{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3GJQ3V4MVJRUV6Q3JOVNJFOFXL","short_pith_number":"pith:3GJQ3V4M","schema_version":"1.0","canonical_sha256":"d9930dd78caa634afa1b4baad495c5baee8df32c221f00fced29e369375d8a39","source":{"kind":"arxiv","id":"2607.27113","version":1},"attestation_state":"computed","paper":{"title":"Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajian Liu, Chuanbiao Song, Hao Tan, Huijia Zhu, Jun Lan, Jun Wan, Weiqiang Wang, Zhen Lei, Zichang Tan, Zijian Yu","submitted_at":"2026-07-29T16:43:59Z","abstract_excerpt":"The growing capability of image generation models has made synthetic images a routine presence in open media, making robust and generalizable AI-Generated Image (AIGI) detection increasingly essential. While multi-modal large language models (MLLMs) offer a transparent alternative to black-box binary scoring, we observe that current MLLM-based detectors still exhibit notable perception bottlenecks in capturing fine-grained anomalies. They primarily focus on how visual evidence is organized and synthesized, leaving the intrinsic perception less optimized. To mitigate this gap, we present Verita"},"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":"2607.27113","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T16:43:59Z","cross_cats_sorted":[],"title_canon_sha256":"8d3feff10e230fea0d5c9a3e0462d1df2ab1df953381e6204288182d1093de23","abstract_canon_sha256":"4abb55b7f3baa854d485b3a0254098faa97c5a8887bfad5e28de90e3aaa8d3d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9930dd78caa634afa1b4baad495c5baee8df32c221f00fced29e369375d8a39","last_reissued_at":"2026-07-30T01:23:37.243867Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:23:37.243867Z"},"graph_snapshot":{"paper":{"title":"Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajian Liu, Chuanbiao Song, Hao Tan, Huijia Zhu, Jun Lan, Jun Wan, Weiqiang Wang, Zhen Lei, Zichang Tan, Zijian Yu","submitted_at":"2026-07-29T16:43:59Z","abstract_excerpt":"The growing capability of image generation models has made synthetic images a routine presence in open media, making robust and generalizable AI-Generated Image (AIGI) detection increasingly essential. While multi-modal large language models (MLLMs) offer a transparent alternative to black-box binary scoring, we observe that current MLLM-based detectors still exhibit notable perception bottlenecks in capturing fine-grained anomalies. They primarily focus on how visual evidence is organized and synthesized, leaving the intrinsic perception less optimized. To mitigate this gap, we present Verita"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27113","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/2607.27113/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":"2607.27113","created_at":"2026-07-30T01:23:37.248968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27113v1","created_at":"2026-07-30T01:23:37.248968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27113","created_at":"2026-07-30T01:23:37.248968+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GJQ3V4MVJRU","created_at":"2026-07-30T01:23:37.248968+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GJQ3V4MVJRUV6Q3","created_at":"2026-07-30T01:23:37.248968+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GJQ3V4M","created_at":"2026-07-30T01:23:37.248968+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/3GJQ3V4MVJRUV6Q3JOVNJFOFXL","json":"https://pith.science/pith/3GJQ3V4MVJRUV6Q3JOVNJFOFXL.json","graph_json":"https://pith.science/api/pith-number/3GJQ3V4MVJRUV6Q3JOVNJFOFXL/graph.json","events_json":"https://pith.science/api/pith-number/3GJQ3V4MVJRUV6Q3JOVNJFOFXL/events.json","paper":"https://pith.science/paper/3GJQ3V4M"},"agent_actions":{"view_html":"https://pith.science/pith/3GJQ3V4MVJRUV6Q3JOVNJFOFXL","download_json":"https://pith.science/pith/3GJQ3V4MVJRUV6Q3JOVNJFOFXL.json","view_paper":"https://pith.science/paper/3GJQ3V4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27113&json=true","fetch_graph":"https://pith.science/api/pith-number/3GJQ3V4MVJRUV6Q3JOVNJFOFXL/graph.json","fetch_events":"https://pith.science/api/pith-number/3GJQ3V4MVJRUV6Q3JOVNJFOFXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GJQ3V4MVJRUV6Q3JOVNJFOFXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GJQ3V4MVJRUV6Q3JOVNJFOFXL/action/storage_attestation","attest_author":"https://pith.science/pith/3GJQ3V4MVJRUV6Q3JOVNJFOFXL/action/author_attestation","sign_citation":"https://pith.science/pith/3GJQ3V4MVJRUV6Q3JOVNJFOFXL/action/citation_signature","submit_replication":"https://pith.science/pith/3GJQ3V4MVJRUV6Q3JOVNJFOFXL/action/replication_record"}},"created_at":"2026-07-30T01:23:37.248968+00:00","updated_at":"2026-07-30T01:23:37.248968+00:00"}