{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7TK2J2PNKUU7WBNYBS7OMCDWVW","short_pith_number":"pith:7TK2J2PN","schema_version":"1.0","canonical_sha256":"fcd5a4e9ed5529fb05b80cbee60876adaa1de9a7a94b84cf294f117706e00d2e","source":{"kind":"arxiv","id":"1912.04783","version":5},"attestation_state":"computed","paper":{"title":"Frivolous Units: Wider Networks Are Not Really That Wide","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gabriel Kreiman, Kasper Vinken, Ling Guo, Martin Schrimpf, Stephen Casper, Vanessa D'Amario, Xavier Boix","submitted_at":"2019-12-10T15:53:45Z","abstract_excerpt":"A remarkable characteristic of overparameterized deep neural networks (DNNs) is that their accuracy does not degrade when the network's width is increased. Recent evidence suggests that developing compressible representations is key for adjusting the complexity of large networks to the learning task at hand. However, these compressible representations are poorly understood. A promising strand of research inspired from biology is understanding representations at the unit level as it offers a more granular and intuitive interpretation of the neural mechanisms. In order to better understand what "},"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":"1912.04783","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-10T15:53:45Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"3d95eeb61b374d31fb6bc7c81157328847609d6a416e51d749e90491b65af2af","abstract_canon_sha256":"422aa8bab68cf9abe4b912a983fce4842aeaf5928ca9ec5c8594e5acff4bd07b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:47.518795Z","signature_b64":"HfsYzj7+xHNZe+AMwcQz4atXDjOCj2npMFlpnSAE9/4SqNdQlfI9U+s9NSa5+LGZ/kt8ZBw3Q2e/iF/TX3y7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcd5a4e9ed5529fb05b80cbee60876adaa1de9a7a94b84cf294f117706e00d2e","last_reissued_at":"2026-07-05T02:44:47.518355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:47.518355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frivolous Units: Wider Networks Are Not Really That Wide","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gabriel Kreiman, Kasper Vinken, Ling Guo, Martin Schrimpf, Stephen Casper, Vanessa D'Amario, Xavier Boix","submitted_at":"2019-12-10T15:53:45Z","abstract_excerpt":"A remarkable characteristic of overparameterized deep neural networks (DNNs) is that their accuracy does not degrade when the network's width is increased. Recent evidence suggests that developing compressible representations is key for adjusting the complexity of large networks to the learning task at hand. However, these compressible representations are poorly understood. A promising strand of research inspired from biology is understanding representations at the unit level as it offers a more granular and intuitive interpretation of the neural mechanisms. In order to better understand what "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.04783","kind":"arxiv","version":5},"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/1912.04783/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":"1912.04783","created_at":"2026-07-05T02:44:47.518418+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.04783v5","created_at":"2026-07-05T02:44:47.518418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.04783","created_at":"2026-07-05T02:44:47.518418+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TK2J2PNKUU7","created_at":"2026-07-05T02:44:47.518418+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TK2J2PNKUU7WBNY","created_at":"2026-07-05T02:44:47.518418+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TK2J2PN","created_at":"2026-07-05T02:44:47.518418+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.09196","citing_title":"PDE: Gene Effect Inspired Parameter Dynamic Evolution for Low-light Image Enhancement","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7TK2J2PNKUU7WBNYBS7OMCDWVW","json":"https://pith.science/pith/7TK2J2PNKUU7WBNYBS7OMCDWVW.json","graph_json":"https://pith.science/api/pith-number/7TK2J2PNKUU7WBNYBS7OMCDWVW/graph.json","events_json":"https://pith.science/api/pith-number/7TK2J2PNKUU7WBNYBS7OMCDWVW/events.json","paper":"https://pith.science/paper/7TK2J2PN"},"agent_actions":{"view_html":"https://pith.science/pith/7TK2J2PNKUU7WBNYBS7OMCDWVW","download_json":"https://pith.science/pith/7TK2J2PNKUU7WBNYBS7OMCDWVW.json","view_paper":"https://pith.science/paper/7TK2J2PN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.04783&json=true","fetch_graph":"https://pith.science/api/pith-number/7TK2J2PNKUU7WBNYBS7OMCDWVW/graph.json","fetch_events":"https://pith.science/api/pith-number/7TK2J2PNKUU7WBNYBS7OMCDWVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TK2J2PNKUU7WBNYBS7OMCDWVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TK2J2PNKUU7WBNYBS7OMCDWVW/action/storage_attestation","attest_author":"https://pith.science/pith/7TK2J2PNKUU7WBNYBS7OMCDWVW/action/author_attestation","sign_citation":"https://pith.science/pith/7TK2J2PNKUU7WBNYBS7OMCDWVW/action/citation_signature","submit_replication":"https://pith.science/pith/7TK2J2PNKUU7WBNYBS7OMCDWVW/action/replication_record"}},"created_at":"2026-07-05T02:44:47.518418+00:00","updated_at":"2026-07-05T02:44:47.518418+00:00"}