{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JSIQAZ2YBZLCW7F4WZDZDZAKCF","short_pith_number":"pith:JSIQAZ2Y","schema_version":"1.0","canonical_sha256":"4c910067580e562b7cbcb64791e40a1152c18d45738994a64854768f387e3b00","source":{"kind":"arxiv","id":"2605.16080","version":1},"attestation_state":"computed","paper":{"title":"ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Zhang, Qing Huang, Xiangyu Yu, Xuanyu Zhang, Zhipei Xu","submitted_at":"2026-05-15T15:43:44Z","abstract_excerpt":"The rise of AI-generated images (AIGIs) poses growing challenges for digital authenticity, prompting the need for efficient, generalizable image forgery detection systems. Existing methods, whether non-LLM-based or LLM-based, exhibit distinct advantages and limitations. While non-LLM-based models offer efficient low-level artifact detection, they often lack semantic understanding. Conversely, LLM-based methods provide strong semantic reasoning and explainability but are computationally intensive and less sensitive to subtle visual artifacts. Moreover, the true contribution of explanatory reaso"},"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":"2605.16080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T15:43:44Z","cross_cats_sorted":[],"title_canon_sha256":"39ac3409289d36c311c4ebcbefd725b94c8c1ce7180b8e8217b445d573e81fb6","abstract_canon_sha256":"1d9c24ddd682ad49078240d212d61dc3d0e6a69cb566f730dce0473628cba895"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:51.827964Z","signature_b64":"aEMgqSrhxk/y0jDKdOSu6y+7zYbbPWP48ocIkRl5i7ZMnBl4Fnnb7F18VVZbO6xXJmSKvfDrK+ZNPTXcEqAjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c910067580e562b7cbcb64791e40a1152c18d45738994a64854768f387e3b00","last_reissued_at":"2026-05-20T00:01:51.827259Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:51.827259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Zhang, Qing Huang, Xiangyu Yu, Xuanyu Zhang, Zhipei Xu","submitted_at":"2026-05-15T15:43:44Z","abstract_excerpt":"The rise of AI-generated images (AIGIs) poses growing challenges for digital authenticity, prompting the need for efficient, generalizable image forgery detection systems. Existing methods, whether non-LLM-based or LLM-based, exhibit distinct advantages and limitations. While non-LLM-based models offer efficient low-level artifact detection, they often lack semantic understanding. Conversely, LLM-based methods provide strong semantic reasoning and explainability but are computationally intensive and less sensitive to subtle visual artifacts. Moreover, the true contribution of explanatory reaso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16080","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/2605.16080/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:41.537469Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.505553Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"c29676544a80832a6c38e6666e22a577539135277f8cef924938a8ba8860204f"},"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":"2605.16080","created_at":"2026-05-20T00:01:51.827363+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16080v1","created_at":"2026-05-20T00:01:51.827363+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16080","created_at":"2026-05-20T00:01:51.827363+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSIQAZ2YBZLC","created_at":"2026-05-20T00:01:51.827363+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSIQAZ2YBZLCW7F4","created_at":"2026-05-20T00:01:51.827363+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSIQAZ2Y","created_at":"2026-05-20T00:01:51.827363+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/JSIQAZ2YBZLCW7F4WZDZDZAKCF","json":"https://pith.science/pith/JSIQAZ2YBZLCW7F4WZDZDZAKCF.json","graph_json":"https://pith.science/api/pith-number/JSIQAZ2YBZLCW7F4WZDZDZAKCF/graph.json","events_json":"https://pith.science/api/pith-number/JSIQAZ2YBZLCW7F4WZDZDZAKCF/events.json","paper":"https://pith.science/paper/JSIQAZ2Y"},"agent_actions":{"view_html":"https://pith.science/pith/JSIQAZ2YBZLCW7F4WZDZDZAKCF","download_json":"https://pith.science/pith/JSIQAZ2YBZLCW7F4WZDZDZAKCF.json","view_paper":"https://pith.science/paper/JSIQAZ2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16080&json=true","fetch_graph":"https://pith.science/api/pith-number/JSIQAZ2YBZLCW7F4WZDZDZAKCF/graph.json","fetch_events":"https://pith.science/api/pith-number/JSIQAZ2YBZLCW7F4WZDZDZAKCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSIQAZ2YBZLCW7F4WZDZDZAKCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSIQAZ2YBZLCW7F4WZDZDZAKCF/action/storage_attestation","attest_author":"https://pith.science/pith/JSIQAZ2YBZLCW7F4WZDZDZAKCF/action/author_attestation","sign_citation":"https://pith.science/pith/JSIQAZ2YBZLCW7F4WZDZDZAKCF/action/citation_signature","submit_replication":"https://pith.science/pith/JSIQAZ2YBZLCW7F4WZDZDZAKCF/action/replication_record"}},"created_at":"2026-05-20T00:01:51.827363+00:00","updated_at":"2026-05-20T00:01:51.827363+00:00"}