{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XFTJAAUUUSPONE7XVTGRMGFPGB","short_pith_number":"pith:XFTJAAUU","schema_version":"1.0","canonical_sha256":"b966900294a49ee693f7accd1618af305cc8270d538697cff00cf6c72f81c1c0","source":{"kind":"arxiv","id":"2507.02664","version":2},"attestation_state":"computed","paper":{"title":"AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiayi Ji, Ke Sun, Ke Yan, Rongrong Ji, Shouhong Ding, Xiaoshuai Sun, Yuanchen Wu, Yunpeng Luo, Yunsheng Wu, Ziyin Zhou","submitted_at":"2025-07-03T14:26:31Z","abstract_excerpt":"The rapid development of AI-generated content (AIGC) technology has led to the misuse of highly realistic AI-generated images (AIGI) in spreading misinformation, posing a threat to public information security. Although existing AIGI detection techniques are generally effective, they face two issues: 1) a lack of human-verifiable explanations, and 2) a lack of generalization in the latest generation technology. To address these issues, we introduce a large-scale and comprehensive dataset, Holmes-Set, which includes the Holmes-SFTSet, an instruction-tuning dataset with explanations on whether im"},"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":"2507.02664","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T14:26:31Z","cross_cats_sorted":[],"title_canon_sha256":"ed0f5f799f2fa55fd1393db591199688f7df34be41dffabd3fcf9a0625cd6a25","abstract_canon_sha256":"fb90750c076c5f9dfff723df04811f3876f25138af6028a4c9ff3141fe710b6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:33.975986Z","signature_b64":"IV/y2zAqujh6M1N9BjHT5HCgCBC3Y43pk6erEVwQ/XJ0IsIVAARqgoI4O2MWb13qKPaDjvHKhTsfnbO9PbqoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b966900294a49ee693f7accd1618af305cc8270d538697cff00cf6c72f81c1c0","last_reissued_at":"2026-07-05T11:32:33.974770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:33.974770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiayi Ji, Ke Sun, Ke Yan, Rongrong Ji, Shouhong Ding, Xiaoshuai Sun, Yuanchen Wu, Yunpeng Luo, Yunsheng Wu, Ziyin Zhou","submitted_at":"2025-07-03T14:26:31Z","abstract_excerpt":"The rapid development of AI-generated content (AIGC) technology has led to the misuse of highly realistic AI-generated images (AIGI) in spreading misinformation, posing a threat to public information security. Although existing AIGI detection techniques are generally effective, they face two issues: 1) a lack of human-verifiable explanations, and 2) a lack of generalization in the latest generation technology. To address these issues, we introduce a large-scale and comprehensive dataset, Holmes-Set, which includes the Holmes-SFTSet, an instruction-tuning dataset with explanations on whether im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02664","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.02664/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":"2507.02664","created_at":"2026-07-05T11:32:33.975429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02664v2","created_at":"2026-07-05T11:32:33.975429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02664","created_at":"2026-07-05T11:32:33.975429+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFTJAAUUUSPO","created_at":"2026-07-05T11:32:33.975429+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFTJAAUUUSPONE7X","created_at":"2026-07-05T11:32:33.975429+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFTJAAUU","created_at":"2026-07-05T11:32:33.975429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26552","citing_title":"Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08634","citing_title":"SSAFE: Simple and Strong AI-Generated Image Detection via Frozen Vision Encoders","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26421","citing_title":"HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16080","citing_title":"ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00181","citing_title":"From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detection","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2602.01738","citing_title":"Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Models","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23951","citing_title":"HunyuanImage 3.0 Technical Report","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27903","citing_title":"HiMix: Hierarchical Artifact-aware Mixup for Generalized Synthetic Image Detection","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12353","citing_title":"Combating Pattern and Content Bias: Adversarial Feature Learning for Generalized AI-Generated Image Detection","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16987","citing_title":"DVAR: Adversarial Multi-Agent Debate for Video Authenticity Detection","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21904","citing_title":"UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFTJAAUUUSPONE7XVTGRMGFPGB","json":"https://pith.science/pith/XFTJAAUUUSPONE7XVTGRMGFPGB.json","graph_json":"https://pith.science/api/pith-number/XFTJAAUUUSPONE7XVTGRMGFPGB/graph.json","events_json":"https://pith.science/api/pith-number/XFTJAAUUUSPONE7XVTGRMGFPGB/events.json","paper":"https://pith.science/paper/XFTJAAUU"},"agent_actions":{"view_html":"https://pith.science/pith/XFTJAAUUUSPONE7XVTGRMGFPGB","download_json":"https://pith.science/pith/XFTJAAUUUSPONE7XVTGRMGFPGB.json","view_paper":"https://pith.science/paper/XFTJAAUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02664&json=true","fetch_graph":"https://pith.science/api/pith-number/XFTJAAUUUSPONE7XVTGRMGFPGB/graph.json","fetch_events":"https://pith.science/api/pith-number/XFTJAAUUUSPONE7XVTGRMGFPGB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFTJAAUUUSPONE7XVTGRMGFPGB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFTJAAUUUSPONE7XVTGRMGFPGB/action/storage_attestation","attest_author":"https://pith.science/pith/XFTJAAUUUSPONE7XVTGRMGFPGB/action/author_attestation","sign_citation":"https://pith.science/pith/XFTJAAUUUSPONE7XVTGRMGFPGB/action/citation_signature","submit_replication":"https://pith.science/pith/XFTJAAUUUSPONE7XVTGRMGFPGB/action/replication_record"}},"created_at":"2026-07-05T11:32:33.975429+00:00","updated_at":"2026-07-05T11:32:33.975429+00:00"}