{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BZWQ4MOSUYWHG2RCJCC3Z5YDBH","short_pith_number":"pith:BZWQ4MOS","schema_version":"1.0","canonical_sha256":"0e6d0e31d2a62c736a224885bcf70309e4bd627a26847d089778193911d0500a","source":{"kind":"arxiv","id":"2605.24340","version":1},"attestation_state":"computed","paper":{"title":"ChainzRule: Sample-Efficient, Robust Deep Learning Across Tabular, NLP, and Vision Tasks","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rowan Martnishn","submitted_at":"2026-05-23T01:52:50Z","abstract_excerpt":"Production deep learning systems across enterprise domains operate under constraints that academic benchmarks routinely obscure: labeled data is expensive, inference budgets are tight, and models that cannot explain their behavior are difficult to trust and maintain. We present ChainzRule (CR), a neural architecture replacing typical activations with learnable polynomial layers governed by Differential Regularization (DREG), a layer-wise Jacobian penalty computed analytically during the forward pass at standard inference cost. The core claim is that bounding intermediate derivatives forces the"},"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":"2605.24340","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T01:52:50Z","cross_cats_sorted":[],"title_canon_sha256":"c1378eeb84bffe69ac7c8342cf1c20269b81eed9b169813e488ac0f0f44c55b5","abstract_canon_sha256":"089a23e6c89b95df17c1bf5ca0cb54ea9d07210daff50d686c16a60098c37a1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:00.759893Z","signature_b64":"z08pxwvTaVBgLPlQdtZKFaywVJdacTMZiiXE5SOLwCIwv8E7MiXsk00d6lmdj2LGzoIn8a5UOpb3K0v5jBqoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e6d0e31d2a62c736a224885bcf70309e4bd627a26847d089778193911d0500a","last_reissued_at":"2026-05-26T01:03:00.759352Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:00.759352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChainzRule: Sample-Efficient, Robust Deep Learning Across Tabular, NLP, and Vision Tasks","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rowan Martnishn","submitted_at":"2026-05-23T01:52:50Z","abstract_excerpt":"Production deep learning systems across enterprise domains operate under constraints that academic benchmarks routinely obscure: labeled data is expensive, inference budgets are tight, and models that cannot explain their behavior are difficult to trust and maintain. We present ChainzRule (CR), a neural architecture replacing typical activations with learnable polynomial layers governed by Differential Regularization (DREG), a layer-wise Jacobian penalty computed analytically during the forward pass at standard inference cost. The core claim is that bounding intermediate derivatives forces the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24340","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/2605.24340/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":"2605.24340","created_at":"2026-05-26T01:03:00.759441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24340v1","created_at":"2026-05-26T01:03:00.759441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24340","created_at":"2026-05-26T01:03:00.759441+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZWQ4MOSUYWH","created_at":"2026-05-26T01:03:00.759441+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZWQ4MOSUYWHG2RC","created_at":"2026-05-26T01:03:00.759441+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZWQ4MOS","created_at":"2026-05-26T01:03:00.759441+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/BZWQ4MOSUYWHG2RCJCC3Z5YDBH","json":"https://pith.science/pith/BZWQ4MOSUYWHG2RCJCC3Z5YDBH.json","graph_json":"https://pith.science/api/pith-number/BZWQ4MOSUYWHG2RCJCC3Z5YDBH/graph.json","events_json":"https://pith.science/api/pith-number/BZWQ4MOSUYWHG2RCJCC3Z5YDBH/events.json","paper":"https://pith.science/paper/BZWQ4MOS"},"agent_actions":{"view_html":"https://pith.science/pith/BZWQ4MOSUYWHG2RCJCC3Z5YDBH","download_json":"https://pith.science/pith/BZWQ4MOSUYWHG2RCJCC3Z5YDBH.json","view_paper":"https://pith.science/paper/BZWQ4MOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24340&json=true","fetch_graph":"https://pith.science/api/pith-number/BZWQ4MOSUYWHG2RCJCC3Z5YDBH/graph.json","fetch_events":"https://pith.science/api/pith-number/BZWQ4MOSUYWHG2RCJCC3Z5YDBH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZWQ4MOSUYWHG2RCJCC3Z5YDBH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZWQ4MOSUYWHG2RCJCC3Z5YDBH/action/storage_attestation","attest_author":"https://pith.science/pith/BZWQ4MOSUYWHG2RCJCC3Z5YDBH/action/author_attestation","sign_citation":"https://pith.science/pith/BZWQ4MOSUYWHG2RCJCC3Z5YDBH/action/citation_signature","submit_replication":"https://pith.science/pith/BZWQ4MOSUYWHG2RCJCC3Z5YDBH/action/replication_record"}},"created_at":"2026-05-26T01:03:00.759441+00:00","updated_at":"2026-05-26T01:03:00.759441+00:00"}