{"as_of":"2026-08-08T16:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:24738fa8e2c267cddecb138954f21b56beb13328f0316f022da63885a8c6c2ff","coverage":[{"denominator":56,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":56,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T12:40:09.145482Z","state":"measured"},{"denominator":61,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":61,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":5,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":5,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-11T23:45:43.436443Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-16T22:01:17.994037Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"cited_work":{"arxiv_id":"2507.21619","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.21619","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Emit: Enhancing mllms for industrial anomaly detection via difficulty-aware grpo","venue":null,"work_id":"740ff6d4-7a21-44fb-b0fe-cdaf59ffceab","year":2025},"citing_paper":{"arxiv_id":"2512.13671","last_updated":"2026-04-14T17:48:11Z","snapshot_observed_at":"2026-07-06T22:39:04.164003Z","submitted_at":"2025-12-15T18:57:04Z","title":"AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentation","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-16T21:58:58.999285Z"},"links":{"cited_paper":"/paper/2507.21619","citing_paper":"/paper/2512.13671"},"observation_digest":"sha256:520b5db8b34166199bf252bee54736cf976cd55acdaada1f38bce413d3a6cc88","observation_id":"27310443-1a63-48a8-ae42-de2b7e9b7d36","resolution":{"observed_at":"2026-05-16T22:01:17.995692Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"cited_work":{"arxiv_id":"2507.21619","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.21619","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Emit: Enhancing mllms for industrial anomaly detection via difficulty-aware grpo","venue":null,"work_id":"740ff6d4-7a21-44fb-b0fe-cdaf59ffceab","year":2025},"citing_paper":{"arxiv_id":"2602.17419","last_updated":"2026-05-07T12:09:13Z","snapshot_observed_at":"2026-07-06T22:46:26.082843Z","submitted_at":"2026-02-19T14:50:58Z","title":"EAGLE: Expert-Augmented Attention Guidance for Tuning-Free Industrial Anomaly Detection in Multimodal Large Language Models","version":4},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-15T21:05:11.117495Z"},"links":{"cited_paper":"/paper/2507.21619","citing_paper":"/paper/2602.17419"},"observation_digest":"sha256:8764208fd26e569cc7225a400da2157244d20b9734fd27dfea7347693b153281","observation_id":"51d0c095-f704-4f28-9341-ee3fe27bb331","resolution":{"observed_at":"2026-05-15T21:06:38.083776Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"cited_work":{"arxiv_id":"2507.21619","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.21619","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Emit: Enhancing mllms for industrial anomaly detection via difficulty-aware grpo","venue":null,"work_id":"740ff6d4-7a21-44fb-b0fe-cdaf59ffceab","year":2025},"citing_paper":{"arxiv_id":"2603.13779","last_updated":"2026-04-21T06:55:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-03-14T06:14:44Z","title":"AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-15T11:54:18.587529Z"},"links":{"cited_paper":"/paper/2507.21619","citing_paper":"/paper/2603.13779"},"observation_digest":"sha256:1a1e4c4e469bd483e80794adbe92a445474c849eebec7dc95ac87ad0c9a01a58","observation_id":"cd7770c5-3f7f-44ba-8e0f-234ec69dbf17","resolution":{"observed_at":"2026-05-15T11:55:33.336832Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"cited_work":{"arxiv_id":"2507.21619","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.21619","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Emit: Enhancing mllms for industrial anomaly detection via difficulty-aware grpo","venue":null,"work_id":"740ff6d4-7a21-44fb-b0fe-cdaf59ffceab","year":2025},"citing_paper":{"arxiv_id":"2604.07413","last_updated":"2026-04-12T03:02:53Z","snapshot_observed_at":"2026-08-02T10:54:24.843668Z","submitted_at":"2026-04-08T12:23:27Z","title":"FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-10T19:24:23.367540Z"},"links":{"cited_paper":"/paper/2507.21619","citing_paper":"/paper/2604.07413"},"observation_digest":"sha256:aa6ebc1b50909e57b44c86a29fb2a2df7a36b98166b70ebc5d20dbd8ff26bcbe","observation_id":"b1cba8b3-4987-42a7-95aa-23c071131261","resolution":{"observed_at":"2026-05-10T23:00:50.195071Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.21619","snapshot_observed_at":"2026-07-11T23:45:43.436443Z","title":"arXiv preprint arXiv:2507.21619 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.03817","last_updated":"2026-07-04T11:05:57Z","snapshot_observed_at":"2026-08-08T07:15:26.115981Z","submitted_at":"2026-07-04T11:05:57Z","title":"Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-11T23:45:43.436443Z"},"links":{"cited_paper":"/paper/2507.21619","citing_paper":"/paper/2607.03817"},"observation_digest":"sha256:0f0d522c25ebacebaa4f7c2553db59ea46aa51cdbd1c5555fca2a70fabc11f7f","observation_id":"8ffa8b25-d671-4500-ad62-b61ec1868b9b","resolution":{"observed_at":"2026-07-11T23:45:43.436443Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2507.21619/citation-record","integrity":"/paper/2507.21619/integrity","json":"/paper/2507.21619/citation-record.json","paper":"/paper/2507.21619"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:08.852129Z","title":", \" * write output.state after.block = add.period write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.852129Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:d5ade9616504b4e4b1229701aa4a95e432d8e58fc32ee900b8ae149f32f170dd","observation_id":"00e221bb-97bc-416e-ae7d-0ca4c02ce789","resolution":{"observed_at":"2026-08-06T12:40:08.852129Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:08.858292Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.858292Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:f0f4eb98901f9f7114b1118727ca7470d1f4f2a8f8cab7b7b579f0d8280e84a7","observation_id":"b7fa2177-ce07-4b4a-8c67-4e7084e877c1","resolution":{"observed_at":"2026-08-06T12:40:08.858292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-06T12:40:08.864234Z","title":"L.; Almeida, D.; Altenschmidt, J.; Altman, S.; Anadkat, S.; et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.864234Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:c71cebeb8a7083ea26d9b2f0a9ebf2c1a88a491c25c29ece558555d8edce9823","observation_id":"7e1efec1-6c4d-471f-a6fc-9bfd3e783d8f","resolution":{"observed_at":"2026-08-06T12:40:08.864234Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.07073","last_updated":"2024-10-10T17:59:16Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-10-09T17:16:22Z","title":"Pixtral 12B","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.07073","snapshot_observed_at":"2026-08-06T12:40:08.869752Z","title":"B.; Bout, B.; Chaplot, D.; Chudnovsky, J.; Costa, D.; Monicault, B","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.869752Z"},"links":{"cited_paper":"/paper/2410.07073","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:2396278fb7b6ac0076711d1446e1948762c08d4ec8ffb048eb4ced95838ca871","observation_id":"aaec8ed6-626d-45ac-82e5-72c0bd482c40","resolution":{"observed_at":"2026-08-06T12:40:08.869752Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.07890","last_updated":"2023-06-18T01:11:04Z","snapshot_observed_at":"2026-08-02T11:43:57.950672Z","submitted_at":"2023-06-13T16:31:02Z","title":"VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.07890","snapshot_observed_at":"2026-08-06T12:40:08.874901Z","title":"G.; Tuzel, O.; Huang, P.; Shan, J.; Shi, J.; and Cao, M","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.874901Z"},"links":{"cited_paper":"/paper/2306.07890","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:1e2ecaec5629f7a7e90aaee72836d2f5cc59cd66936f0bb3ca98d218e6b2236f","observation_id":"6f022aee-9599-42ec-91ec-e0fefbe08d6e","resolution":{"observed_at":"2026-08-06T12:40:08.874901Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13923","last_updated":"2025-02-19T18:00:14Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-19T18:00:14Z","title":"Qwen2.5-VL Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13923","snapshot_observed_at":"2026-08-06T12:40:08.879879Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.879879Z"},"links":{"cited_paper":"/paper/2502.13923","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:f02d6e08447dbfd65af8adbdd4e10520c3377d1d366a327c3564cdfc8738e6f6","observation_id":"e93dea11-15a1-4d01-bf75-938c5b1d8bfd","resolution":{"observed_at":"2026-08-06T12:40:08.879879Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:08.885209Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.885209Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:b93453b0b6e874b7097c5e49d123f1d514fdc88a2c448904bdbcb0274c892d81","observation_id":"236e4937-1854-43c3-bc16-636291e7c65c","resolution":{"observed_at":"2026-08-06T12:40:08.885209Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:08.890655Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.890655Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:43f78a997c69ae50f8de4de1ee9f135ddfabfe91ee7e12e36eaf2d318ccbc4b9","observation_id":"68b0523e-298e-4129-9b65-e92316cf34c5","resolution":{"observed_at":"2026-08-06T12:40:08.890655Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.444179Z","title":null,"venue":null,"work_id":"67a25c50-9857-46e0-96dc-d6bf22e658da","year":2024},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.896298Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:0bef9dd3c985c29bda9fdd82c1891b229dce2668f3350cfd56cfaff7485b0cc2","observation_id":"35853851-dda4-40e9-9a9e-c85ca3e269dc","resolution":{"observed_at":"2026-08-06T12:40:10.452536Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.11914","last_updated":"2025-04-16T09:48:41Z","snapshot_observed_at":"2026-08-07T16:01:52.576967Z","submitted_at":"2025-04-16T09:48:41Z","title":"AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.11914","snapshot_observed_at":"2026-08-06T12:40:08.901123Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.901123Z"},"links":{"cited_paper":"/paper/2504.11914","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:a1795fa3477c3d539f13f4eba9e8b40417dd754f0dc6ff33aef8e7d1ab279c9b","observation_id":"a9db3fcc-f3cb-4f5c-a685-2d35d9a36ffb","resolution":{"observed_at":"2026-08-06T12:40:08.901123Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.11468","last_updated":"2025-04-10T16:54:05Z","snapshot_observed_at":"2026-08-05T02:57:13.928237Z","submitted_at":"2025-04-10T16:54:05Z","title":"SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.11468","snapshot_observed_at":"2026-08-06T12:40:08.907260Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.907260Z"},"links":{"cited_paper":"/paper/2504.11468","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:9b41f859c4ba2daa690189ea0e0c5181526fde6f8670172507af875ef466433a","observation_id":"2f1f051a-9bf5-45f5-bfb7-ad7af829376f","resolution":{"observed_at":"2026-08-06T12:40:08.907260Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.15795","last_updated":"2025-01-27T05:41:10Z","snapshot_observed_at":"2026-07-06T20:26:31.558337Z","submitted_at":"2025-01-27T05:41:10Z","title":"Can Multimodal Large Language Models be Guided to Improve Industrial Anomaly Detection?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.15795","snapshot_observed_at":"2026-08-06T12:40:08.912929Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.912929Z"},"links":{"cited_paper":"/paper/2501.15795","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:26f000d4c1fb7fc8176d05427d4f16d9c1329476a9f6db487097212daf036b8f","observation_id":"34e8e425-fae2-4883-8d95-e557d56e9e67","resolution":{"observed_at":"2026-08-06T12:40:08.912929Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:08.917690Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.917690Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:d51e645f408e2a371a5f81b3f6c5874b7abb582011f121c53a6d2340c1d65f7d","observation_id":"2ba5473a-01b4-47b6-a103-368106feb191","resolution":{"observed_at":"2026-08-06T12:40:08.917690Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.422044Z","title":null,"venue":null,"work_id":"7a4b984b-2d0a-4252-ba2d-27fee85b31fc","year":2024},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.922276Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:6aa9380f0ce3f2d6e396f9915728bc840999aa8f664e3e50f6ff118e1c2194e5","observation_id":"7f2329c7-ee51-432d-9f8d-8eafe68949b1","resolution":{"observed_at":"2026-08-06T12:40:10.429507Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.04769","last_updated":"2025-07-17T15:16:09Z","snapshot_observed_at":"2026-08-05T13:51:02.330984Z","submitted_at":"2024-12-06T04:31:09Z","title":"Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detection","version":2},"cited_work":{"arxiv_id":"2412.04769","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.04769","snapshot_observed_at":"2026-08-06T12:40:09.786310Z","title":"Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detection","venue":"cs.CV","work_id":"27f72115-50a1-444c-b7f9-84899010d169","year":2024},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.927566Z"},"links":{"cited_paper":"/paper/2412.04769","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:3f8f626928c9922766c96058e08557e9ed9c053cd37805f28f52aea3275f938c","observation_id":"ff02cf4d-2a46-4650-a861-d3845cfaaf4e","resolution":{"observed_at":"2026-08-06T12:40:09.791610Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.394685Z","title":null,"venue":null,"work_id":"c06e2ba7-6514-4762-b1c1-29eedd0123bb","year":2023},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.932617Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:cd3731194ddb485a7b3822d4ab134390ae9e13370172ec2cfacc99338a57a480","observation_id":"c6652989-e577-4694-a2ca-7005ad01f334","resolution":{"observed_at":"2026-08-06T12:40:10.401380Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.372710Z","title":null,"venue":null,"work_id":"1f01218f-e0ef-4135-96a0-b0cfb3bbdecc","year":2024},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.937212Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:3ce11486b73d2819db22bf6dd84ef476fa989a3b42277cf52d2f95059cd56f67","observation_id":"b26f6877-ea85-40ce-9ff2-eb4cda56fc10","resolution":{"observed_at":"2026-08-06T12:40:10.378789Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.355688Z","title":null,"venue":null,"work_id":"d327d529-3046-44d1-bdfc-bb8a34ad81c5","year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.942337Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:2a8dac5ceb43420090c5f088c717b9642c8ebfe7fb4e12eec7752942996c9ed7","observation_id":"e89c7fb9-4743-47e7-adad-bb154a9d8a44","resolution":{"observed_at":"2026-08-06T12:40:10.360380Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.336714Z","title":"X.; Nguyen, A.-N.; Tran, D.-T.; Duong, V.-H.; Mai, A.-T.; Pham, D.-L.; Phan, K.-T.; Do, M.-Q.; Duong, T","venue":null,"work_id":"c756b255-4df0-4993-9a95-050a87fccfa4","year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.947484Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:9d853c51a2f1fb74522410243911186963799f387e584230d4e66277fa67a8d9","observation_id":"e73b8163-f4a0-4484-be53-65d7f07aecfb","resolution":{"observed_at":"2026-08-06T12:40:10.342111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.315092Z","title":null,"venue":null,"work_id":"cca337f0-43f0-4a51-9f7d-9e461676880d","year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.952959Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:6b289b1c42aef977604fe7ea78eb6122cd12dbaa8556a0474824abbeab6e5cec","observation_id":"9a40814f-a810-4fed-8834-84086d62a5f8","resolution":{"observed_at":"2026-08-06T12:40:10.320984Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.291000Z","title":"H.; Bae, K.; and Kang, B","venue":null,"work_id":"e32a7b47-7062-436b-a36a-279a5ee2b7df","year":2024},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.958314Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:bf3f8a1a5e8aad164fa47ea2f05e9a984f1e3bddb4b948904f86c98330984889","observation_id":"5aaba38c-c518-44bd-bad0-a78a97c5e5c1","resolution":{"observed_at":"2026-08-06T12:40:10.298361Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:08.963663Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.963663Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:0235b7d697d2822102437871438e7c2835e4eb5a4e17eea7132520ed0b2bb4ae","observation_id":"142b79de-f94a-4ea8-84ba-20b7fd50ad1b","resolution":{"observed_at":"2026-08-06T12:40:08.963663Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.259676Z","title":null,"venue":null,"work_id":"92dce34a-f6c6-4845-9ba0-5dafe87cf173","year":2021},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.968985Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:49c8d4069d47f01630843fb930cd036c1e62baf44e05aa59f551937517c19087","observation_id":"5cf7a066-025b-4c2b-a35c-28c09e2f7526","resolution":{"observed_at":"2026-08-06T12:40:10.265128Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.09453","last_updated":"2025-02-21T04:50:45Z","snapshot_observed_at":"2026-08-06T23:07:59.630081Z","submitted_at":"2024-10-12T09:16:09Z","title":"MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.09453","snapshot_observed_at":"2026-08-06T12:40:08.974046Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.974046Z"},"links":{"cited_paper":"/paper/2410.09453","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:22e1fa30a56b64d40ba7d13660c316c22b5a3e63d316e7a8cbc470cf67904d18","observation_id":"007bb533-27df-4c62-8e37-bbfb189e3896","resolution":{"observed_at":"2026-08-06T12:40:08.974046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:08.979414Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.979414Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:ca813aca48924014988f95a3ca10319bfad7242f4aabba22d90619f840b5ec17","observation_id":"266db05a-0095-4418-908f-b7326492176b","resolution":{"observed_at":"2026-08-06T12:40:08.979414Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.229549Z","title":null,"venue":null,"work_id":"5051f9d7-9078-4ac8-9f70-8b24fa4ef253","year":2024},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.983826Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:954fad20293c1db29c3c7a38c1190e4760f28c12855e5252015db2855946f510","observation_id":"9d968cc0-595e-4c5c-b79b-01049a331c94","resolution":{"observed_at":"2026-08-06T12:40:10.235881Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.212626Z","title":null,"venue":null,"work_id":"9faf21ab-6e3d-4c20-88ec-81b80466ee9a","year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.989042Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:2c6d005cbbc59f8c39a551673f46df4cf4828dfce2b1a2ff4713a3c6e15a37d6","observation_id":"c8dbd619-02f6-4b04-871b-e4aa6f5cbff9","resolution":{"observed_at":"2026-08-06T12:40:10.218050Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2504.14919","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:09.737244Z","title":null,"venue":null,"work_id":"f488e760-c0ab-478a-a6bf-f860ef419dc3","year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.994082Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:17a1eacc49ded974a1937ddfd3ec8eee0fdaa7765c4a7dcdc2c8007fcdab7648","observation_id":"bb28c23c-e091-4010-901e-4d0c15e9b1f9","resolution":{"observed_at":"2026-08-06T12:40:09.745612Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.03326","last_updated":"2024-10-26T16:35:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-08-06T17:59:44Z","title":"LLaVA-OneVision: Easy Visual Task Transfer","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.03326","snapshot_observed_at":"2026-08-06T12:40:08.998962Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:08.998962Z"},"links":{"cited_paper":"/paper/2408.03326","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:38bcbb9d6d989b0c71e2c70d047107f3b9db96e28a4390afced9d17b9a83b770","observation_id":"f1755db4-efc8-42be-a793-82fe83d168cd","resolution":{"observed_at":"2026-08-06T12:40:08.998962Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07895","last_updated":"2024-07-28T19:58:08Z","snapshot_observed_at":"2026-07-06T18:44:24.873040Z","submitted_at":"2024-07-10T17:59:43Z","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07895","snapshot_observed_at":"2026-08-06T12:40:09.004173Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.004173Z"},"links":{"cited_paper":"/paper/2407.07895","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:9cd7fb4ae10989538e6251cf1f840d50ffeb8267ea0bb2157834e6f0a1e43061","observation_id":"c5af75d5-94d6-40be-ab56-232a5a907760","resolution":{"observed_at":"2026-08-06T12:40:09.004173Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.195571Z","title":null,"venue":null,"work_id":"ed29ed76-f6f5-4a06-a679-1e1066828e34","year":2024},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.009829Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:e7552b4455e954377818c56ef68f2ee092630dc500fb94fa87d98811e1b87ea6","observation_id":"489955fa-f0db-40dd-aab8-7bcd5950611e","resolution":{"observed_at":"2026-08-06T12:40:10.200212Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.12749","last_updated":"2025-04-17T08:41:23Z","snapshot_observed_at":"2026-08-07T16:01:33.828607Z","submitted_at":"2025-04-17T08:41:23Z","title":"LAD-Reasoner: Tiny Multimodal Models are Good Reasoners for Logical Anomaly Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.12749","snapshot_observed_at":"2026-08-06T12:40:09.026068Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.026068Z"},"links":{"cited_paper":"/paper/2504.12749","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:bf43c6731b070cc6b0540e4931cc85246c45ed5fbee1915b271d5a294455749c","observation_id":"1b5a060a-d28d-4eb4-badc-1a12c134e530","resolution":{"observed_at":"2026-08-06T12:40:09.026068Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.19070","last_updated":"2025-01-17T06:13:20Z","snapshot_observed_at":"2026-07-06T16:40:08.030032Z","submitted_at":"2023-10-29T16:49:45Z","title":"Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.19070","snapshot_observed_at":"2026-08-06T12:40:09.030806Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.030806Z"},"links":{"cited_paper":"/paper/2310.19070","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:3b49488bd0db91768dfd28ab9f9e4bd851f14bfda503d2313d9d0c78b97413e0","observation_id":"e1d38f56-05e5-4ca2-b905-e9bc1153908d","resolution":{"observed_at":"2026-08-06T12:40:09.030806Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-06T12:40:09.035569Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.035569Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:5d98ca7b4df03be212349b13b0db5459ca68c8acf2c9b5bbca24b15b019e361e","observation_id":"a7930e1a-a61a-47ff-be98-d60544282e9d","resolution":{"observed_at":"2026-08-06T12:40:09.035569Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.179040Z","title":null,"venue":null,"work_id":"989b9aa4-1c2f-42a0-a031-6ba91757e03f","year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.040959Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:3b2cdd8f35e710f646528baa1550d04bed346460a604338c9983f819770a2594","observation_id":"60f7aea7-46a0-4276-ac8b-3313effe7c7a","resolution":{"observed_at":"2026-08-06T12:40:10.183971Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.158371Z","title":null,"venue":null,"work_id":"503dc91b-0644-4167-929b-feb210abf848","year":2022},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.045775Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:e0ad2f4c97a54569ce32b79ca207093a83a28cf54952c735e0c415b01484cec3","observation_id":"9423b6a8-e601-4784-a642-2f8fa04fa683","resolution":{"observed_at":"2026-08-06T12:40:10.164806Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-08-06T12:40:09.055599Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.055599Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:43488872fb39eb95614033ec25298f8575c273380e7ff3cd0bc35838ca70ae95","observation_id":"5ffa0a77-bb26-47fa-9436-25c1869ed6f9","resolution":{"observed_at":"2026-08-06T12:40:09.055599Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03300","last_updated":"2024-04-27T15:25:53Z","snapshot_observed_at":"2026-08-06T14:58:42.911363Z","submitted_at":"2024-02-05T18:55:32Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-08-06T12:40:09.060733Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.060733Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:0df101c6117d878a88fb5f191f95a3ef6e065157dae90b64f50420a81a148200","observation_id":"49291026-ffd8-495c-a8f5-88184fa11fa3","resolution":{"observed_at":"2026-08-06T12:40:09.060733Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.19786","last_updated":"2025-03-25T15:52:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-03-25T15:52:34Z","title":"Gemma 3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.19786","snapshot_observed_at":"2026-08-06T12:40:09.065678Z","title":"M.; Goedeckemeyer, A.; Saade, A.; Feng, A.; Kolesnikov, A.; Bendebury, A.; Abdagic, A.; Vadi, A.; György, A.; Pinto, A","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.065678Z"},"links":{"cited_paper":"/paper/2503.19786","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:8218fdcc8f7540ff433384eb975888c4d355e0c7a8a112975aa2cf4135ef5650","observation_id":"10d08445-05c6-476d-acbb-f6b8e35c06d7","resolution":{"observed_at":"2026-08-06T12:40:09.065678Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.07491","last_updated":"2025-06-23T13:45:50Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-04-10T06:48:26Z","title":"Kimi-VL Technical Report","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.07491","snapshot_observed_at":"2026-08-06T12:40:09.070461Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.070461Z"},"links":{"cited_paper":"/paper/2504.07491","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:0ee9c88fb8d7d1cb5374278ca572bfc565754100c8358ea575d0fc8c754af892","observation_id":"eef64f66-a01b-4867-a120-9f3264f46d84","resolution":{"observed_at":"2026-08-06T12:40:09.070461Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.01006","last_updated":"2026-01-01T13:07:25Z","snapshot_observed_at":"2026-08-03T18:50:30.558321Z","submitted_at":"2025-07-01T17:55:04Z","title":"GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.01006","snapshot_observed_at":"2026-08-06T12:40:09.075553Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.075553Z"},"links":{"cited_paper":"/paper/2507.01006","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:5de46768a1be5ea1d89d90b5572fa7fd62c39fae39ab256e87b6bf88eaedf518","observation_id":"edabd728-5618-4112-ad4a-022bddbccac1","resolution":{"observed_at":"2026-08-06T12:40:09.075553Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.136492Z","title":null,"venue":null,"work_id":"d45cdc13-b980-4558-9f88-538532f06de2","year":2024},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.080029Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:db40c799cedeac8b0856541e50e424122909a7b6a0b4d79efb5e712ec28af7c3","observation_id":"bc49ce24-5c23-48f2-8f7e-5e0c64f175db","resolution":{"observed_at":"2026-08-06T12:40:10.143145Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.03569","last_updated":"2025-06-04T04:32:54Z","snapshot_observed_at":"2026-08-07T10:57:30.804332Z","submitted_at":"2025-06-04T04:32:54Z","title":"MiMo-VL Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.03569","snapshot_observed_at":"2026-08-06T12:40:09.085046Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.085046Z"},"links":{"cited_paper":"/paper/2506.03569","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:2d458b42e9f3719c947e10ec2165d4a3d4cd89bd851524dc855fe64a991a4fa2","observation_id":"4d8ff12c-2c07-4a63-99f6-b547ba3544cc","resolution":{"observed_at":"2026-08-06T12:40:09.085046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.118950Z","title":"M.; and Dwivedi, I","venue":null,"work_id":"b20d05a5-aa26-46e6-8e1d-fe1eabf5b527","year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.089994Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:fae709d3826f6e9eacd833af3c291ca046e6497bec50f8cde51e4cb019442cbd","observation_id":"f3f5af56-2881-48cb-8682-7106a842be25","resolution":{"observed_at":"2026-08-06T12:40:10.123965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.03373","last_updated":"2025-02-05T17:13:32Z","snapshot_observed_at":"2026-07-06T20:31:41.231839Z","submitted_at":"2025-02-05T17:13:32Z","title":"Demystifying Long Chain-of-Thought Reasoning in LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.03373","snapshot_observed_at":"2026-08-06T12:40:09.094196Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.094196Z"},"links":{"cited_paper":"/paper/2502.03373","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:1ed45fec26da0efbaecf67890f2a447c50bdf3995870be9eb5c72ddd5809930f","observation_id":"f3710da3-0809-49a6-8512-8f7d756894fe","resolution":{"observed_at":"2026-08-06T12:40:09.094196Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.14476","last_updated":"2025-05-20T01:37:34Z","snapshot_observed_at":"2026-08-02T01:40:54.187278Z","submitted_at":"2025-03-18T17:49:06Z","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.14476","snapshot_observed_at":"2026-08-06T12:40:09.098676Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.098676Z"},"links":{"cited_paper":"/paper/2503.14476","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:a34ea1588bc606a4ef3884392a2841d94d907013c132f2a96c7cf923be6d704c","observation_id":"6751c8cb-fbe5-49d6-9c41-68c33b1b09fd","resolution":{"observed_at":"2026-08-06T12:40:09.098676Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.12910","last_updated":"2025-08-18T02:02:38Z","snapshot_observed_at":"2026-08-07T16:58:44.584280Z","submitted_at":"2025-03-17T08:18:55Z","title":"AFR-CLIP: Enhancing Zero-Shot Industrial Anomaly Detection with Stateless-to-Stateful Anomaly Feature Rectification","version":3},"cited_work":{"arxiv_id":"2503.12910","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.12910","snapshot_observed_at":"2026-08-06T12:40:09.369208Z","title":"AFR-CLIP: Enhancing Zero-Shot Industrial Anomaly Detection with Stateless-to-Stateful Anomaly Feature Rectification","venue":"cs.CV","work_id":"36c817a5-39cc-4ead-b770-94fee1dba466","year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.103026Z"},"links":{"cited_paper":"/paper/2503.12910","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:e6c2bdfd9ad34b2cdb546b7882f31bb788a22c1b3fcb41ba2d3cd52210c57f1b","observation_id":"3b75b157-92d3-4b53-b934-bdafdce5508d","resolution":{"observed_at":"2026-08-06T12:40:09.377752Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.19524","last_updated":"2025-04-28T06:52:35Z","snapshot_observed_at":"2026-08-07T15:58:42.590234Z","submitted_at":"2025-04-28T06:52:35Z","title":"LR-IAD:Mask-Free Industrial Anomaly Detection with Logical Reasoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.19524","snapshot_observed_at":"2026-08-06T12:40:09.107647Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.107647Z"},"links":{"cited_paper":"/paper/2504.19524","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:cd42f5529b92656f7edcd891329cf4a7cd17c82524f3aaafdfabd4e0df288794","observation_id":"a606a82d-2e84-4faf-9b0c-f88a7abed14f","resolution":{"observed_at":"2026-08-06T12:40:09.107647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:09.112920Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.112920Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:545229b7f42898a30f9767dd7b5c44972719c0b452d788cf52864f30676eddf0","observation_id":"1819753b-6981-4042-9eb5-c37956694526","resolution":{"observed_at":"2026-08-06T12:40:09.112920Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.089052Z","title":null,"venue":null,"work_id":"6d3d0c06-9cd5-4a46-b9fc-8f967478fc81","year":2024},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.117850Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:6e2d8b01dd4bc945c344c585a6769bdd952b7024f1a25c705f98589ae7fa519c","observation_id":"e03d549c-589b-4ff7-a744-a3fe99a42268","resolution":{"observed_at":"2026-08-06T12:40:10.093907Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.070440Z","title":null,"venue":null,"work_id":"c37830d0-d73b-4135-900d-67d214172e16","year":2024},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.122298Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:1e82fae36e393b9924a795893e53d94619a6431d088791787ec0d4d07c2cac88","observation_id":"b881d835-b58d-455f-a2fb-f01a98b264f0","resolution":{"observed_at":"2026-08-06T12:40:10.076114Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.14162","last_updated":"2025-05-16T15:25:03Z","snapshot_observed_at":"2026-08-07T16:55:09.264799Z","submitted_at":"2025-03-18T11:33:29Z","title":"EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.14162","snapshot_observed_at":"2026-08-06T12:40:09.126875Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.126875Z"},"links":{"cited_paper":"/paper/2503.14162","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:23a5dd7f9b16bbc93d7ff9462697e0b33c9469d522e690d43838a5ffea45b879","observation_id":"1ae09957-90b8-4934-9624-6cb90b19a291","resolution":{"observed_at":"2026-08-06T12:40:09.126875Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.22039","last_updated":"2026-07-29T09:31:57Z","snapshot_observed_at":"2026-08-07T21:55:46.500544Z","submitted_at":"2025-05-28T07:02:15Z","title":"OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.22039","snapshot_observed_at":"2026-08-06T12:40:09.131334Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.131334Z"},"links":{"cited_paper":"/paper/2505.22039","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:c415c081a9ae37c713f24c71b2346e1bebbaa524a4dcc39a1af551d6093ef965","observation_id":"6f400cd3-fb95-49cc-bfa7-d4bede28acbf","resolution":{"observed_at":"2026-08-06T12:40:09.131334Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:09.135705Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.135705Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:1d48419b57a3b9666ccdef4217c94bea3e94dfa68d71021988759241b19197a8","observation_id":"a91e6f93-06e8-4478-805f-c7c37868bae8","resolution":{"observed_at":"2026-08-06T12:40:09.135705Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.10479","last_updated":"2025-04-19T03:47:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-04-14T17:59:25Z","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.10479","snapshot_observed_at":"2026-08-06T12:40:09.140188Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.140188Z"},"links":{"cited_paper":"/paper/2504.10479","citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:b5929fa7c7ee421ba1926d317a9f18220acde3c8e5f29fab87253968bed9b483","observation_id":"2dae77c6-46d6-4cdc-84d7-f2e4269458fb","resolution":{"observed_at":"2026-08-06T12:40:09.140188Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:40:10.049089Z","title":null,"venue":null,"work_id":"03c2551c-a3c6-4f63-8ec1-0621063307b4","year":2022},"citing_paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-06T12:40:09.145482Z"},"links":{"citing_paper":"/paper/2507.21619"},"observation_digest":"sha256:4e2c0ffdc4823dee8b261a464f182a72ea984932a03087cc590742b88c788089","observation_id":"b5232b97-f0a7-49bc-a75d-b157cce370b9","resolution":{"observed_at":"2026-08-06T12:40:10.056240Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.21619","last_updated":"2025-07-29T09:18:22Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T23:36:20.034251Z","submitted_at":"2025-07-29T09:18:22Z","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO"},"reference_resolution":{"displayed":56,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":50,"verified_exact":3,"verified_fuzzy":3},"total_outbound_references":56},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 5 inbound Pith citation observations for arXiv:2507.21619."}