{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V4NWNXVEELGFKAK2MRPKJVMLCU","short_pith_number":"pith:V4NWNXVE","schema_version":"1.0","canonical_sha256":"af1b66dea422cc55015a645ea4d58b15040f784311896684c2604b53d7289188","source":{"kind":"arxiv","id":"2606.07908","version":1},"attestation_state":"computed","paper":{"title":"Layer-wise Derivative Controlled Networks Achieve Competitive Accuracy and Gradient Stability Across Data Regimes","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rowan Martnishn","submitted_at":"2026-06-06T00:14:22Z","abstract_excerpt":"Derivative-controlled networks based on ChainzRule (CR) combine cubic polynomial layers with a lightweight forward-mode per-layer Jacobian penalty (DREG). In this second paper of a multi-part series, we evaluate the generalization properties of CR across data regimes.\n  We ablate the shape of the DREG coefficient schedule, demonstrating that the optimal annealing range depends on representation noise. On the Pima Diabetes dataset, CR achieves strong low-data performance and maintains a consistent accuracy advantage over baselines from 5\\% to 100\\% training data, supported by exceptionally stab"},"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":"2606.07908","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T00:14:22Z","cross_cats_sorted":[],"title_canon_sha256":"9e44958ba47f77f419de81c66537c1808d4ce9274e501e4554288f710aac623e","abstract_canon_sha256":"d808bcbdafd1894d1d14f327be52958cfc86c4baa5066a6d644e9df4a5c57edd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:55.109514Z","signature_b64":"JjsJ/kyz9j2bWKNqJyWjbrlT3aNQFG26X1ajKq4LWJgugDM1lBu5EF6a5WiDRZt7AB1MjsBXYVLTUgE4Y282Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af1b66dea422cc55015a645ea4d58b15040f784311896684c2604b53d7289188","last_reissued_at":"2026-06-09T01:04:55.109107Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:55.109107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Layer-wise Derivative Controlled Networks Achieve Competitive Accuracy and Gradient Stability Across Data Regimes","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rowan Martnishn","submitted_at":"2026-06-06T00:14:22Z","abstract_excerpt":"Derivative-controlled networks based on ChainzRule (CR) combine cubic polynomial layers with a lightweight forward-mode per-layer Jacobian penalty (DREG). In this second paper of a multi-part series, we evaluate the generalization properties of CR across data regimes.\n  We ablate the shape of the DREG coefficient schedule, demonstrating that the optimal annealing range depends on representation noise. On the Pima Diabetes dataset, CR achieves strong low-data performance and maintains a consistent accuracy advantage over baselines from 5\\% to 100\\% training data, supported by exceptionally stab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07908","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/2606.07908/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":"2606.07908","created_at":"2026-06-09T01:04:55.109167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07908v1","created_at":"2026-06-09T01:04:55.109167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07908","created_at":"2026-06-09T01:04:55.109167+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4NWNXVEELGF","created_at":"2026-06-09T01:04:55.109167+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4NWNXVEELGFKAK2","created_at":"2026-06-09T01:04:55.109167+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4NWNXVE","created_at":"2026-06-09T01:04:55.109167+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/V4NWNXVEELGFKAK2MRPKJVMLCU","json":"https://pith.science/pith/V4NWNXVEELGFKAK2MRPKJVMLCU.json","graph_json":"https://pith.science/api/pith-number/V4NWNXVEELGFKAK2MRPKJVMLCU/graph.json","events_json":"https://pith.science/api/pith-number/V4NWNXVEELGFKAK2MRPKJVMLCU/events.json","paper":"https://pith.science/paper/V4NWNXVE"},"agent_actions":{"view_html":"https://pith.science/pith/V4NWNXVEELGFKAK2MRPKJVMLCU","download_json":"https://pith.science/pith/V4NWNXVEELGFKAK2MRPKJVMLCU.json","view_paper":"https://pith.science/paper/V4NWNXVE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07908&json=true","fetch_graph":"https://pith.science/api/pith-number/V4NWNXVEELGFKAK2MRPKJVMLCU/graph.json","fetch_events":"https://pith.science/api/pith-number/V4NWNXVEELGFKAK2MRPKJVMLCU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4NWNXVEELGFKAK2MRPKJVMLCU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4NWNXVEELGFKAK2MRPKJVMLCU/action/storage_attestation","attest_author":"https://pith.science/pith/V4NWNXVEELGFKAK2MRPKJVMLCU/action/author_attestation","sign_citation":"https://pith.science/pith/V4NWNXVEELGFKAK2MRPKJVMLCU/action/citation_signature","submit_replication":"https://pith.science/pith/V4NWNXVEELGFKAK2MRPKJVMLCU/action/replication_record"}},"created_at":"2026-06-09T01:04:55.109167+00:00","updated_at":"2026-06-09T01:04:55.109167+00:00"}