{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MUNVWGCK3M7JTGI2IKYVD5XC7I","short_pith_number":"pith:MUNVWGCK","schema_version":"1.0","canonical_sha256":"651b5b184adb3e99991a42b151f6e2fa2ae189a397710a39b994ac2f82015673","source":{"kind":"arxiv","id":"2301.13710","version":1},"attestation_state":"computed","paper":{"title":"On the Initialisation of Wide Low-Rank Feedforward Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jared Tanner, Thiziri Nait Saada","submitted_at":"2023-01-31T15:40:50Z","abstract_excerpt":"The edge-of-chaos dynamics of wide randomly initialized low-rank feedforward networks are analyzed. Formulae for the optimal weight and bias variances are extended from the full-rank to low-rank setting and are shown to follow from multiplicative scaling. The principle second order effect, the variance of the input-output Jacobian, is derived and shown to increase as the rank to width ratio decreases. These results inform practitioners how to randomly initialize feedforward networks with a reduced number of learnable parameters while in the same ambient dimension, allowing reductions in the co"},"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":"2301.13710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2023-01-31T15:40:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0a4cba5347e4440de149c1c52c132fe33245bb4c68918814c1f5c491dfd7c38c","abstract_canon_sha256":"3419ca6b788aa3315a91057f66148f82942d6ffd6d65742bfd17c3678d5966b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:17.830125Z","signature_b64":"BmZ7knjm2UL628qvgRnVRXmS4J4JRZ/seqFx9+plKkcbl3EG7egsBCFxSxZm3j+6c8AHLHDdBligHjYlib4nBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"651b5b184adb3e99991a42b151f6e2fa2ae189a397710a39b994ac2f82015673","last_reissued_at":"2026-07-05T05:37:17.829637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:17.829637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Initialisation of Wide Low-Rank Feedforward Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jared Tanner, Thiziri Nait Saada","submitted_at":"2023-01-31T15:40:50Z","abstract_excerpt":"The edge-of-chaos dynamics of wide randomly initialized low-rank feedforward networks are analyzed. Formulae for the optimal weight and bias variances are extended from the full-rank to low-rank setting and are shown to follow from multiplicative scaling. The principle second order effect, the variance of the input-output Jacobian, is derived and shown to increase as the rank to width ratio decreases. These results inform practitioners how to randomly initialize feedforward networks with a reduced number of learnable parameters while in the same ambient dimension, allowing reductions in the co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13710","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/2301.13710/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":"2301.13710","created_at":"2026-07-05T05:37:17.829711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13710v1","created_at":"2026-07-05T05:37:17.829711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13710","created_at":"2026-07-05T05:37:17.829711+00:00"},{"alias_kind":"pith_short_12","alias_value":"MUNVWGCK3M7J","created_at":"2026-07-05T05:37:17.829711+00:00"},{"alias_kind":"pith_short_16","alias_value":"MUNVWGCK3M7JTGI2","created_at":"2026-07-05T05:37:17.829711+00:00"},{"alias_kind":"pith_short_8","alias_value":"MUNVWGCK","created_at":"2026-07-05T05:37:17.829711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02608","citing_title":"Pruning Deep Neural Networks via the Marchenko--Pastur Distribution","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03667","citing_title":"ELAS: Efficient Pre-Training of Low-Rank Large Language Models via 2:4 Activation Sparsity","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MUNVWGCK3M7JTGI2IKYVD5XC7I","json":"https://pith.science/pith/MUNVWGCK3M7JTGI2IKYVD5XC7I.json","graph_json":"https://pith.science/api/pith-number/MUNVWGCK3M7JTGI2IKYVD5XC7I/graph.json","events_json":"https://pith.science/api/pith-number/MUNVWGCK3M7JTGI2IKYVD5XC7I/events.json","paper":"https://pith.science/paper/MUNVWGCK"},"agent_actions":{"view_html":"https://pith.science/pith/MUNVWGCK3M7JTGI2IKYVD5XC7I","download_json":"https://pith.science/pith/MUNVWGCK3M7JTGI2IKYVD5XC7I.json","view_paper":"https://pith.science/paper/MUNVWGCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13710&json=true","fetch_graph":"https://pith.science/api/pith-number/MUNVWGCK3M7JTGI2IKYVD5XC7I/graph.json","fetch_events":"https://pith.science/api/pith-number/MUNVWGCK3M7JTGI2IKYVD5XC7I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MUNVWGCK3M7JTGI2IKYVD5XC7I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MUNVWGCK3M7JTGI2IKYVD5XC7I/action/storage_attestation","attest_author":"https://pith.science/pith/MUNVWGCK3M7JTGI2IKYVD5XC7I/action/author_attestation","sign_citation":"https://pith.science/pith/MUNVWGCK3M7JTGI2IKYVD5XC7I/action/citation_signature","submit_replication":"https://pith.science/pith/MUNVWGCK3M7JTGI2IKYVD5XC7I/action/replication_record"}},"created_at":"2026-07-05T05:37:17.829711+00:00","updated_at":"2026-07-05T05:37:17.829711+00:00"}