{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6CUXCWXYYBEPQK6X5GTIRTGQ7A","short_pith_number":"pith:6CUXCWXY","schema_version":"1.0","canonical_sha256":"f0a9715af8c048f82bd7e9a688ccd0f807eec219cd8a5713c8bf30c52089855a","source":{"kind":"arxiv","id":"2208.10576","version":1},"attestation_state":"computed","paper":{"title":"Different Spectral Representations in Optimized Artificial Neural Networks and Brains","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","q-bio.NC"],"primary_cat":"cs.LG","authors_text":"Alona Fyshe, Cassidy Pirlot, Joel Zylberberg, Richard C. Gerum","submitted_at":"2022-08-22T20:13:20Z","abstract_excerpt":"Recent studies suggest that artificial neural networks (ANNs) that match the spectral properties of the mammalian visual cortex -- namely, the $\\sim 1/n$ eigenspectrum of the covariance matrix of neural activities -- achieve higher object recognition performance and robustness to adversarial attacks than those that do not. To our knowledge, however, no previous work systematically explored how modifying the ANN's spectral properties affects performance. To fill this gap, we performed a systematic search over spectral regularizers, forcing the ANN's eigenspectrum to follow $1/n^\\alpha$ power la"},"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":"2208.10576","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-22T20:13:20Z","cross_cats_sorted":["cs.AI","q-bio.NC"],"title_canon_sha256":"6ad88cf6fee5bdbafeeeee37d616360fa2e6e0e40221147d4976d21164b511d0","abstract_canon_sha256":"999fc60d99c67395a39d5222d0116b297c2186ae959d7cc1df85d4498fe879d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:50:36.993185Z","signature_b64":"qFRoW2Tp4tQm55Uw5qB6740rzvxmK4+sErqnjIYn3QaWgjq/HtVD4taReU6KiDvn1bsiz2WZ4SBIELGgRm9VAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0a9715af8c048f82bd7e9a688ccd0f807eec219cd8a5713c8bf30c52089855a","last_reissued_at":"2026-07-05T04:50:36.992726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:50:36.992726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Different Spectral Representations in Optimized Artificial Neural Networks and Brains","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","q-bio.NC"],"primary_cat":"cs.LG","authors_text":"Alona Fyshe, Cassidy Pirlot, Joel Zylberberg, Richard C. Gerum","submitted_at":"2022-08-22T20:13:20Z","abstract_excerpt":"Recent studies suggest that artificial neural networks (ANNs) that match the spectral properties of the mammalian visual cortex -- namely, the $\\sim 1/n$ eigenspectrum of the covariance matrix of neural activities -- achieve higher object recognition performance and robustness to adversarial attacks than those that do not. To our knowledge, however, no previous work systematically explored how modifying the ANN's spectral properties affects performance. To fill this gap, we performed a systematic search over spectral regularizers, forcing the ANN's eigenspectrum to follow $1/n^\\alpha$ power la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.10576","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/2208.10576/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":"2208.10576","created_at":"2026-07-05T04:50:36.992778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.10576v1","created_at":"2026-07-05T04:50:36.992778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.10576","created_at":"2026-07-05T04:50:36.992778+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CUXCWXYYBEP","created_at":"2026-07-05T04:50:36.992778+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CUXCWXYYBEPQK6X","created_at":"2026-07-05T04:50:36.992778+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CUXCWXY","created_at":"2026-07-05T04:50:36.992778+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08188","citing_title":"Neuroscience-Inspired Analyses of Visual Interestingness in Multimodal Transformers","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CUXCWXYYBEPQK6X5GTIRTGQ7A","json":"https://pith.science/pith/6CUXCWXYYBEPQK6X5GTIRTGQ7A.json","graph_json":"https://pith.science/api/pith-number/6CUXCWXYYBEPQK6X5GTIRTGQ7A/graph.json","events_json":"https://pith.science/api/pith-number/6CUXCWXYYBEPQK6X5GTIRTGQ7A/events.json","paper":"https://pith.science/paper/6CUXCWXY"},"agent_actions":{"view_html":"https://pith.science/pith/6CUXCWXYYBEPQK6X5GTIRTGQ7A","download_json":"https://pith.science/pith/6CUXCWXYYBEPQK6X5GTIRTGQ7A.json","view_paper":"https://pith.science/paper/6CUXCWXY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.10576&json=true","fetch_graph":"https://pith.science/api/pith-number/6CUXCWXYYBEPQK6X5GTIRTGQ7A/graph.json","fetch_events":"https://pith.science/api/pith-number/6CUXCWXYYBEPQK6X5GTIRTGQ7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CUXCWXYYBEPQK6X5GTIRTGQ7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CUXCWXYYBEPQK6X5GTIRTGQ7A/action/storage_attestation","attest_author":"https://pith.science/pith/6CUXCWXYYBEPQK6X5GTIRTGQ7A/action/author_attestation","sign_citation":"https://pith.science/pith/6CUXCWXYYBEPQK6X5GTIRTGQ7A/action/citation_signature","submit_replication":"https://pith.science/pith/6CUXCWXYYBEPQK6X5GTIRTGQ7A/action/replication_record"}},"created_at":"2026-07-05T04:50:36.992778+00:00","updated_at":"2026-07-05T04:50:36.992778+00:00"}