{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3GJQ3V4MVJRUV6Q3JOVNJFOFXL","short_pith_number":"pith:3GJQ3V4M","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"},"canonical_sha256":"d9930dd78caa634afa1b4baad495c5baee8df32c221f00fced29e369375d8a39","source":{"kind":"arxiv","id":"2607.27113","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27113","created_at":"2026-07-30T01:23:37Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27113v1","created_at":"2026-07-30T01:23:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27113","created_at":"2026-07-30T01:23:37Z"},{"alias_kind":"pith_short_12","alias_value":"3GJQ3V4MVJRU","created_at":"2026-07-30T01:23:37Z"},{"alias_kind":"pith_short_16","alias_value":"3GJQ3V4MVJRUV6Q3","created_at":"2026-07-30T01:23:37Z"},{"alias_kind":"pith_short_8","alias_value":"3GJQ3V4M","created_at":"2026-07-30T01:23:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3GJQ3V4MVJRUV6Q3JOVNJFOFXL","target":"record","payload":{"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"},"canonical_sha256":"d9930dd78caa634afa1b4baad495c5baee8df32c221f00fced29e369375d8a39","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"},"source_kind":"arxiv","source_id":"2607.27113","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T01:23:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4u7HPF5Wemmibf8XEyn3qrZCGZcaPZ6eh/1fbeR2flAlG7um7uLNXyVImZ0Ep1wAkRaUDt/Tl2og6A8yhWDNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T05:30:21.440660Z"},"content_sha256":"61bbee2f8003a499eeec7a201228db073cbf7d8375fb0563ede4c020d293c6b4","schema_version":"1.0","event_id":"sha256:61bbee2f8003a499eeec7a201228db073cbf7d8375fb0563ede4c020d293c6b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3GJQ3V4MVJRUV6Q3JOVNJFOFXL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T01:23:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/17MuQjt+BrAndPNJEumFc5FV3ru7h1P6Xr1xAm/8Uuc+ftQW9EOsSR5ulJsh3PcCpmIoEomwc9A5eTzUNuNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T05:30:21.441223Z"},"content_sha256":"a9fcb23c9312346cd358b7e1eaac4bbb7654e1b85ed3359b5f797398f708d0bf","schema_version":"1.0","event_id":"sha256:a9fcb23c9312346cd358b7e1eaac4bbb7654e1b85ed3359b5f797398f708d0bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3GJQ3V4MVJRUV6Q3JOVNJFOFXL/bundle.json","state_url":"https://pith.science/pith/3GJQ3V4MVJRUV6Q3JOVNJFOFXL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3GJQ3V4MVJRUV6Q3JOVNJFOFXL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T05:30:21Z","links":{"resolver":"https://pith.science/pith/3GJQ3V4MVJRUV6Q3JOVNJFOFXL","bundle":"https://pith.science/pith/3GJQ3V4MVJRUV6Q3JOVNJFOFXL/bundle.json","state":"https://pith.science/pith/3GJQ3V4MVJRUV6Q3JOVNJFOFXL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3GJQ3V4MVJRUV6Q3JOVNJFOFXL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3GJQ3V4MVJRUV6Q3JOVNJFOFXL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4abb55b7f3baa854d485b3a0254098faa97c5a8887bfad5e28de90e3aaa8d3d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T16:43:59Z","title_canon_sha256":"8d3feff10e230fea0d5c9a3e0462d1df2ab1df953381e6204288182d1093de23"},"schema_version":"1.0","source":{"id":"2607.27113","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27113","created_at":"2026-07-30T01:23:37Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27113v1","created_at":"2026-07-30T01:23:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27113","created_at":"2026-07-30T01:23:37Z"},{"alias_kind":"pith_short_12","alias_value":"3GJQ3V4MVJRU","created_at":"2026-07-30T01:23:37Z"},{"alias_kind":"pith_short_16","alias_value":"3GJQ3V4MVJRUV6Q3","created_at":"2026-07-30T01:23:37Z"},{"alias_kind":"pith_short_8","alias_value":"3GJQ3V4M","created_at":"2026-07-30T01:23:37Z"}],"graph_snapshots":[{"event_id":"sha256:a9fcb23c9312346cd358b7e1eaac4bbb7654e1b85ed3359b5f797398f708d0bf","target":"graph","created_at":"2026-07-30T01:23:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.27113/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ajian Liu, Chuanbiao Song, Hao Tan, Huijia Zhu, Jun Lan, Jun Wan, Weiqiang Wang, Zhen Lei, Zichang Tan, Zijian Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T16:43:59Z","title":"Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27113","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:61bbee2f8003a499eeec7a201228db073cbf7d8375fb0563ede4c020d293c6b4","target":"record","created_at":"2026-07-30T01:23:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4abb55b7f3baa854d485b3a0254098faa97c5a8887bfad5e28de90e3aaa8d3d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T16:43:59Z","title_canon_sha256":"8d3feff10e230fea0d5c9a3e0462d1df2ab1df953381e6204288182d1093de23"},"schema_version":"1.0","source":{"id":"2607.27113","kind":"arxiv","version":1}},"canonical_sha256":"d9930dd78caa634afa1b4baad495c5baee8df32c221f00fced29e369375d8a39","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9930dd78caa634afa1b4baad495c5baee8df32c221f00fced29e369375d8a39","first_computed_at":"2026-07-30T01:23:37.243867Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:23:37.243867Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.27113","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61bbee2f8003a499eeec7a201228db073cbf7d8375fb0563ede4c020d293c6b4","sha256:a9fcb23c9312346cd358b7e1eaac4bbb7654e1b85ed3359b5f797398f708d0bf"],"state_sha256":"5d5d9c3dab78253596552e3f2d920d1d6711cb77afc4105e1cbd384beb327421"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"swIpu3zBuxSddDjZqOBoay+Xc0wiWC1EwvwynKwjN6zDVV0+VqtSYFy6j+/K9CA2xONKtNo0Z9KKBsg5OojFCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T05:30:21.445013Z","bundle_sha256":"4c7ded49f267cd856202d568d97c71cc0e76e2f44a81e496001eb7bc28c33255"}}