{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MNX4RTRL5LFYVQT5PYO26RFCSG","short_pith_number":"pith:MNX4RTRL","canonical_record":{"source":{"id":"2607.15482","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T21:57:27Z","cross_cats_sorted":[],"title_canon_sha256":"14fc309e397cb5729d689b19f62b86a8c17de09fb064c48e514264bf04af11b0","abstract_canon_sha256":"f5e1f0c70031c700b4f4852de295a2a42ba4d1691cfb4a1e676f73a9d3bcd56e"},"schema_version":"1.0"},"canonical_sha256":"636fc8ce2beacb8ac27d7e1daf44a291b1c76b5cc79920ef72ee9e30c052956c","source":{"kind":"arxiv","id":"2607.15482","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15482","created_at":"2026-07-20T00:18:36Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15482v1","created_at":"2026-07-20T00:18:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15482","created_at":"2026-07-20T00:18:36Z"},{"alias_kind":"pith_short_12","alias_value":"MNX4RTRL5LFY","created_at":"2026-07-20T00:18:36Z"},{"alias_kind":"pith_short_16","alias_value":"MNX4RTRL5LFYVQT5","created_at":"2026-07-20T00:18:36Z"},{"alias_kind":"pith_short_8","alias_value":"MNX4RTRL","created_at":"2026-07-20T00:18:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MNX4RTRL5LFYVQT5PYO26RFCSG","target":"record","payload":{"canonical_record":{"source":{"id":"2607.15482","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T21:57:27Z","cross_cats_sorted":[],"title_canon_sha256":"14fc309e397cb5729d689b19f62b86a8c17de09fb064c48e514264bf04af11b0","abstract_canon_sha256":"f5e1f0c70031c700b4f4852de295a2a42ba4d1691cfb4a1e676f73a9d3bcd56e"},"schema_version":"1.0"},"canonical_sha256":"636fc8ce2beacb8ac27d7e1daf44a291b1c76b5cc79920ef72ee9e30c052956c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T00:18:36.319346Z","signature_b64":"1CZrXQ6wq6VlR7MxbnGQyhbVgj704MHxvI6zADtQDBT9obVoWvXqYkwH9vDvqZ+pT4DuSz3KqfP6Wx23iCBMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"636fc8ce2beacb8ac27d7e1daf44a291b1c76b5cc79920ef72ee9e30c052956c","last_reissued_at":"2026-07-20T00:18:36.318513Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T00:18:36.318513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.15482","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":"2026-07-20T00:18:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ikk4XaIVQXFZP+prsEHF5Kd+lywy4KnIYcN/cVo1wtjWjsRyA0UllSCsZikseCpZHqmgReKKQFKM14qBsxztAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:15:59.803032Z"},"content_sha256":"6adbd791cddedd0608921819d81071ac60de60eb5e727463569091d5cd74fbfe","schema_version":"1.0","event_id":"sha256:6adbd791cddedd0608921819d81071ac60de60eb5e727463569091d5cd74fbfe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MNX4RTRL5LFYVQT5PYO26RFCSG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inpainting Insights: Elevating Visual XAI with Photorealistic Perturbations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Damien Garreau, Josef Lindl, Mariana Chaves","submitted_at":"2026-07-16T21:57:27Z","abstract_excerpt":"The increasing complexity of state-of-the-art machine learning models has made their behavior progressively harder to interpret, spurring rapid advancements in the field of eXplainable Artificial Intelligence (XAI). Among many methods proposed, perturbation-based approaches play a major role. By systematically altering (perturbing) input features, these approaches measure the impact on the model's predictions. For image data, traditional perturbation techniques, often involve replacing pixel values e.g., with a pre-defined color. However, such approaches, but also more refined deterministic te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15482","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/2607.15482/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":"2026-07-20T00:18:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vwaWZRUNOCo5JLLNAtvv4WF2176mBYTXHejkCUEWjGUjQzAczbB1lgqZYxFPryKAXvGC4SraY4DJWWkFPamUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:15:59.803966Z"},"content_sha256":"f5c2977232fde59b872993b489bcbb7ceae1d763f02d1792319ae7a12cb64e48","schema_version":"1.0","event_id":"sha256:f5c2977232fde59b872993b489bcbb7ceae1d763f02d1792319ae7a12cb64e48"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MNX4RTRL5LFYVQT5PYO26RFCSG/bundle.json","state_url":"https://pith.science/pith/MNX4RTRL5LFYVQT5PYO26RFCSG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MNX4RTRL5LFYVQT5PYO26RFCSG/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":"2026-08-04T15:15:59Z","links":{"resolver":"https://pith.science/pith/MNX4RTRL5LFYVQT5PYO26RFCSG","bundle":"https://pith.science/pith/MNX4RTRL5LFYVQT5PYO26RFCSG/bundle.json","state":"https://pith.science/pith/MNX4RTRL5LFYVQT5PYO26RFCSG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MNX4RTRL5LFYVQT5PYO26RFCSG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MNX4RTRL5LFYVQT5PYO26RFCSG","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":"f5e1f0c70031c700b4f4852de295a2a42ba4d1691cfb4a1e676f73a9d3bcd56e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T21:57:27Z","title_canon_sha256":"14fc309e397cb5729d689b19f62b86a8c17de09fb064c48e514264bf04af11b0"},"schema_version":"1.0","source":{"id":"2607.15482","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15482","created_at":"2026-07-20T00:18:36Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15482v1","created_at":"2026-07-20T00:18:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15482","created_at":"2026-07-20T00:18:36Z"},{"alias_kind":"pith_short_12","alias_value":"MNX4RTRL5LFY","created_at":"2026-07-20T00:18:36Z"},{"alias_kind":"pith_short_16","alias_value":"MNX4RTRL5LFYVQT5","created_at":"2026-07-20T00:18:36Z"},{"alias_kind":"pith_short_8","alias_value":"MNX4RTRL","created_at":"2026-07-20T00:18:36Z"}],"graph_snapshots":[{"event_id":"sha256:f5c2977232fde59b872993b489bcbb7ceae1d763f02d1792319ae7a12cb64e48","target":"graph","created_at":"2026-07-20T00:18:36Z","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/2607.15482/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasing complexity of state-of-the-art machine learning models has made their behavior progressively harder to interpret, spurring rapid advancements in the field of eXplainable Artificial Intelligence (XAI). Among many methods proposed, perturbation-based approaches play a major role. By systematically altering (perturbing) input features, these approaches measure the impact on the model's predictions. For image data, traditional perturbation techniques, often involve replacing pixel values e.g., with a pre-defined color. However, such approaches, but also more refined deterministic te","authors_text":"Damien Garreau, Josef Lindl, Mariana Chaves","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T21:57:27Z","title":"Inpainting Insights: Elevating Visual XAI with Photorealistic Perturbations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15482","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":"sha256:6adbd791cddedd0608921819d81071ac60de60eb5e727463569091d5cd74fbfe","target":"record","created_at":"2026-07-20T00:18:36Z","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":"f5e1f0c70031c700b4f4852de295a2a42ba4d1691cfb4a1e676f73a9d3bcd56e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T21:57:27Z","title_canon_sha256":"14fc309e397cb5729d689b19f62b86a8c17de09fb064c48e514264bf04af11b0"},"schema_version":"1.0","source":{"id":"2607.15482","kind":"arxiv","version":1}},"canonical_sha256":"636fc8ce2beacb8ac27d7e1daf44a291b1c76b5cc79920ef72ee9e30c052956c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"636fc8ce2beacb8ac27d7e1daf44a291b1c76b5cc79920ef72ee9e30c052956c","first_computed_at":"2026-07-20T00:18:36.318513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-20T00:18:36.318513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1CZrXQ6wq6VlR7MxbnGQyhbVgj704MHxvI6zADtQDBT9obVoWvXqYkwH9vDvqZ+pT4DuSz3KqfP6Wx23iCBMDA==","signature_status":"signed_v1","signed_at":"2026-07-20T00:18:36.319346Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.15482","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6adbd791cddedd0608921819d81071ac60de60eb5e727463569091d5cd74fbfe","sha256:f5c2977232fde59b872993b489bcbb7ceae1d763f02d1792319ae7a12cb64e48"],"state_sha256":"7652a2b2348d6c9c33768e59ef604e7252c9440e7f71ce86fdb461b3628a9298"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KYlPMDkN21drqQ6XL2gPHZztmicAWL/2xZ4EJPllA/NPdm5A9FK4ef5SBoVpzLCNehx5bzz/hd+7S+mOlidIDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:15:59.810974Z","bundle_sha256":"017f602dbe7f6f3c126a13d76ca6bb1ba05a8a03fad9b126ddb4f7618511fa9e"}}