{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Z3VOTPH27WVQLJATBJW7O52P6U","short_pith_number":"pith:Z3VOTPH2","canonical_record":{"source":{"id":"2605.12937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T03:16:12Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"b5eb7a1701914019b0f7cc7f253006692ab2d36df3efb6700cc140f177f577cf","abstract_canon_sha256":"b39d316020eaf5f3aa6c9c8ac0375942748c164a375566d888e1ecf5084c25da"},"schema_version":"1.0"},"canonical_sha256":"ceeae9bcfafdab05a4130a6df7774ff52d4faa3751a258cd028cd71c500a2fd5","source":{"kind":"arxiv","id":"2605.12937","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12937","created_at":"2026-05-18T03:09:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12937v1","created_at":"2026-05-18T03:09:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12937","created_at":"2026-05-18T03:09:09Z"},{"alias_kind":"pith_short_12","alias_value":"Z3VOTPH27WVQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"Z3VOTPH27WVQLJAT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"Z3VOTPH2","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Z3VOTPH27WVQLJATBJW7O52P6U","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T03:16:12Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"b5eb7a1701914019b0f7cc7f253006692ab2d36df3efb6700cc140f177f577cf","abstract_canon_sha256":"b39d316020eaf5f3aa6c9c8ac0375942748c164a375566d888e1ecf5084c25da"},"schema_version":"1.0"},"canonical_sha256":"ceeae9bcfafdab05a4130a6df7774ff52d4faa3751a258cd028cd71c500a2fd5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:09.819349Z","signature_b64":"jnJWpT0i5SfEBxWSAvEBqaFeTZS0WNyhchBW/lnRet1WhkJtTJBJDDxOh5++XNZh/0fZ7MXQ2HE7TpZhjpsoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ceeae9bcfafdab05a4130a6df7774ff52d4faa3751a258cd028cd71c500a2fd5","last_reissued_at":"2026-05-18T03:09:09.818545Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:09.818545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12937","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":"2026-05-18T03:09:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NM0AafFDc8d2pJHJJUDdWGJEpkeY4t270O8fpOIrC6v/m82mlbtx42+CFqaLs5bicp9CNtUcMWHp6/53Ci/AAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T13:42:23.434684Z"},"content_sha256":"b8222b9eb11220ccbc349eecf8d6059c486ee0363342cfae74319c5c85a70d3b","schema_version":"1.0","event_id":"sha256:b8222b9eb11220ccbc349eecf8d6059c486ee0363342cfae74319c5c85a70d3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Z3VOTPH27WVQLJATBJW7O52P6U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AuraMask: An Extensible Pipeline for Developing Aesthetic Anti-Facial Recognition Image Filters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"AuraMask pipeline produces aesthetic filters that block facial recognition while matching Instagram styles.","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CV","authors_text":"Jacob Lagogiannis, Rosa I. Arriaga, Sauvik Das, William Agnew","submitted_at":"2026-05-13T03:16:12Z","abstract_excerpt":"Anti-facial recognition (AFR) image filters alter images in ways that are subtle to people but blinding to computer vision. Yet, despite widespread interest in these technologies to subvert surveillance, users rarely use them in practice -- because the ``subtle'' alterations are visible enough to conflict with users' self-presentation goals. To address this challenge, we propose AuraMask: a novel approach to creating AFR filters that are both adversarially effective and aesthetically acceptable. Using AuraMask, we produce 40 ``aesthetic'' filters that emulate popular ``one-click'' Instagram im"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Using AuraMask, we produce 40 ``aesthetic'' filters that emulate popular ``one-click'' Instagram image filters. We show that AuraMask filters meet or exceed the adversarial effectiveness of prior methods against open-source facial recognition models. Moreover, in a controlled online user study (N=630) we confirm these filters achieve significantly higher user acceptance than prior methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That effectiveness demonstrated on open-source facial recognition models and acceptance in a controlled online study will generalize to proprietary real-world systems and diverse everyday usage contexts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AuraMask produces 40 aesthetic anti-facial recognition filters that match or exceed prior adversarial effectiveness and achieve significantly higher user acceptance in a 630-person study.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"AuraMask pipeline produces aesthetic filters that block facial recognition while matching Instagram styles.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"165ae61f00ba119d24e1a8dfe96a87dff06e2c18b0a1c79c48a3155940c830a0"},"source":{"id":"2605.12937","kind":"arxiv","version":1},"verdict":{"id":"97782a68-496b-4c82-9f51-c22468cd9da9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:08:46.755526Z","strongest_claim":"Using AuraMask, we produce 40 ``aesthetic'' filters that emulate popular ``one-click'' Instagram image filters. We show that AuraMask filters meet or exceed the adversarial effectiveness of prior methods against open-source facial recognition models. Moreover, in a controlled online user study (N=630) we confirm these filters achieve significantly higher user acceptance than prior methods.","one_line_summary":"AuraMask produces 40 aesthetic anti-facial recognition filters that match or exceed prior adversarial effectiveness and achieve significantly higher user acceptance in a 630-person study.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That effectiveness demonstrated on open-source facial recognition models and acceptance in a controlled online study will generalize to proprietary real-world systems and diverse everyday usage contexts.","pith_extraction_headline":"AuraMask pipeline produces aesthetic filters that block facial recognition while matching Instagram styles."},"references":{"count":125,"sample":[{"doi":"","year":2023,"title":"William Agnew, Kevin R McKee, I Gabriel, J Kay, W Isaac, AS Bergman, S El-Sayed, and S Mohamed. 2023. Technologies of Resistance to AI.Equity and Access in Algorithms, Mechanisms, and Optimization(202","work_id":"7a1c4026-293d-440b-97b0-3f06eea96f5c","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2007,"title":"Good, Simon King, Mor Naaman, and Rahul Nair","work_id":"d8425811-4cb1-4a78-8663-ed300933cd27","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey","work_id":"1e85f197-a9a6-46c1-8bd7-1bbb7ea43c13","ref_index":3,"cited_arxiv_id":"1801.00553","is_internal_anchor":true},{"doi":"10.48550/arxiv.1802.06955","year":2018,"title":"Recurrent residual convolu- tional neural network based on u-net (r2u-net) for medical image segmentation","work_id":"e753528c-df4e-48dc-a4e1-9ca185c12701","ref_index":4,"cited_arxiv_id":"1802.06955","is_internal_anchor":true},{"doi":"","year":2020,"title":"Bertenthal, and Apu Kapadia","work_id":"c44261aa-04fa-4db2-8426-ad651b467af4","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":125,"snapshot_sha256":"d437a943d2f21d80df2247cebd4be1f325763796e8f9e0a4b450b80461940e30","internal_anchors":9},"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":"97782a68-496b-4c82-9f51-c22468cd9da9"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UZB2yUcd2IvcdpsBqI+E8drjs0mw5EAPa1rZ+MDWcWcuGthOw2DlLjMw6XpCzl95H2RdTL9Q9X2z4L+bcBfGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T13:42:23.435650Z"},"content_sha256":"9f4a3d82a20e021e410d977b5076f1314ca1293e84d10a8c7e57d9d3ed2b258c","schema_version":"1.0","event_id":"sha256:9f4a3d82a20e021e410d977b5076f1314ca1293e84d10a8c7e57d9d3ed2b258c"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:Z3VOTPH27WVQLJATBJW7O52P6U","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1038/d41586-024-03990-224) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Nicola Jones. 2024. The AI Revolution Is Running out of Data. What Can Researchers Do?Nature636, 8042 (Dec. 2024), 290–292. doi:10.1038/d41586- 024-03990-2 24 Lagogiannis et al","arxiv_id":"2605.12937","detector":"doi_compliance","evidence":{"ref_index":53,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Nicola Jones. 2024. The AI Revolution Is Running out of Data. What Can Researchers Do?Nature636, 8042 (Dec. 2024), 290–292. doi:10.1038/d41586- 024-03990-2 24 Lagogiannis et al","reconstructed_doi":"10.1038/d41586-024-03990-224"},"severity":"advisory","ref_index":53,"audited_at":"2026-05-19T06:58:14.583842Z","event_type":"pith.integrity.v1","detected_doi":"10.1038/d41586-024-03990-224","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"2dbd2e50069db146248294c5fdaafad734a11e559a0c7fe692496df369585600","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":245,"payload_sha256":"95507e41b3e758767c3fd10566d8462a2f4a619c071d8f711c30f621b7798691","signature_b64":"EwYfflBC7ZUtv+IS77hQpf5AgQadet1H7zaprZSAoJgFtfG8a6DlGFuI6UBwCuRZIXG7tTOmx/V4m1SdooKVBQ==","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":"2026-05-19T07:01:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vQN5TgMxqsnsuypgAFeYoYb/ZAYeTyMazAES7THG9CQ9Oe8mMrwWkrexdKPCia9XfPNp0pr+30IqRX94Kjp2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T13:42:23.436944Z"},"content_sha256":"b77ce687870c86d40895a111ffbe5a39bdaa93ffeeeb8be8bf9df89e7c6425b1","schema_version":"1.0","event_id":"sha256:b77ce687870c86d40895a111ffbe5a39bdaa93ffeeeb8be8bf9df89e7c6425b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z3VOTPH27WVQLJATBJW7O52P6U/bundle.json","state_url":"https://pith.science/pith/Z3VOTPH27WVQLJATBJW7O52P6U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z3VOTPH27WVQLJATBJW7O52P6U/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":"2026-05-21T13:42:23Z","links":{"resolver":"https://pith.science/pith/Z3VOTPH27WVQLJATBJW7O52P6U","bundle":"https://pith.science/pith/Z3VOTPH27WVQLJATBJW7O52P6U/bundle.json","state":"https://pith.science/pith/Z3VOTPH27WVQLJATBJW7O52P6U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z3VOTPH27WVQLJATBJW7O52P6U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Z3VOTPH27WVQLJATBJW7O52P6U","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b39d316020eaf5f3aa6c9c8ac0375942748c164a375566d888e1ecf5084c25da","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T03:16:12Z","title_canon_sha256":"b5eb7a1701914019b0f7cc7f253006692ab2d36df3efb6700cc140f177f577cf"},"schema_version":"1.0","source":{"id":"2605.12937","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12937","created_at":"2026-05-18T03:09:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12937v1","created_at":"2026-05-18T03:09:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12937","created_at":"2026-05-18T03:09:09Z"},{"alias_kind":"pith_short_12","alias_value":"Z3VOTPH27WVQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"Z3VOTPH27WVQLJAT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"Z3VOTPH2","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:9f4a3d82a20e021e410d977b5076f1314ca1293e84d10a8c7e57d9d3ed2b258c","target":"graph","created_at":"2026-05-18T03:09:09Z","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":"Using AuraMask, we produce 40 ``aesthetic'' filters that emulate popular ``one-click'' Instagram image filters. We show that AuraMask filters meet or exceed the adversarial effectiveness of prior methods against open-source facial recognition models. Moreover, in a controlled online user study (N=630) we confirm these filters achieve significantly higher user acceptance than prior methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That effectiveness demonstrated on open-source facial recognition models and acceptance in a controlled online study will generalize to proprietary real-world systems and diverse everyday usage contexts."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"AuraMask produces 40 aesthetic anti-facial recognition filters that match or exceed prior adversarial effectiveness and achieve significantly higher user acceptance in a 630-person study."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"AuraMask pipeline produces aesthetic filters that block facial recognition while matching Instagram styles."}],"snapshot_sha256":"165ae61f00ba119d24e1a8dfe96a87dff06e2c18b0a1c79c48a3155940c830a0"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Anti-facial recognition (AFR) image filters alter images in ways that are subtle to people but blinding to computer vision. Yet, despite widespread interest in these technologies to subvert surveillance, users rarely use them in practice -- because the ``subtle'' alterations are visible enough to conflict with users' self-presentation goals. To address this challenge, we propose AuraMask: a novel approach to creating AFR filters that are both adversarially effective and aesthetically acceptable. Using AuraMask, we produce 40 ``aesthetic'' filters that emulate popular ``one-click'' Instagram im","authors_text":"Jacob Lagogiannis, Rosa I. Arriaga, Sauvik Das, William Agnew","cross_cats":["cs.AI","cs.HC"],"headline":"AuraMask pipeline produces aesthetic filters that block facial recognition while matching Instagram styles.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T03:16:12Z","title":"AuraMask: An Extensible Pipeline for Developing Aesthetic Anti-Facial Recognition Image Filters"},"references":{"count":125,"internal_anchors":9,"resolved_work":125,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"William Agnew, Kevin R McKee, I Gabriel, J Kay, W Isaac, AS Bergman, S El-Sayed, and S Mohamed. 2023. Technologies of Resistance to AI.Equity and Access in Algorithms, Mechanisms, and Optimization(202","work_id":"7a1c4026-293d-440b-97b0-3f06eea96f5c","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Good, Simon King, Mor Naaman, and Rahul Nair","work_id":"d8425811-4cb1-4a78-8663-ed300933cd27","year":2007},{"cited_arxiv_id":"1801.00553","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey","work_id":"1e85f197-a9a6-46c1-8bd7-1bbb7ea43c13","year":2018},{"cited_arxiv_id":"1802.06955","doi":"10.48550/arxiv.1802.06955","is_internal_anchor":true,"ref_index":4,"title":"Recurrent residual convolu- tional neural network based on u-net (r2u-net) for medical image segmentation","work_id":"e753528c-df4e-48dc-a4e1-9ca185c12701","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Bertenthal, and Apu Kapadia","work_id":"c44261aa-04fa-4db2-8426-ad651b467af4","year":2020}],"snapshot_sha256":"d437a943d2f21d80df2247cebd4be1f325763796e8f9e0a4b450b80461940e30"},"source":{"id":"2605.12937","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:08:46.755526Z","id":"97782a68-496b-4c82-9f51-c22468cd9da9","model_set":{"reader":"grok-4.3"},"one_line_summary":"AuraMask produces 40 aesthetic anti-facial recognition filters that match or exceed prior adversarial effectiveness and achieve significantly higher user acceptance in a 630-person study.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"AuraMask pipeline produces aesthetic filters that block facial recognition while matching Instagram styles.","strongest_claim":"Using AuraMask, we produce 40 ``aesthetic'' filters that emulate popular ``one-click'' Instagram image filters. We show that AuraMask filters meet or exceed the adversarial effectiveness of prior methods against open-source facial recognition models. Moreover, in a controlled online user study (N=630) we confirm these filters achieve significantly higher user acceptance than prior methods.","weakest_assumption":"That effectiveness demonstrated on open-source facial recognition models and acceptance in a controlled online study will generalize to proprietary real-world systems and diverse everyday usage contexts."}},"verdict_id":"97782a68-496b-4c82-9f51-c22468cd9da9"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b8222b9eb11220ccbc349eecf8d6059c486ee0363342cfae74319c5c85a70d3b","target":"record","created_at":"2026-05-18T03:09:09Z","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":"b39d316020eaf5f3aa6c9c8ac0375942748c164a375566d888e1ecf5084c25da","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T03:16:12Z","title_canon_sha256":"b5eb7a1701914019b0f7cc7f253006692ab2d36df3efb6700cc140f177f577cf"},"schema_version":"1.0","source":{"id":"2605.12937","kind":"arxiv","version":1}},"canonical_sha256":"ceeae9bcfafdab05a4130a6df7774ff52d4faa3751a258cd028cd71c500a2fd5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ceeae9bcfafdab05a4130a6df7774ff52d4faa3751a258cd028cd71c500a2fd5","first_computed_at":"2026-05-18T03:09:09.818545Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:09.818545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jnJWpT0i5SfEBxWSAvEBqaFeTZS0WNyhchBW/lnRet1WhkJtTJBJDDxOh5++XNZh/0fZ7MXQ2HE7TpZhjpsoBA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:09.819349Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12937","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8222b9eb11220ccbc349eecf8d6059c486ee0363342cfae74319c5c85a70d3b","sha256:9f4a3d82a20e021e410d977b5076f1314ca1293e84d10a8c7e57d9d3ed2b258c","sha256:b77ce687870c86d40895a111ffbe5a39bdaa93ffeeeb8be8bf9df89e7c6425b1"],"state_sha256":"c7c423a76319f5474e40306a9cbe1da0d4c012a8176b2039dc61cad6dd268fc1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cP5ug8FA8Szsky8bdlEKz+SM+PIaw2gfrsWAEui3+IJPtUDg5htzhJjrdQS5j1h1zuaedaPTP8BSGp2hP5z7AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T13:42:23.440750Z","bundle_sha256":"02a9025f1c5eb41b546d99bbac9c7e13231855e66f04d865ee92177857aa750b"}}