{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JW7IYMBAHRJSO23AELJGEB56T6","short_pith_number":"pith:JW7IYMBA","canonical_record":{"source":{"id":"2607.22087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T08:34:56Z","cross_cats_sorted":[],"title_canon_sha256":"ebde085cba81897045635a577ce4ce82c72361dde0b30a8d44136490ffa80674","abstract_canon_sha256":"fda425f14379a3a4ecff3f2364cfca2a8a52d8bd590a0271b9d079e05511d976"},"schema_version":"1.0"},"canonical_sha256":"4dbe8c30203c53276b6022d26207be9fa58e0dc17af7af05af462706479be23c","source":{"kind":"arxiv","id":"2607.22087","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22087","created_at":"2026-07-27T01:20:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22087v1","created_at":"2026-07-27T01:20:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22087","created_at":"2026-07-27T01:20:47Z"},{"alias_kind":"pith_short_12","alias_value":"JW7IYMBAHRJS","created_at":"2026-07-27T01:20:47Z"},{"alias_kind":"pith_short_16","alias_value":"JW7IYMBAHRJSO23A","created_at":"2026-07-27T01:20:47Z"},{"alias_kind":"pith_short_8","alias_value":"JW7IYMBA","created_at":"2026-07-27T01:20:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JW7IYMBAHRJSO23AELJGEB56T6","target":"record","payload":{"canonical_record":{"source":{"id":"2607.22087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T08:34:56Z","cross_cats_sorted":[],"title_canon_sha256":"ebde085cba81897045635a577ce4ce82c72361dde0b30a8d44136490ffa80674","abstract_canon_sha256":"fda425f14379a3a4ecff3f2364cfca2a8a52d8bd590a0271b9d079e05511d976"},"schema_version":"1.0"},"canonical_sha256":"4dbe8c30203c53276b6022d26207be9fa58e0dc17af7af05af462706479be23c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:20:47.533453Z","signature_b64":"FbBqDESbb4U/w9XcUGVJ0oH+g0Q+D22s3gobcWHmOq7FK9gMy+wotPYIZl2rEXqpb2Ax/k5vXtgAzLVfwqOMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dbe8c30203c53276b6022d26207be9fa58e0dc17af7af05af462706479be23c","last_reissued_at":"2026-07-27T01:20:47.532553Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:20:47.532553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.22087","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":"2026-07-27T01:20:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yjXi33A4QJlvddAFa0m1/5JSOIAb0qFmQcCNT4IVC4ZcOvk2cfW441ALWKmiACR43+9xK6X3nSsiyoy5PTn8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:51:23.913867Z"},"content_sha256":"f4e92d19e60f1ea4e3911b7e4478d982a6682648af80441f55041c047669c45a","schema_version":"1.0","event_id":"sha256:f4e92d19e60f1ea4e3911b7e4478d982a6682648af80441f55041c047669c45a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JW7IYMBAHRJSO23AELJGEB56T6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FAIR: Feature-Augmented Implicit Regularization for AI-generated Fake Image Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Manoranjan Paul, Manzur Murshed, Md Redwanul Haque, Tsz-Kwan Lee","submitted_at":"2026-07-24T08:34:56Z","abstract_excerpt":"Generalization remains a critical bottleneck in AI-generated image detection. Because many modern generators are proprietary or adversarially modified, existing detectors overfit to the low-level textural patterns of accessible training data, resulting in severe failures on unseen domains. Conventional regularization techniques (e.g., $L_1$/$L_2$ norms, Dropout) apply indiscriminate parametric constraints and fail to provide the domain-invariant structure necessary for cross-generator robustness. To address this, we propose Feature-Augmented Implicit Regularization (FAIR). FAIR introduces an o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22087","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/2607.22087/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":"2026-07-27T01:20:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jbhAAg95L4xSCI1fjvw3SID1sEBKqDngU+3EEIJI1XtA2HzIdTqsA9XLQDkcA3iTriVuL5eN34krALjFwj6RAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:51:23.914355Z"},"content_sha256":"523f68bd5e5eb68df3fb9655af2cbdb8ac9548dbeba3f24e5e385baeec0da603","schema_version":"1.0","event_id":"sha256:523f68bd5e5eb68df3fb9655af2cbdb8ac9548dbeba3f24e5e385baeec0da603"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:JW7IYMBAHRJSO23AELJGEB56T6","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1007/978-3-031-19781-9_6) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Liu, B., Yang, F., Bi, X., Xiao, B., Li, W., Gao, X.: Detecting Generated Images byRealImages.In:ComputerVision–ECCV2022:17thEuropeanConference,Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XIV. pp. 95–110. Springer- Verlag, Berl","arxiv_id":"2607.22087","detector":"doi_compliance","evidence":{"ref_index":19,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1007/978-3-031-","reconstructed_doi":"10.1007/978-3-031-19781-9_6"},"severity":"advisory","ref_index":19,"audited_at":"2026-08-01T05:58:57.276182Z","event_type":"pith.integrity.v1","detected_doi":"10.1007/978-3-031-19781-9_6","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"3100a48e68564a422f33582826928e312f7a96a0faa26e7a99d7a35ecdde80a5","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":15231,"payload_sha256":"d02907651dc363ef8cb2e5de963057ef3f90a40f63ded5a21e1f9d88cb5bfe89","signature_b64":"i1ZIGVD2S7O2noAmc2GzKSS9/SGdObVKV5OA8JlmQ8lB/Mv84SJ/nrLygZQ8sCDdYh9T8seaQWYbn6DL/yc4DA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-01T06:03:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LiFWXn667tNq6cE2wKZliRovkput2QvF7sBSGsY4IDxBSdLellzImL4L5QDXEogGSd+PMsbaGCea+00wt8iSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:51:23.916903Z"},"content_sha256":"3c6a1948434eb0d525d7153f8840509c589b4f5af04a2788d8e63ff91cc59f83","schema_version":"1.0","event_id":"sha256:3c6a1948434eb0d525d7153f8840509c589b4f5af04a2788d8e63ff91cc59f83"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:JW7IYMBAHRJSO23AELJGEB56T6","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1038/s42256-020-00257-z) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Geirhos, R., Jacobsen, J.H., Michaelis, C., Zemel, R., Brendel, W., Bethge, M., Wichmann, F.A.: Shortcut learning in deep neural networks. Nature Machine In- telligence2(11), 665–673 (Nov 2020).https://doi.org/10.1038/s42256-020- 00257-z","arxiv_id":"2607.22087","detector":"doi_compliance","evidence":{"ref_index":10,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1038/s42256-020-","reconstructed_doi":"10.1038/s42256-020-00257-z"},"severity":"advisory","ref_index":10,"audited_at":"2026-08-01T05:58:57.276182Z","event_type":"pith.integrity.v1","detected_doi":"10.1038/s42256-020-00257-z","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"66e73a9fc38edb7edef8de50646f8df7fac51ff1416b9fbe8ed9e1741f44c16f","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":15230,"payload_sha256":"fe0eec5aef205c2e75601797a0f64cf3014a30a192c62375379744dd031a4407","signature_b64":"1JYrQ1bZZdMC4p1oPRKZn7ANbic3f2S3e5pz6ymgXkkBd2rAzsg29bfHPAU1pfLAvEDYSBQt8JvjqCAXyRZoBg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-01T06:03:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rUNkU7sIlgATvVq/PUExjhrUy6tp1qZj/1UQw7DSxiMqj5ITT3TH1HWIez9BYAcvBe+4/aaqvVO45oB6ZfPLBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:51:23.917316Z"},"content_sha256":"8e05476476cae1ae28f058e08f218a816dc25ebe8ce36c9f45865f7e144a6f7d","schema_version":"1.0","event_id":"sha256:8e05476476cae1ae28f058e08f218a816dc25ebe8ce36c9f45865f7e144a6f7d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JW7IYMBAHRJSO23AELJGEB56T6/bundle.json","state_url":"https://pith.science/pith/JW7IYMBAHRJSO23AELJGEB56T6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JW7IYMBAHRJSO23AELJGEB56T6/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":"2026-08-03T20:51:23Z","links":{"resolver":"https://pith.science/pith/JW7IYMBAHRJSO23AELJGEB56T6","bundle":"https://pith.science/pith/JW7IYMBAHRJSO23AELJGEB56T6/bundle.json","state":"https://pith.science/pith/JW7IYMBAHRJSO23AELJGEB56T6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JW7IYMBAHRJSO23AELJGEB56T6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JW7IYMBAHRJSO23AELJGEB56T6","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fda425f14379a3a4ecff3f2364cfca2a8a52d8bd590a0271b9d079e05511d976","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T08:34:56Z","title_canon_sha256":"ebde085cba81897045635a577ce4ce82c72361dde0b30a8d44136490ffa80674"},"schema_version":"1.0","source":{"id":"2607.22087","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22087","created_at":"2026-07-27T01:20:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22087v1","created_at":"2026-07-27T01:20:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22087","created_at":"2026-07-27T01:20:47Z"},{"alias_kind":"pith_short_12","alias_value":"JW7IYMBAHRJS","created_at":"2026-07-27T01:20:47Z"},{"alias_kind":"pith_short_16","alias_value":"JW7IYMBAHRJSO23A","created_at":"2026-07-27T01:20:47Z"},{"alias_kind":"pith_short_8","alias_value":"JW7IYMBA","created_at":"2026-07-27T01:20:47Z"}],"graph_snapshots":[{"event_id":"sha256:523f68bd5e5eb68df3fb9655af2cbdb8ac9548dbeba3f24e5e385baeec0da603","target":"graph","created_at":"2026-07-27T01:20:47Z","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/2607.22087/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generalization remains a critical bottleneck in AI-generated image detection. Because many modern generators are proprietary or adversarially modified, existing detectors overfit to the low-level textural patterns of accessible training data, resulting in severe failures on unseen domains. Conventional regularization techniques (e.g., $L_1$/$L_2$ norms, Dropout) apply indiscriminate parametric constraints and fail to provide the domain-invariant structure necessary for cross-generator robustness. To address this, we propose Feature-Augmented Implicit Regularization (FAIR). FAIR introduces an o","authors_text":"Manoranjan Paul, Manzur Murshed, Md Redwanul Haque, Tsz-Kwan Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T08:34:56Z","title":"FAIR: Feature-Augmented Implicit Regularization for AI-generated Fake Image Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22087","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:f4e92d19e60f1ea4e3911b7e4478d982a6682648af80441f55041c047669c45a","target":"record","created_at":"2026-07-27T01:20:47Z","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":"fda425f14379a3a4ecff3f2364cfca2a8a52d8bd590a0271b9d079e05511d976","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T08:34:56Z","title_canon_sha256":"ebde085cba81897045635a577ce4ce82c72361dde0b30a8d44136490ffa80674"},"schema_version":"1.0","source":{"id":"2607.22087","kind":"arxiv","version":1}},"canonical_sha256":"4dbe8c30203c53276b6022d26207be9fa58e0dc17af7af05af462706479be23c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4dbe8c30203c53276b6022d26207be9fa58e0dc17af7af05af462706479be23c","first_computed_at":"2026-07-27T01:20:47.532553Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T01:20:47.532553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FbBqDESbb4U/w9XcUGVJ0oH+g0Q+D22s3gobcWHmOq7FK9gMy+wotPYIZl2rEXqpb2Ax/k5vXtgAzLVfwqOMDA==","signature_status":"signed_v1","signed_at":"2026-07-27T01:20:47.533453Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22087","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:3c6a1948434eb0d525d7153f8840509c589b4f5af04a2788d8e63ff91cc59f83","sha256:8e05476476cae1ae28f058e08f218a816dc25ebe8ce36c9f45865f7e144a6f7d"]}],"invalid_events":[],"applied_event_ids":["sha256:f4e92d19e60f1ea4e3911b7e4478d982a6682648af80441f55041c047669c45a","sha256:523f68bd5e5eb68df3fb9655af2cbdb8ac9548dbeba3f24e5e385baeec0da603"],"state_sha256":"f345cb457fdc57b27ade0a561d224184b0d7db3f7b904856dcef1d3f163d0b3a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7tPHQI2t0KOY4qZHnHjeZrhaMLLKxFx7s7qxnpntCLx/taFA9LUtUgDBeGLacnHO24BacGjtJ+Y27ECMhtNGCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:51:23.919994Z","bundle_sha256":"2ed07875b784434c2b73399f6cd45c0d00d2320c87e5a37964c89c3e6edea8e7"}}