{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BOFEDZ4IZASR7E24FUR5NXUX2Y","short_pith_number":"pith:BOFEDZ4I","schema_version":"1.0","canonical_sha256":"0b8a41e788c8251f935c2d23d6de97d618b542eafc51a3cd8075e5148417beaf","source":{"kind":"arxiv","id":"2606.26552","version":1},"attestation_state":"computed","paper":{"title":"Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fei Huang, Fei Wu, Jingren Zhou, Keyu Yan, Rong Zhang, Yangjun Wu, Yu Liu, Zhou Zhao","submitted_at":"2026-06-25T02:59:33Z","abstract_excerpt":"The rapid advancement of generative models presents a significant challenge to existing deepfake detection methods, particularly given the widespread dissemination of highly realistic AI-generated images. Although Multimodal Large Language Models (MLLMs) show strong potential for this task, existing approaches suffer from two key limitations: insufficient sensitivity to fine-grained forensic artifacts and reliance on static synthetic supervision from frontier models, leading to limited flexibility and high-cost. To address these issues, we propose ForeAgent, an agentic forensics framework for "},"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":"2606.26552","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T02:59:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8932c216092df2ac34987d73e06d36ce228ace101f7e66d41736ba118f76d373","abstract_canon_sha256":"3b032f6673e3fa2fd6d44ea699af36748d254b4f4d82bef03fc848b36b879806"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:34.430788Z","signature_b64":"PAHFUYlY5eEkq8NiFGinmbFVvjhSjqM59MDKaqb84ZzigSXM0H2oiu+cpUT6ZDL+hrrbVOLlkUfzSGmcYeErBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b8a41e788c8251f935c2d23d6de97d618b542eafc51a3cd8075e5148417beaf","last_reissued_at":"2026-06-26T01:15:34.430365Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:34.430365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fei Huang, Fei Wu, Jingren Zhou, Keyu Yan, Rong Zhang, Yangjun Wu, Yu Liu, Zhou Zhao","submitted_at":"2026-06-25T02:59:33Z","abstract_excerpt":"The rapid advancement of generative models presents a significant challenge to existing deepfake detection methods, particularly given the widespread dissemination of highly realistic AI-generated images. Although Multimodal Large Language Models (MLLMs) show strong potential for this task, existing approaches suffer from two key limitations: insufficient sensitivity to fine-grained forensic artifacts and reliance on static synthetic supervision from frontier models, leading to limited flexibility and high-cost. To address these issues, we propose ForeAgent, an agentic forensics framework for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26552","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/2606.26552/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":"2606.26552","created_at":"2026-06-26T01:15:34.430429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26552v1","created_at":"2026-06-26T01:15:34.430429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26552","created_at":"2026-06-26T01:15:34.430429+00:00"},{"alias_kind":"pith_short_12","alias_value":"BOFEDZ4IZASR","created_at":"2026-06-26T01:15:34.430429+00:00"},{"alias_kind":"pith_short_16","alias_value":"BOFEDZ4IZASR7E24","created_at":"2026-06-26T01:15:34.430429+00:00"},{"alias_kind":"pith_short_8","alias_value":"BOFEDZ4I","created_at":"2026-06-26T01:15:34.430429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BOFEDZ4IZASR7E24FUR5NXUX2Y","json":"https://pith.science/pith/BOFEDZ4IZASR7E24FUR5NXUX2Y.json","graph_json":"https://pith.science/api/pith-number/BOFEDZ4IZASR7E24FUR5NXUX2Y/graph.json","events_json":"https://pith.science/api/pith-number/BOFEDZ4IZASR7E24FUR5NXUX2Y/events.json","paper":"https://pith.science/paper/BOFEDZ4I"},"agent_actions":{"view_html":"https://pith.science/pith/BOFEDZ4IZASR7E24FUR5NXUX2Y","download_json":"https://pith.science/pith/BOFEDZ4IZASR7E24FUR5NXUX2Y.json","view_paper":"https://pith.science/paper/BOFEDZ4I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26552&json=true","fetch_graph":"https://pith.science/api/pith-number/BOFEDZ4IZASR7E24FUR5NXUX2Y/graph.json","fetch_events":"https://pith.science/api/pith-number/BOFEDZ4IZASR7E24FUR5NXUX2Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BOFEDZ4IZASR7E24FUR5NXUX2Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BOFEDZ4IZASR7E24FUR5NXUX2Y/action/storage_attestation","attest_author":"https://pith.science/pith/BOFEDZ4IZASR7E24FUR5NXUX2Y/action/author_attestation","sign_citation":"https://pith.science/pith/BOFEDZ4IZASR7E24FUR5NXUX2Y/action/citation_signature","submit_replication":"https://pith.science/pith/BOFEDZ4IZASR7E24FUR5NXUX2Y/action/replication_record"}},"created_at":"2026-06-26T01:15:34.430429+00:00","updated_at":"2026-06-26T01:15:34.430429+00:00"}