{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:45C7SB4AS4TZZ3S7ZA3BDNDP7V","short_pith_number":"pith:45C7SB4A","schema_version":"1.0","canonical_sha256":"e745f9078097279cee5fc83611b46ffd7fcb617c69cdafb6a6ba4f7cf5ad6b19","source":{"kind":"arxiv","id":"2607.07884","version":1},"attestation_state":"computed","paper":{"title":"Optimal Learning Rate Scaling Depends on Data in Deep Scalar Linear Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Saxe, Leena Chennuru Vankadara, Peter E. Latham, Yedi Zhang","submitted_at":"2026-07-08T19:39:11Z","abstract_excerpt":"In this short note we consider the gradient descent dynamics of deep scalar linear networks, $f(x) = \\prod_{l=1}^L w_l x$, which enjoy exact time-course solutions for any integer depth. We show that even in this minimal model, the optimal depth-wise learning rate scaling depends on data, whereas data-agnostic scaling rules fail to transfer across depths. Under the data-dependent optimal scaling, the learning dynamics is independent of data and weakly dependent on depth, resulting in a constant linear convergence rate across all depths including infinity. We further show similar data-dependent "},"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":"2607.07884","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T19:39:11Z","cross_cats_sorted":[],"title_canon_sha256":"5e766de8ae006ef1ab0724c8adeb7ee3a6be9c69a5b65678503aa4c3a35607ef","abstract_canon_sha256":"54641ec84b668c90411368d8d8a64355a77de8dd0266e6697acc8c371cd6a7a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T00:19:04.007771Z","signature_b64":"NqfrSMTDNjEqBRHBqUCVhTqP+go0GPkWu9UY15wk9W9Xb+P0JZgvzyBfYPTXDLyxQVz3z3wUs+oBj/mu2ub2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e745f9078097279cee5fc83611b46ffd7fcb617c69cdafb6a6ba4f7cf5ad6b19","last_reissued_at":"2026-07-10T00:19:04.007360Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T00:19:04.007360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Learning Rate Scaling Depends on Data in Deep Scalar Linear Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Saxe, Leena Chennuru Vankadara, Peter E. Latham, Yedi Zhang","submitted_at":"2026-07-08T19:39:11Z","abstract_excerpt":"In this short note we consider the gradient descent dynamics of deep scalar linear networks, $f(x) = \\prod_{l=1}^L w_l x$, which enjoy exact time-course solutions for any integer depth. We show that even in this minimal model, the optimal depth-wise learning rate scaling depends on data, whereas data-agnostic scaling rules fail to transfer across depths. Under the data-dependent optimal scaling, the learning dynamics is independent of data and weakly dependent on depth, resulting in a constant linear convergence rate across all depths including infinity. We further show similar data-dependent "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07884","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/2607.07884/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":"2607.07884","created_at":"2026-07-10T00:19:04.007426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.07884v1","created_at":"2026-07-10T00:19:04.007426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07884","created_at":"2026-07-10T00:19:04.007426+00:00"},{"alias_kind":"pith_short_12","alias_value":"45C7SB4AS4TZ","created_at":"2026-07-10T00:19:04.007426+00:00"},{"alias_kind":"pith_short_16","alias_value":"45C7SB4AS4TZZ3S7","created_at":"2026-07-10T00:19:04.007426+00:00"},{"alias_kind":"pith_short_8","alias_value":"45C7SB4A","created_at":"2026-07-10T00:19:04.007426+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/45C7SB4AS4TZZ3S7ZA3BDNDP7V","json":"https://pith.science/pith/45C7SB4AS4TZZ3S7ZA3BDNDP7V.json","graph_json":"https://pith.science/api/pith-number/45C7SB4AS4TZZ3S7ZA3BDNDP7V/graph.json","events_json":"https://pith.science/api/pith-number/45C7SB4AS4TZZ3S7ZA3BDNDP7V/events.json","paper":"https://pith.science/paper/45C7SB4A"},"agent_actions":{"view_html":"https://pith.science/pith/45C7SB4AS4TZZ3S7ZA3BDNDP7V","download_json":"https://pith.science/pith/45C7SB4AS4TZZ3S7ZA3BDNDP7V.json","view_paper":"https://pith.science/paper/45C7SB4A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.07884&json=true","fetch_graph":"https://pith.science/api/pith-number/45C7SB4AS4TZZ3S7ZA3BDNDP7V/graph.json","fetch_events":"https://pith.science/api/pith-number/45C7SB4AS4TZZ3S7ZA3BDNDP7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45C7SB4AS4TZZ3S7ZA3BDNDP7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45C7SB4AS4TZZ3S7ZA3BDNDP7V/action/storage_attestation","attest_author":"https://pith.science/pith/45C7SB4AS4TZZ3S7ZA3BDNDP7V/action/author_attestation","sign_citation":"https://pith.science/pith/45C7SB4AS4TZZ3S7ZA3BDNDP7V/action/citation_signature","submit_replication":"https://pith.science/pith/45C7SB4AS4TZZ3S7ZA3BDNDP7V/action/replication_record"}},"created_at":"2026-07-10T00:19:04.007426+00:00","updated_at":"2026-07-10T00:19:04.007426+00:00"}