{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WIIXMMCXMQQBDRSVPYTTQANW7H","short_pith_number":"pith:WIIXMMCX","canonical_record":{"source":{"id":"2604.10102","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-11T08:52:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d78d4b4871463890cd4d10ee679dfeadea6c6d68d8914d8d8fe94582af00ee9","abstract_canon_sha256":"679e6cd445b015a9ac5c897bb4b994e58234da5750bf11aa204c6a06dc273c5c"},"schema_version":"1.0"},"canonical_sha256":"b211763057642011c6557e273801b6f9ebfe7c12bb673b2c5296a6c87919ff0c","source":{"kind":"arxiv","id":"2604.10102","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.10102","created_at":"2026-05-27T02:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"2604.10102v2","created_at":"2026-05-27T02:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.10102","created_at":"2026-05-27T02:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"WIIXMMCXMQQB","created_at":"2026-05-27T02:05:19Z"},{"alias_kind":"pith_short_16","alias_value":"WIIXMMCXMQQBDRSV","created_at":"2026-05-27T02:05:19Z"},{"alias_kind":"pith_short_8","alias_value":"WIIXMMCX","created_at":"2026-05-27T02:05:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WIIXMMCXMQQBDRSVPYTTQANW7H","target":"record","payload":{"canonical_record":{"source":{"id":"2604.10102","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-11T08:52:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d78d4b4871463890cd4d10ee679dfeadea6c6d68d8914d8d8fe94582af00ee9","abstract_canon_sha256":"679e6cd445b015a9ac5c897bb4b994e58234da5750bf11aa204c6a06dc273c5c"},"schema_version":"1.0"},"canonical_sha256":"b211763057642011c6557e273801b6f9ebfe7c12bb673b2c5296a6c87919ff0c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:05:19.525267Z","signature_b64":"Cpw31IEvST+FI9yuT7cb4d8UcPhiSmR2UnbCNaMRnHjcr/ZwuIdk0CziuhlA04DqADuv0Da/jyfRt9hFxLVJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b211763057642011c6557e273801b6f9ebfe7c12bb673b2c5296a6c87919ff0c","last_reissued_at":"2026-05-27T02:05:19.524692Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:05:19.524692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.10102","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T02:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G4nEPFQvWKYU8aINbxyRocbo1nOBX/ovEcJgEjlt2cFmqo/uWDkaVl9JDbxQyMdkvW3dXL5StRBYTBZDm/w9CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T07:52:07.953397Z"},"content_sha256":"9edf09e8d41929126664f1f5ca2b70154e8da644d14eb87502ff1e367b667823","schema_version":"1.0","event_id":"sha256:9edf09e8d41929126664f1f5ca2b70154e8da644d14eb87502ff1e367b667823"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WIIXMMCXMQQBDRSVPYTTQANW7H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Degradation-Consistent Paired Training for Robust AI-Generated Image Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Degradation-Consistent Paired Training raises AI-generated image detector accuracy on corrupted inputs by 9.1 percentage points with only a 0.9 percent drop on clean images.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Xiaokun Yang, Yinghan Hou, Zongyou Yang","submitted_at":"2026-04-11T08:52:28Z","abstract_excerpt":"AI-generated image detectors suffer significant performance degradation under real-world image corruptions such as JPEG compression, Gaussian blur, and resolution downsampling. We observe that state-of-the-art methods, including B-Free, treat degradation robustness as a byproduct of data augmentation rather than an explicit training objective. In this work, we propose Degradation-Consistent Paired Training (DCPT), a simple yet effective training strategy that explicitly enforces robustness through paired consistency constraints. For each training image, we construct a clean view and a degraded"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on the Synthbuster benchmark (9 generators, 8 degradation conditions) demonstrate that DCPT improves the degraded-condition average accuracy by 9.1 percentage points compared to an identical baseline without paired training, while sacrificing only 0.9% clean accuracy. The improvement is most pronounced under JPEG compression (+15.7% to +17.9%).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the specific degradations (JPEG compression, Gaussian blur, resolution downsampling) and consistency losses used during training will generalize to unseen real-world corruptions and that the Synthbuster benchmark sufficiently represents practical deployment conditions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DCPT raises average accuracy of AI image detectors under real-world degradations by 9.1 points on the Synthbuster benchmark using paired consistency losses, with only 0.9% drop on clean images and no added parameters or inference cost.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Degradation-Consistent Paired Training raises AI-generated image detector accuracy on corrupted inputs by 9.1 percentage points with only a 0.9 percent drop on clean images.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"be26887965bba4e1e5219d36dd6307a869e58a329224a6a3e025290d17b2d58e"},"source":{"id":"2604.10102","kind":"arxiv","version":2},"verdict":{"id":"963d075e-8d30-4e3a-a957-30b6105a4db2","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T16:12:16.091897Z","strongest_claim":"Experiments on the Synthbuster benchmark (9 generators, 8 degradation conditions) demonstrate that DCPT improves the degraded-condition average accuracy by 9.1 percentage points compared to an identical baseline without paired training, while sacrificing only 0.9% clean accuracy. The improvement is most pronounced under JPEG compression (+15.7% to +17.9%).","one_line_summary":"DCPT raises average accuracy of AI image detectors under real-world degradations by 9.1 points on the Synthbuster benchmark using paired consistency losses, with only 0.9% drop on clean images and no added parameters or inference cost.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the specific degradations (JPEG compression, Gaussian blur, resolution downsampling) and consistency losses used during training will generalize to unseen real-world corruptions and that the Synthbuster benchmark sufficiently represents practical deployment conditions.","pith_extraction_headline":"Degradation-Consistent Paired Training raises AI-generated image detector accuracy on corrupted inputs by 9.1 percentage points with only a 0.9 percent drop on clean images."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.10102/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":2,"snapshot_sha256":"483efbc719a53b9aa393b9fe5dc5efbf20147727a685ea80e6634342d3f6b649"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"963d075e-8d30-4e3a-a957-30b6105a4db2"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T02:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nTejBj3ohiAf7Al6rufYsvqbrGJkDK5jV7+j2Y28DPDpaoJ8pIneooEAzZ4B7pAi7XfO7KSk/aV3ssavp50UAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T07:52:07.953846Z"},"content_sha256":"d0c081e4bf77576170b3f055a3f3a03af0349b82ba395e188c36c22e38589804","schema_version":"1.0","event_id":"sha256:d0c081e4bf77576170b3f055a3f3a03af0349b82ba395e188c36c22e38589804"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WIIXMMCXMQQBDRSVPYTTQANW7H/bundle.json","state_url":"https://pith.science/pith/WIIXMMCXMQQBDRSVPYTTQANW7H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WIIXMMCXMQQBDRSVPYTTQANW7H/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":"2026-06-02T07:52:07Z","links":{"resolver":"https://pith.science/pith/WIIXMMCXMQQBDRSVPYTTQANW7H","bundle":"https://pith.science/pith/WIIXMMCXMQQBDRSVPYTTQANW7H/bundle.json","state":"https://pith.science/pith/WIIXMMCXMQQBDRSVPYTTQANW7H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WIIXMMCXMQQBDRSVPYTTQANW7H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WIIXMMCXMQQBDRSVPYTTQANW7H","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":"679e6cd445b015a9ac5c897bb4b994e58234da5750bf11aa204c6a06dc273c5c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-11T08:52:28Z","title_canon_sha256":"4d78d4b4871463890cd4d10ee679dfeadea6c6d68d8914d8d8fe94582af00ee9"},"schema_version":"1.0","source":{"id":"2604.10102","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.10102","created_at":"2026-05-27T02:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"2604.10102v2","created_at":"2026-05-27T02:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.10102","created_at":"2026-05-27T02:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"WIIXMMCXMQQB","created_at":"2026-05-27T02:05:19Z"},{"alias_kind":"pith_short_16","alias_value":"WIIXMMCXMQQBDRSV","created_at":"2026-05-27T02:05:19Z"},{"alias_kind":"pith_short_8","alias_value":"WIIXMMCX","created_at":"2026-05-27T02:05:19Z"}],"graph_snapshots":[{"event_id":"sha256:d0c081e4bf77576170b3f055a3f3a03af0349b82ba395e188c36c22e38589804","target":"graph","created_at":"2026-05-27T02:05:19Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments on the Synthbuster benchmark (9 generators, 8 degradation conditions) demonstrate that DCPT improves the degraded-condition average accuracy by 9.1 percentage points compared to an identical baseline without paired training, while sacrificing only 0.9% clean accuracy. The improvement is most pronounced under JPEG compression (+15.7% to +17.9%)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the specific degradations (JPEG compression, Gaussian blur, resolution downsampling) and consistency losses used during training will generalize to unseen real-world corruptions and that the Synthbuster benchmark sufficiently represents practical deployment conditions."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DCPT raises average accuracy of AI image detectors under real-world degradations by 9.1 points on the Synthbuster benchmark using paired consistency losses, with only 0.9% drop on clean images and no added parameters or inference cost."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Degradation-Consistent Paired Training raises AI-generated image detector accuracy on corrupted inputs by 9.1 percentage points with only a 0.9 percent drop on clean images."}],"snapshot_sha256":"be26887965bba4e1e5219d36dd6307a869e58a329224a6a3e025290d17b2d58e"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"483efbc719a53b9aa393b9fe5dc5efbf20147727a685ea80e6634342d3f6b649"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.10102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"AI-generated image detectors suffer significant performance degradation under real-world image corruptions such as JPEG compression, Gaussian blur, and resolution downsampling. We observe that state-of-the-art methods, including B-Free, treat degradation robustness as a byproduct of data augmentation rather than an explicit training objective. In this work, we propose Degradation-Consistent Paired Training (DCPT), a simple yet effective training strategy that explicitly enforces robustness through paired consistency constraints. For each training image, we construct a clean view and a degraded","authors_text":"Xiaokun Yang, Yinghan Hou, Zongyou Yang","cross_cats":["cs.AI"],"headline":"Degradation-Consistent Paired Training raises AI-generated image detector accuracy on corrupted inputs by 9.1 percentage points with only a 0.9 percent drop on clean images.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-11T08:52:28Z","title":"Degradation-Consistent Paired Training for Robust AI-Generated Image Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.10102","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T16:12:16.091897Z","id":"963d075e-8d30-4e3a-a957-30b6105a4db2","model_set":{"reader":"grok-4.3"},"one_line_summary":"DCPT raises average accuracy of AI image detectors under real-world degradations by 9.1 points on the Synthbuster benchmark using paired consistency losses, with only 0.9% drop on clean images and no added parameters or inference cost.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Degradation-Consistent Paired Training raises AI-generated image detector accuracy on corrupted inputs by 9.1 percentage points with only a 0.9 percent drop on clean images.","strongest_claim":"Experiments on the Synthbuster benchmark (9 generators, 8 degradation conditions) demonstrate that DCPT improves the degraded-condition average accuracy by 9.1 percentage points compared to an identical baseline without paired training, while sacrificing only 0.9% clean accuracy. The improvement is most pronounced under JPEG compression (+15.7% to +17.9%).","weakest_assumption":"That the specific degradations (JPEG compression, Gaussian blur, resolution downsampling) and consistency losses used during training will generalize to unseen real-world corruptions and that the Synthbuster benchmark sufficiently represents practical deployment conditions."}},"verdict_id":"963d075e-8d30-4e3a-a957-30b6105a4db2"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9edf09e8d41929126664f1f5ca2b70154e8da644d14eb87502ff1e367b667823","target":"record","created_at":"2026-05-27T02:05:19Z","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":"679e6cd445b015a9ac5c897bb4b994e58234da5750bf11aa204c6a06dc273c5c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-11T08:52:28Z","title_canon_sha256":"4d78d4b4871463890cd4d10ee679dfeadea6c6d68d8914d8d8fe94582af00ee9"},"schema_version":"1.0","source":{"id":"2604.10102","kind":"arxiv","version":2}},"canonical_sha256":"b211763057642011c6557e273801b6f9ebfe7c12bb673b2c5296a6c87919ff0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b211763057642011c6557e273801b6f9ebfe7c12bb673b2c5296a6c87919ff0c","first_computed_at":"2026-05-27T02:05:19.524692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T02:05:19.524692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cpw31IEvST+FI9yuT7cb4d8UcPhiSmR2UnbCNaMRnHjcr/ZwuIdk0CziuhlA04DqADuv0Da/jyfRt9hFxLVJAw==","signature_status":"signed_v1","signed_at":"2026-05-27T02:05:19.525267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.10102","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9edf09e8d41929126664f1f5ca2b70154e8da644d14eb87502ff1e367b667823","sha256:d0c081e4bf77576170b3f055a3f3a03af0349b82ba395e188c36c22e38589804"],"state_sha256":"0f0f61afc1e26bdb1bca10ccb674e7249f08db58616a7f319c65c3b3d84a157a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mai0AOfY8trBdO8byvpq5A08VtqahWe9igSuh/KwnVvLG50URYgZGK4KIWibF7df+A1qlfuZf/xEWIgK3DxADg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T07:52:07.956151Z","bundle_sha256":"5aa50b97596de3e5f8b11ede384653a13a72452c5d87bb974513ce39b7553d2e"}}