{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MFY57QK7ULKKTK6PFNMYNRKJAF","short_pith_number":"pith:MFY57QK7","schema_version":"1.0","canonical_sha256":"6171dfc15fa2d4a9abcf2b5986c549015cf06dd5a44d239113ddb5e774c33230","source":{"kind":"arxiv","id":"2603.17343","version":2},"attestation_state":"computed","paper":{"title":"EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Zhu, Ching-Chun Chang, Isao Echizen, Jun Liu, Maorong Wang","submitted_at":"2026-03-18T04:14:40Z","abstract_excerpt":"The rapid proliferation of AI-Generated Images (AIGIs) poses severe misinformation risks, making AIGI detection critical yet challenging. Traditional detection paradigms mainly rely on low-level features, whereas recent research increasingly focuses on leveraging the general understanding ability of Multimodal Large Language Models (MLLMs) to achieve better generalization, yet it still suffers from limited extensibility and expensive data annotations. Instead of building yet another detector, we recast AIGI detection as learned, reasoning-based evidence synthesis over a pool of heterogeneous o"},"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":"2603.17343","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-18T04:14:40Z","cross_cats_sorted":[],"title_canon_sha256":"67f462b461be39a02dff3054b0e090d2ed5cfa4da234652f26a54efc2cb2a14e","abstract_canon_sha256":"2b86de324141da5e0d94e58bf4f3ec7a05334249a3a53bcb289d353ad388d278"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:20:56.614214Z","signature_b64":"gjthZVs1oFGv7MtQpV/dDi84ulVjc411+pYZo6VTPizQn1nJ7yNnHTfVVPcoL+MXDpUyjGzNYXusRihOU9SwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6171dfc15fa2d4a9abcf2b5986c549015cf06dd5a44d239113ddb5e774c33230","last_reissued_at":"2026-07-14T01:20:56.613327Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:20:56.613327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Zhu, Ching-Chun Chang, Isao Echizen, Jun Liu, Maorong Wang","submitted_at":"2026-03-18T04:14:40Z","abstract_excerpt":"The rapid proliferation of AI-Generated Images (AIGIs) poses severe misinformation risks, making AIGI detection critical yet challenging. Traditional detection paradigms mainly rely on low-level features, whereas recent research increasingly focuses on leveraging the general understanding ability of Multimodal Large Language Models (MLLMs) to achieve better generalization, yet it still suffers from limited extensibility and expensive data annotations. Instead of building yet another detector, we recast AIGI detection as learned, reasoning-based evidence synthesis over a pool of heterogeneous o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.17343","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/2603.17343/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":"2603.17343","created_at":"2026-07-14T01:20:56.613757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.17343v2","created_at":"2026-07-14T01:20:56.613757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.17343","created_at":"2026-07-14T01:20:56.613757+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFY57QK7ULKK","created_at":"2026-07-14T01:20:56.613757+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFY57QK7ULKKTK6P","created_at":"2026-07-14T01:20:56.613757+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFY57QK7","created_at":"2026-07-14T01:20:56.613757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.14091","citing_title":"Venus-DeFakerOne: Unified Fake Image Detection & Localization","ref_index":216,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MFY57QK7ULKKTK6PFNMYNRKJAF","json":"https://pith.science/pith/MFY57QK7ULKKTK6PFNMYNRKJAF.json","graph_json":"https://pith.science/api/pith-number/MFY57QK7ULKKTK6PFNMYNRKJAF/graph.json","events_json":"https://pith.science/api/pith-number/MFY57QK7ULKKTK6PFNMYNRKJAF/events.json","paper":"https://pith.science/paper/MFY57QK7"},"agent_actions":{"view_html":"https://pith.science/pith/MFY57QK7ULKKTK6PFNMYNRKJAF","download_json":"https://pith.science/pith/MFY57QK7ULKKTK6PFNMYNRKJAF.json","view_paper":"https://pith.science/paper/MFY57QK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.17343&json=true","fetch_graph":"https://pith.science/api/pith-number/MFY57QK7ULKKTK6PFNMYNRKJAF/graph.json","fetch_events":"https://pith.science/api/pith-number/MFY57QK7ULKKTK6PFNMYNRKJAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFY57QK7ULKKTK6PFNMYNRKJAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFY57QK7ULKKTK6PFNMYNRKJAF/action/storage_attestation","attest_author":"https://pith.science/pith/MFY57QK7ULKKTK6PFNMYNRKJAF/action/author_attestation","sign_citation":"https://pith.science/pith/MFY57QK7ULKKTK6PFNMYNRKJAF/action/citation_signature","submit_replication":"https://pith.science/pith/MFY57QK7ULKKTK6PFNMYNRKJAF/action/replication_record"}},"created_at":"2026-07-14T01:20:56.613757+00:00","updated_at":"2026-07-14T01:20:56.613757+00:00"}