{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MF2PILEKDCT4U3FWAVS5CC2FG2","short_pith_number":"pith:MF2PILEK","canonical_record":{"source":{"id":"2605.16879","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T08:39:54Z","cross_cats_sorted":[],"title_canon_sha256":"b2ff810814c5769dcfc475c020bc82816a9f4b49f4ac4a2fd565c581bb248da4","abstract_canon_sha256":"c2a634d64184f07067a94ce47daa550e9b2729552775d3c9e6362b9a8cf3a06f"},"schema_version":"1.0"},"canonical_sha256":"6174f42c8a18a7ca6cb60565d10b4536b545bc34706b02b6dea4ec375db2b397","source":{"kind":"arxiv","id":"2605.16879","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16879","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16879v1","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16879","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"MF2PILEKDCT4","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_16","alias_value":"MF2PILEKDCT4U3FW","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_8","alias_value":"MF2PILEK","created_at":"2026-05-20T00:03:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MF2PILEKDCT4U3FWAVS5CC2FG2","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16879","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T08:39:54Z","cross_cats_sorted":[],"title_canon_sha256":"b2ff810814c5769dcfc475c020bc82816a9f4b49f4ac4a2fd565c581bb248da4","abstract_canon_sha256":"c2a634d64184f07067a94ce47daa550e9b2729552775d3c9e6362b9a8cf3a06f"},"schema_version":"1.0"},"canonical_sha256":"6174f42c8a18a7ca6cb60565d10b4536b545bc34706b02b6dea4ec375db2b397","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:27.916831Z","signature_b64":"qsRQ+xXTJA23HEwU/6SEnibjC9NUzxGr3j+s+yAX6G3yKFa7nEmWQfNpo3O626cELSKPKpdRIXBU11/I49m3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6174f42c8a18a7ca6cb60565d10b4536b545bc34706b02b6dea4ec375db2b397","last_reissued_at":"2026-05-20T00:03:27.915983Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:27.915983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16879","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":"2026-05-20T00:03:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bgvHA/xol0hF7jXHAkZ68o7Fq2XwSFlyc9gP9pwaun1WmH1ra2IG/gqvk/vaPKKzipwVVo00BF7N3ry/VTUmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T23:29:35.336681Z"},"content_sha256":"b5f1b3005d25fffd60a44e67199fdcd5cea342402c35b248cf992a4679b9fb0c","schema_version":"1.0","event_id":"sha256:b5f1b3005d25fffd60a44e67199fdcd5cea342402c35b248cf992a4679b9fb0c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MF2PILEKDCT4U3FWAVS5CC2FG2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Generalized Image Manipulation Localization via Score-based Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"DiffIML approximates the score function of mask distributions to iteratively recover coherent manipulation masks from noise, improving generalization over discriminative methods.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Du, Ji-Zhe Zhou, Tianxin Xu, Xin Liu, Yunfei Wang, Zhe Yang, Zhiyu Lin","submitted_at":"2026-05-16T08:39:54Z","abstract_excerpt":"With the rapid evolution of synthetic media, Image Manipulation Localization (IML) has emerged as a critical component in multimedia forensics for ensuring the integrity of digital content. However, generalization remains a core challenge, as existing discriminative methods typically learn a fixed decision boundary that tends to overfit to specific training artifacts and fails to adapt to unseen manipulation types. To address this, we propose DiffIML, a novel framework that introduces score-based generative modeling to IML. Diverging from the direct estimation of hard boundaries, DiffIML appro"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"DiffIML approximates the score function of mask distributions to iteratively recover coherent masks from noise, circumventing the brittleness of discriminative models and yielding consistent generalization improvements on diverse unseen datasets across eight non-generative and three generative benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that the learned score function, combined with edge supervision and error prior in a lightweight latent-space diffusion process, will reliably produce coherent masks without overfitting to training artifacts or requiring extensive per-dataset tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DiffIML applies score-based generative modeling to image manipulation localization, recovering coherent masks iteratively from noise to improve generalization on unseen manipulation types.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"DiffIML approximates the score function of mask distributions to iteratively recover coherent manipulation masks from noise, improving generalization over discriminative methods.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a39744368b11009a58c16e98d7f03ab921efbededc373bb7f71f99ef84c77108"},"source":{"id":"2605.16879","kind":"arxiv","version":1},"verdict":{"id":"f59f8bd5-2a03-4617-8149-44ac289a800f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T20:11:13.644647Z","strongest_claim":"DiffIML approximates the score function of mask distributions to iteratively recover coherent masks from noise, circumventing the brittleness of discriminative models and yielding consistent generalization improvements on diverse unseen datasets across eight non-generative and three generative benchmarks.","one_line_summary":"DiffIML applies score-based generative modeling to image manipulation localization, recovering coherent masks iteratively from noise to improve generalization on unseen manipulation types.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that the learned score function, combined with edge supervision and error prior in a lightweight latent-space diffusion process, will reliably produce coherent masks without overfitting to training artifacts or requiring extensive per-dataset tuning.","pith_extraction_headline":"DiffIML approximates the score function of mask distributions to iteratively recover coherent manipulation masks from noise, improving generalization over discriminative methods."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16879/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T20:31:19.111592Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T20:22:04.379240Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.292146Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.369324Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"2a352a3ef6338b74d9e0649fd7d370e2e50c0eadccd264879e3e9ec9bcd2df0b"},"references":{"count":39,"sample":[{"doi":"","year":2022,"title":"Analytic-dpm: an analytic estimate of the optimal reverse variance in diffusion probabilistic models","work_id":"2cec8148-2818-442d-9f52-4f50f61ea90b","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Xinru Chen, Chengbo Dong, Jiaqi Ji, Juan Cao, and Xirong Li. 2021. Image manipulation detection by multi-view multi-scale supervision. InProceedings of the IEEE/CVF International Conference on Compute","work_id":"d3e1e69e-dd3a-4dc6-a281-d73beaa75e3c","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Chengbo Dong, Xinru Chen, Ruohan Hu, Juan Cao, and Xirong Li. 2023. MVSS- Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detec- tion.IEEE Transactions on Pattern Analysis and M","work_id":"63f31d88-b667-4758-9c2a-6b0cd66db1db","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2013,"title":"Jing Dong, Wei Wang, and Tieniu Tan. 2013. CASIA Image Tampering Detection Evaluation Database. In2013 IEEE China summit and international conference on signal and information processing. IEEE, 422–42","work_id":"4fd0e93f-c54a-4d34-ac83-49104fe0e74b","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Bo Du, Xuekang Zhu, Xiaochen Ma, Chenfan Qu, Kaiwen Feng, Zhe Yang, Chi- Man Pun, Jian Liu, and Ji-Zhe Zhou. 2025. ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and L","work_id":"a99f2a78-90d6-4c39-8c90-fb66e4762ca7","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":39,"snapshot_sha256":"feab2d28f1d5df4e8659a305657ce18281ac96c98cdc8fc0e4aba59265d52f15","internal_anchors":5},"formal_canon":{"evidence_count":1,"snapshot_sha256":"15b7b60bbe77df668b9a53a693b3cc07ecda5c506d5cc699157e5b1c537c198b"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"f59f8bd5-2a03-4617-8149-44ac289a800f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fm7yuIkJZZsufMG6avKJpVMyIFqtXSgZeoj2g5n+raMh2V6K4lmAdUUBqtIaLKE/M7+1T+LDiORk0m6oFrFuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T23:29:35.337929Z"},"content_sha256":"c61a74f7f4a368acb0a8f186dd1cc9e3fdf67ee27bbbce9e6ffb5fb809406669","schema_version":"1.0","event_id":"sha256:c61a74f7f4a368acb0a8f186dd1cc9e3fdf67ee27bbbce9e6ffb5fb809406669"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MF2PILEKDCT4U3FWAVS5CC2FG2/bundle.json","state_url":"https://pith.science/pith/MF2PILEKDCT4U3FWAVS5CC2FG2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MF2PILEKDCT4U3FWAVS5CC2FG2/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":"2026-05-20T23:29:35Z","links":{"resolver":"https://pith.science/pith/MF2PILEKDCT4U3FWAVS5CC2FG2","bundle":"https://pith.science/pith/MF2PILEKDCT4U3FWAVS5CC2FG2/bundle.json","state":"https://pith.science/pith/MF2PILEKDCT4U3FWAVS5CC2FG2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MF2PILEKDCT4U3FWAVS5CC2FG2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MF2PILEKDCT4U3FWAVS5CC2FG2","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":"c2a634d64184f07067a94ce47daa550e9b2729552775d3c9e6362b9a8cf3a06f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T08:39:54Z","title_canon_sha256":"b2ff810814c5769dcfc475c020bc82816a9f4b49f4ac4a2fd565c581bb248da4"},"schema_version":"1.0","source":{"id":"2605.16879","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16879","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16879v1","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16879","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"MF2PILEKDCT4","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_16","alias_value":"MF2PILEKDCT4U3FW","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_8","alias_value":"MF2PILEK","created_at":"2026-05-20T00:03:27Z"}],"graph_snapshots":[{"event_id":"sha256:c61a74f7f4a368acb0a8f186dd1cc9e3fdf67ee27bbbce9e6ffb5fb809406669","target":"graph","created_at":"2026-05-20T00:03:27Z","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":"DiffIML approximates the score function of mask distributions to iteratively recover coherent masks from noise, circumventing the brittleness of discriminative models and yielding consistent generalization improvements on diverse unseen datasets across eight non-generative and three generative benchmarks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the learned score function, combined with edge supervision and error prior in a lightweight latent-space diffusion process, will reliably produce coherent masks without overfitting to training artifacts or requiring extensive per-dataset tuning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DiffIML applies score-based generative modeling to image manipulation localization, recovering coherent masks iteratively from noise to improve generalization on unseen manipulation types."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"DiffIML approximates the score function of mask distributions to iteratively recover coherent manipulation masks from noise, improving generalization over discriminative methods."}],"snapshot_sha256":"a39744368b11009a58c16e98d7f03ab921efbededc373bb7f71f99ef84c77108"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"15b7b60bbe77df668b9a53a693b3cc07ecda5c506d5cc699157e5b1c537c198b"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T20:31:19.111592Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T20:22:04.379240Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.292146Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.369324Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16879/integrity.json","findings":[],"snapshot_sha256":"2a352a3ef6338b74d9e0649fd7d370e2e50c0eadccd264879e3e9ec9bcd2df0b","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rapid evolution of synthetic media, Image Manipulation Localization (IML) has emerged as a critical component in multimedia forensics for ensuring the integrity of digital content. However, generalization remains a core challenge, as existing discriminative methods typically learn a fixed decision boundary that tends to overfit to specific training artifacts and fails to adapt to unseen manipulation types. To address this, we propose DiffIML, a novel framework that introduces score-based generative modeling to IML. Diverging from the direct estimation of hard boundaries, DiffIML appro","authors_text":"Bo Du, Ji-Zhe Zhou, Tianxin Xu, Xin Liu, Yunfei Wang, Zhe Yang, Zhiyu Lin","cross_cats":[],"headline":"DiffIML approximates the score function of mask distributions to iteratively recover coherent manipulation masks from noise, improving generalization over discriminative methods.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T08:39:54Z","title":"Towards Generalized Image Manipulation Localization via Score-based Model"},"references":{"count":39,"internal_anchors":5,"resolved_work":39,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Analytic-dpm: an analytic estimate of the optimal reverse variance in diffusion probabilistic models","work_id":"2cec8148-2818-442d-9f52-4f50f61ea90b","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Xinru Chen, Chengbo Dong, Jiaqi Ji, Juan Cao, and Xirong Li. 2021. Image manipulation detection by multi-view multi-scale supervision. InProceedings of the IEEE/CVF International Conference on Compute","work_id":"d3e1e69e-dd3a-4dc6-a281-d73beaa75e3c","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Chengbo Dong, Xinru Chen, Ruohan Hu, Juan Cao, and Xirong Li. 2023. MVSS- Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detec- tion.IEEE Transactions on Pattern Analysis and M","work_id":"63f31d88-b667-4758-9c2a-6b0cd66db1db","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Jing Dong, Wei Wang, and Tieniu Tan. 2013. CASIA Image Tampering Detection Evaluation Database. In2013 IEEE China summit and international conference on signal and information processing. IEEE, 422–42","work_id":"4fd0e93f-c54a-4d34-ac83-49104fe0e74b","year":2013},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Bo Du, Xuekang Zhu, Xiaochen Ma, Chenfan Qu, Kaiwen Feng, Zhe Yang, Chi- Man Pun, Jian Liu, and Ji-Zhe Zhou. 2025. ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and L","work_id":"a99f2a78-90d6-4c39-8c90-fb66e4762ca7","year":2025}],"snapshot_sha256":"feab2d28f1d5df4e8659a305657ce18281ac96c98cdc8fc0e4aba59265d52f15"},"source":{"id":"2605.16879","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T20:11:13.644647Z","id":"f59f8bd5-2a03-4617-8149-44ac289a800f","model_set":{"reader":"grok-4.3"},"one_line_summary":"DiffIML applies score-based generative modeling to image manipulation localization, recovering coherent masks iteratively from noise to improve generalization on unseen manipulation types.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"DiffIML approximates the score function of mask distributions to iteratively recover coherent manipulation masks from noise, improving generalization over discriminative methods.","strongest_claim":"DiffIML approximates the score function of mask distributions to iteratively recover coherent masks from noise, circumventing the brittleness of discriminative models and yielding consistent generalization improvements on diverse unseen datasets across eight non-generative and three generative benchmarks.","weakest_assumption":"The assumption that the learned score function, combined with edge supervision and error prior in a lightweight latent-space diffusion process, will reliably produce coherent masks without overfitting to training artifacts or requiring extensive per-dataset tuning."}},"verdict_id":"f59f8bd5-2a03-4617-8149-44ac289a800f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b5f1b3005d25fffd60a44e67199fdcd5cea342402c35b248cf992a4679b9fb0c","target":"record","created_at":"2026-05-20T00:03:27Z","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":"c2a634d64184f07067a94ce47daa550e9b2729552775d3c9e6362b9a8cf3a06f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T08:39:54Z","title_canon_sha256":"b2ff810814c5769dcfc475c020bc82816a9f4b49f4ac4a2fd565c581bb248da4"},"schema_version":"1.0","source":{"id":"2605.16879","kind":"arxiv","version":1}},"canonical_sha256":"6174f42c8a18a7ca6cb60565d10b4536b545bc34706b02b6dea4ec375db2b397","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6174f42c8a18a7ca6cb60565d10b4536b545bc34706b02b6dea4ec375db2b397","first_computed_at":"2026-05-20T00:03:27.915983Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:27.915983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qsRQ+xXTJA23HEwU/6SEnibjC9NUzxGr3j+s+yAX6G3yKFa7nEmWQfNpo3O626cELSKPKpdRIXBU11/I49m3DQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:27.916831Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16879","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5f1b3005d25fffd60a44e67199fdcd5cea342402c35b248cf992a4679b9fb0c","sha256:c61a74f7f4a368acb0a8f186dd1cc9e3fdf67ee27bbbce9e6ffb5fb809406669"],"state_sha256":"939587f87c64a21fa8ad7aad7c9ecb9e7706d4a9fefa17ed8a08fb0590e30ada"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0pF+yKrr0npfTJnfr6ygV4mYsuiBVcMouWjPf9SPpVAQ9wCizojPuAZfQzslvYsTgFysuGVOTe8e9ugbbwU4AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T23:29:35.343400Z","bundle_sha256":"39f520dee7c251b38df4482ae9eafe13b7c94ef213004e917219d308b814b181"}}