{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W4YYLOY4WW7NYZOR7FKAYPXTCZ","short_pith_number":"pith:W4YYLOY4","schema_version":"1.0","canonical_sha256":"b73185bb1cb5bedc65d1f9540c3ef31674b37c34202c51a01534b3379d20ee58","source":{"kind":"arxiv","id":"2308.06887","version":2},"attestation_state":"computed","paper":{"title":"Robustified ANNs Reveal Wormholes Between Human Category Percepts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.NC"],"primary_cat":"cs.CV","authors_text":"Guy Gaziv, James J. DiCarlo, Michael J. Lee","submitted_at":"2023-08-14T01:47:26Z","abstract_excerpt":"The visual object category reports of artificial neural networks (ANNs) are notoriously sensitive to tiny, adversarial image perturbations. Because human category reports (aka human percepts) are thought to be insensitive to those same small-norm perturbations -- and locally stable in general -- this argues that ANNs are incomplete scientific models of human visual perception. Consistent with this, we show that when small-norm image perturbations are generated by standard ANN models, human object category percepts are indeed highly stable. However, in this very same \"human-presumed-stable\" reg"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2308.06887","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-14T01:47:26Z","cross_cats_sorted":["cs.AI","q-bio.NC"],"title_canon_sha256":"0bc5012491aad6d00fb74475dc59a29e6091c7685ae36fa986e639d47e90f354","abstract_canon_sha256":"8bd94c5a0528e31014d5520f713f986644da23a5728c80985b052b531a8d7752"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:09.695495Z","signature_b64":"sF1XRWo1KGpKuHgRfCsBvsQjez6qmiZYs88gQ6b/cb4bh/2oqMLuVRyUbzyey24dQRSts7yDlXltX3Kx/s0VBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b73185bb1cb5bedc65d1f9540c3ef31674b37c34202c51a01534b3379d20ee58","last_reissued_at":"2026-07-05T06:57:09.695046Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:09.695046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robustified ANNs Reveal Wormholes Between Human Category Percepts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.NC"],"primary_cat":"cs.CV","authors_text":"Guy Gaziv, James J. DiCarlo, Michael J. Lee","submitted_at":"2023-08-14T01:47:26Z","abstract_excerpt":"The visual object category reports of artificial neural networks (ANNs) are notoriously sensitive to tiny, adversarial image perturbations. Because human category reports (aka human percepts) are thought to be insensitive to those same small-norm perturbations -- and locally stable in general -- this argues that ANNs are incomplete scientific models of human visual perception. Consistent with this, we show that when small-norm image perturbations are generated by standard ANN models, human object category percepts are indeed highly stable. However, in this very same \"human-presumed-stable\" reg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06887","kind":"arxiv","version":2},"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/2308.06887/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2308.06887","created_at":"2026-07-05T06:57:09.695103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.06887v2","created_at":"2026-07-05T06:57:09.695103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06887","created_at":"2026-07-05T06:57:09.695103+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4YYLOY4WW7N","created_at":"2026-07-05T06:57:09.695103+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4YYLOY4WW7NYZOR","created_at":"2026-07-05T06:57:09.695103+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4YYLOY4","created_at":"2026-07-05T06:57:09.695103+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05633","citing_title":"Noninvasive precision modulation of high-level neural population activity via natural vision perturbations","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W4YYLOY4WW7NYZOR7FKAYPXTCZ","json":"https://pith.science/pith/W4YYLOY4WW7NYZOR7FKAYPXTCZ.json","graph_json":"https://pith.science/api/pith-number/W4YYLOY4WW7NYZOR7FKAYPXTCZ/graph.json","events_json":"https://pith.science/api/pith-number/W4YYLOY4WW7NYZOR7FKAYPXTCZ/events.json","paper":"https://pith.science/paper/W4YYLOY4"},"agent_actions":{"view_html":"https://pith.science/pith/W4YYLOY4WW7NYZOR7FKAYPXTCZ","download_json":"https://pith.science/pith/W4YYLOY4WW7NYZOR7FKAYPXTCZ.json","view_paper":"https://pith.science/paper/W4YYLOY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.06887&json=true","fetch_graph":"https://pith.science/api/pith-number/W4YYLOY4WW7NYZOR7FKAYPXTCZ/graph.json","fetch_events":"https://pith.science/api/pith-number/W4YYLOY4WW7NYZOR7FKAYPXTCZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4YYLOY4WW7NYZOR7FKAYPXTCZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4YYLOY4WW7NYZOR7FKAYPXTCZ/action/storage_attestation","attest_author":"https://pith.science/pith/W4YYLOY4WW7NYZOR7FKAYPXTCZ/action/author_attestation","sign_citation":"https://pith.science/pith/W4YYLOY4WW7NYZOR7FKAYPXTCZ/action/citation_signature","submit_replication":"https://pith.science/pith/W4YYLOY4WW7NYZOR7FKAYPXTCZ/action/replication_record"}},"created_at":"2026-07-05T06:57:09.695103+00:00","updated_at":"2026-07-05T06:57:09.695103+00:00"}