{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HB2PQQSVVZ6DJLGULS3DPNKHBI","short_pith_number":"pith:HB2PQQSV","schema_version":"1.0","canonical_sha256":"3874f84255ae7c34acd45cb637b5470a3f553a671a322c660b72f14735668048","source":{"kind":"arxiv","id":"2207.04890","version":1},"attestation_state":"computed","paper":{"title":"The Mean Dimension of Neural Networks -- What causes the interaction effects?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christoph Feinauer, Emanuele Borgonovo, Roman Hahn","submitted_at":"2022-07-11T14:00:06Z","abstract_excerpt":"Owen and Hoyt recently showed that the effective dimension offers key structural information about the input-output mapping underlying an artificial neural network. Along this line of research, this work proposes an estimation procedure that allows the calculation of the mean dimension from a given dataset, without resampling from external distributions. The design yields total indices when features are independent and a variant of total indices when features are correlated. We show that this variant possesses the zero independence property. With synthetic datasets, we analyse how the mean dim"},"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":"2207.04890","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-07-11T14:00:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"294db432b4871834eb69f7a7f3381f479f05024659e7e005fe2e44674bfd8691","abstract_canon_sha256":"184187c8435c24ac7b578c7746cbb0a8e082e3fd71325b2b7b0999b814e2393b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:04.500504Z","signature_b64":"jU3NSPwxa45y92ur8mUdE5r9Gu1/JdHuYMxJ9ldo+pbQPdRodNIo/LMMvaD51Erp1lYj49OLI4BVkBu79Pq/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3874f84255ae7c34acd45cb637b5470a3f553a671a322c660b72f14735668048","last_reissued_at":"2026-07-05T04:39:04.500085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:04.500085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Mean Dimension of Neural Networks -- What causes the interaction effects?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christoph Feinauer, Emanuele Borgonovo, Roman Hahn","submitted_at":"2022-07-11T14:00:06Z","abstract_excerpt":"Owen and Hoyt recently showed that the effective dimension offers key structural information about the input-output mapping underlying an artificial neural network. Along this line of research, this work proposes an estimation procedure that allows the calculation of the mean dimension from a given dataset, without resampling from external distributions. The design yields total indices when features are independent and a variant of total indices when features are correlated. We show that this variant possesses the zero independence property. With synthetic datasets, we analyse how the mean dim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04890","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/2207.04890/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":"2207.04890","created_at":"2026-07-05T04:39:04.500149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.04890v1","created_at":"2026-07-05T04:39:04.500149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04890","created_at":"2026-07-05T04:39:04.500149+00:00"},{"alias_kind":"pith_short_12","alias_value":"HB2PQQSVVZ6D","created_at":"2026-07-05T04:39:04.500149+00:00"},{"alias_kind":"pith_short_16","alias_value":"HB2PQQSVVZ6DJLGU","created_at":"2026-07-05T04:39:04.500149+00:00"},{"alias_kind":"pith_short_8","alias_value":"HB2PQQSV","created_at":"2026-07-05T04:39:04.500149+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HB2PQQSVVZ6DJLGULS3DPNKHBI","json":"https://pith.science/pith/HB2PQQSVVZ6DJLGULS3DPNKHBI.json","graph_json":"https://pith.science/api/pith-number/HB2PQQSVVZ6DJLGULS3DPNKHBI/graph.json","events_json":"https://pith.science/api/pith-number/HB2PQQSVVZ6DJLGULS3DPNKHBI/events.json","paper":"https://pith.science/paper/HB2PQQSV"},"agent_actions":{"view_html":"https://pith.science/pith/HB2PQQSVVZ6DJLGULS3DPNKHBI","download_json":"https://pith.science/pith/HB2PQQSVVZ6DJLGULS3DPNKHBI.json","view_paper":"https://pith.science/paper/HB2PQQSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.04890&json=true","fetch_graph":"https://pith.science/api/pith-number/HB2PQQSVVZ6DJLGULS3DPNKHBI/graph.json","fetch_events":"https://pith.science/api/pith-number/HB2PQQSVVZ6DJLGULS3DPNKHBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HB2PQQSVVZ6DJLGULS3DPNKHBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HB2PQQSVVZ6DJLGULS3DPNKHBI/action/storage_attestation","attest_author":"https://pith.science/pith/HB2PQQSVVZ6DJLGULS3DPNKHBI/action/author_attestation","sign_citation":"https://pith.science/pith/HB2PQQSVVZ6DJLGULS3DPNKHBI/action/citation_signature","submit_replication":"https://pith.science/pith/HB2PQQSVVZ6DJLGULS3DPNKHBI/action/replication_record"}},"created_at":"2026-07-05T04:39:04.500149+00:00","updated_at":"2026-07-05T04:39:04.500149+00:00"}