training-Free Agentic Models for Zero-/Few-Shot Anomaly Detection","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20682","citing_title":"IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13671","citing_title":"AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09850","citing_title":"Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2602.17419","citing_title":"EAGLE: Expert-Augmented Attention Guidance for Tuning-Free Industrial Anomaly Detection in Multimodal Large Language Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2603.13779","citing_title":"AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2603.13054","citing_title":"Topo-R1: Detecting Topological Anomalies via Vision-Language Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10833","citing_title":"MMVIAD: Multi-view Multi-task Video Understanding for Industrial Anomaly Detection","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IEXNQOSXMQ3I4VAYRJUVSKZTFD","json":"https://pith.science/pith/IEXNQOSXMQ3I4VAYRJUVSKZTFD.json","graph_json":"https://pith.science/api/pith-number/IEXNQOSXMQ3I4VAYRJUVSKZTFD/graph.json","events_json":"https://pith.science/api/pith-number/IEXNQOSXMQ3I4VAYRJUVSKZTFD/events.json","paper":"https://pith.science/paper/IEXNQOSX"},"agent_actions":{"view_html":"https://pith.science/pith/IEXNQOSXMQ3I4VAYRJUVSKZTFD","download_json":"https://pith.science/pith/IEXNQOSXMQ3I4VAYRJUVSKZTFD.json","view_paper":"https://pith.science/paper/IEXNQOSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.11914&json=true","fetch_graph":"https://pith.science/api/pith-number/IEXNQOSXMQ3I4VAYRJUVSKZTFD/graph.json","fetch_events":"https://pith.science/api/pith-number/IEXNQOSXMQ3I4VAYRJUVSKZTFD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEXNQOSXMQ3I4VAYRJUVSKZTFD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEXNQOSXMQ3I4VAYRJUVSKZTFD/action/storage_attestation","attest_author":"https://pith.science/pith/IEXNQOSXMQ3I4VAYRJUVSKZTFD/action/author_attestation","sign_citation":"https://pith.science/pith/IEXNQOSXMQ3I4VAYRJUVSKZTFD/action/citation_signature","submit_replication":"https://pith.science/pith/IEXNQOSXMQ3I4VAYRJUVSKZTFD/action/replication_record"}},"created_at":"2026-07-05T10:49:59.698989+00:00","updated_at":"2026-07-05T10:49:59.698989+00:00"}