{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6M5JYGMHE6QY4AVQVT7TL2OX7Z","short_pith_number":"pith:6M5JYGMH","canonical_record":{"source":{"id":"2605.15463","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T22:57:51Z","cross_cats_sorted":[],"title_canon_sha256":"5b0ccb7fbf378ee7a75551319777d324302f0b7bc8417586774696849b46b0de","abstract_canon_sha256":"491b5f697383889b86ecee0b1434b3a25afae001d0cc677f359033aacfadee16"},"schema_version":"1.0"},"canonical_sha256":"f33a9c198727a18e02b0acff35e9d7fe4dc3a3dd8501d8b2841897df6daa264a","source":{"kind":"arxiv","id":"2605.15463","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15463","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15463v1","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15463","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"pith_short_12","alias_value":"6M5JYGMHE6QY","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"pith_short_16","alias_value":"6M5JYGMHE6QY4AVQ","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"pith_short_8","alias_value":"6M5JYGMH","created_at":"2026-05-20T00:00:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6M5JYGMHE6QY4AVQVT7TL2OX7Z","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15463","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T22:57:51Z","cross_cats_sorted":[],"title_canon_sha256":"5b0ccb7fbf378ee7a75551319777d324302f0b7bc8417586774696849b46b0de","abstract_canon_sha256":"491b5f697383889b86ecee0b1434b3a25afae001d0cc677f359033aacfadee16"},"schema_version":"1.0"},"canonical_sha256":"f33a9c198727a18e02b0acff35e9d7fe4dc3a3dd8501d8b2841897df6daa264a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:59.853418Z","signature_b64":"exxdfX0TTnHIaL2PaLBRBBYdxHK7z0lmi3x6sRgPICz68hZu3E75YDON+ku5VvypqyD1XxrM/mWkbdigrcCyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f33a9c198727a18e02b0acff35e9d7fe4dc3a3dd8501d8b2841897df6daa264a","last_reissued_at":"2026-05-20T00:00:59.852548Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:59.852548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15463","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YCY7brL6HGbne/gAyex9dosqQzTbqvRddQXgs956C/ljMkmiUMWrugv4Eg6rAOiChZ+rWeqkfXV/jAR3Az+TBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T12:29:45.324341Z"},"content_sha256":"439d021a9401a6692d143828463d5c3fca18fad814c7bc41555735ff848bb8b9","schema_version":"1.0","event_id":"sha256:439d021a9401a6692d143828463d5c3fca18fad814c7bc41555735ff848bb8b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6M5JYGMHE6QY4AVQVT7TL2OX7Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Layer-wise Derivative Controlled Networks","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"ChainzRule replaces standard activations with a Polynomial Engine under layer-wise Differential Regularization to cut parameters while lowering gradient volatility.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rowan Martnishn, Sean Anderson","submitted_at":"2026-05-14T22:57:51Z","abstract_excerpt":"As machine learning models grow in complexity, they increasingly struggle with three conflicting demands: the need for high accuracy, the requirement for hardware efficiency, and the necessity of functional stability. Traditional architectures often achieve performance at the expense of spiky or unpredictable behavior, where small changes in input lead to massive swings in output -- a critical flaw for real-world deployment in sensitive environments. This paper introduces ChainzRule (CR), a novel neural architecture designed to harmonize these competing goals. ChainzRule replaces standard piec"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"ChainzRule outperformed standard models while using 15.5x fewer parameters; on MNIST it reduced peak gradient volatility by 23.1% and on Yelp Full it reached 70.17% accuracy under explicit DREG regularization.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the 'Fair Fight' benchmarks use identical training protocols, data splits, and hyperparameter tuning for baselines and that DREG preserves full representational capacity of the Polynomial Engine without post-hoc adjustments that favor the proposed model.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ChainzRule with DREG regularization claims 15.5x fewer parameters than standard models, 23.1% lower peak gradient volatility on MNIST, and 70.17% accuracy on Yelp Full ordinal regression.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ChainzRule replaces standard activations with a Polynomial Engine under layer-wise Differential Regularization to cut parameters while lowering gradient volatility.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"92c40e9e0ca01b61a125b47e2d70eddbbcc90a19008de0d8719b00df64acd19c"},"source":{"id":"2605.15463","kind":"arxiv","version":1},"verdict":{"id":"9ddd24e0-118d-4901-bf6a-16f0671bcc6d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T15:15:55.955446Z","strongest_claim":"ChainzRule outperformed standard models while using 15.5x fewer parameters; on MNIST it reduced peak gradient volatility by 23.1% and on Yelp Full it reached 70.17% accuracy under explicit DREG regularization.","one_line_summary":"ChainzRule with DREG regularization claims 15.5x fewer parameters than standard models, 23.1% lower peak gradient volatility on MNIST, and 70.17% accuracy on Yelp Full ordinal regression.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the 'Fair Fight' benchmarks use identical training protocols, data splits, and hyperparameter tuning for baselines and that DREG preserves full representational capacity of the Polynomial Engine without post-hoc adjustments that favor the proposed model.","pith_extraction_headline":"ChainzRule replaces standard activations with a Polynomial Engine under layer-wise Differential Regularization to cut parameters while lowering gradient volatility."},"integrity":{"clean":false,"summary":{"advisory":2,"critical":1,"by_detector":{"doi_compliance":{"total":3,"advisory":2,"critical":1,"informational":0}},"informational":0},"endpoint":"/pith/2605.15463/integrity.json","findings":[{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2404.19756.URLhttps://arxiv.org/abs/2404.19756.Ilya) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detector":"doi_compliance","severity":"advisory","ref_index":12,"audited_at":"2026-05-19T15:20:52.070923Z","detected_doi":"10.48550/arXiv.2404.19756.URLhttps://arxiv.org/abs/2404.19756.Ilya","finding_type":"recoverable_identifier","verdict_class":"incontrovertible","detected_arxiv_id":null},{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.3389/fdata.2024.12705377.URLhttps://pmc.ncbi.nlm.nih.gov/articles/PMC12705377/.Christopher) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detector":"doi_compliance","severity":"advisory","ref_index":1,"audited_at":"2026-05-19T15:20:52.070923Z","detected_doi":"10.3389/fdata.2024.12705377.URLhttps://pmc.ncbi.nlm.nih.gov/articles/PMC12705377/.Christopher","finding_type":"recoverable_identifier","verdict_class":"incontrovertible","detected_arxiv_id":null},{"note":"Identifier '10.1016/j.jcp.2018.10' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","detector":"doi_compliance","severity":"critical","ref_index":15,"audited_at":"2026-05-19T15:20:52.070923Z","detected_doi":"10.1016/j.jcp.2018.10","finding_type":"unresolvable_identifier","verdict_class":"cross_source","detected_arxiv_id":null}],"available":true,"detectors_run":[{"name":"citation_quote_validity","ran_at":"2026-05-19T15:49:42.263010Z","status":"completed","version":"0.1.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T15:31:17.727408Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T15:22:45.563444Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:20:52.070923Z","status":"completed","version":"1.0.0","findings_count":3},{"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.095818Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.668972Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"985e09bec2773137751f8b4cdd398e596ef75e610e691afcaa7979dcf21584bd"},"references":{"count":19,"sample":[{"doi":"10.3389/fdata.2024.12705377","year":2024,"title":"URLhttps://pmc.ncbi","work_id":"f73322c6-3a37-40bb-b630-b3dcdc9b3714","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Neural Ordinary Differential Equations","work_id":"d9298290-3e2a-4cb1-b26b-f4c4fcb3e744","ref_index":2,"cited_arxiv_id":"1806.07366","is_internal_anchor":true},{"doi":"10.48550/arxiv.1806.07366","year":null,"title":"Neural Ordinary Differential Equations","work_id":"d9298290-3e2a-4cb1-b26b-f4c4fcb3e744","ref_index":3,"cited_arxiv_id":"1806.07366","is_internal_anchor":true},{"doi":"10.48550/arxiv.1704.08847","year":null,"title":"Parseval Networks: Improving Robustness to Adversarial Examples","work_id":"08cc951c-cdf6-450a-b4bf-8ff4d8eb30a7","ref_index":4,"cited_arxiv_id":"1704.08847","is_internal_anchor":true},{"doi":"","year":null,"title":"Sobolev training for neural networks","work_id":"06c95db5-4bad-4bd2-8e48-fa4bb81e9d78","ref_index":5,"cited_arxiv_id":"1706.04859","is_internal_anchor":true}],"resolved_work":19,"snapshot_sha256":"4e1c658108e5fc989835f9cb8f2c52981a7547af80bd375e37866b80770e1c83","internal_anchors":14},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f4beaf4a9ee756c5736ce9653a725b765873a57fc0acfbc1ac95c18a25845cc4"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"9ddd24e0-118d-4901-bf6a-16f0671bcc6d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uDBo4IxO1R/6Gcn7MEfjioI9NbFlZh7hEMeXcCXpJk1+yNGux/rfCAHoLhlBkWraVuJZhtXQezNOLbbtkOH2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T12:29:45.325051Z"},"content_sha256":"35fc85589571d4bedec44e46bb5d70ee047acc6e5337bbdce71d0d8bb63eb940","schema_version":"1.0","event_id":"sha256:35fc85589571d4bedec44e46bb5d70ee047acc6e5337bbdce71d0d8bb63eb940"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:6M5JYGMHE6QY4AVQVT7TL2OX7Z","target":"integrity","payload":{"note":"Identifier '10.1016/j.jcp.2018.10' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"doi: 10.1016/j.jcp.2018.10","arxiv_id":"2605.15463","detector":"doi_compliance","evidence":{"doi":"10.1016/j.jcp.2018.10","arxiv_id":null,"ref_index":15,"raw_excerpt":"doi: 10.1016/j.jcp.2018.10","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"]},"severity":"critical","ref_index":15,"audited_at":"2026-05-19T15:20:52.070923Z","event_type":"pith.integrity.v1","detected_doi":"10.1016/j.jcp.2018.10","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"cb10bb6b37c08f64d7d433a1503b85d8e80bf7e06f2de3853579e589d21b0c44","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":1833,"payload_sha256":"0d09eec6de26b86174118162a5b2c62dc3ca852100635c7b078a8a3d45f035c0","signature_b64":"Az0W4jOCkxy4NBYpd2ZBMWCYAi8/rlgnIprug0a9eE4JesoJkUeWEH2xs31DWWaHR6mq73FyJtthn5lJm3ePCQ==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T15:22:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mzHvB+erQutQB/xINWE+h70dcfNaGakdDlED4vqNKyK8DKpaxtzH2dZoKFFgybs6jBe23TbEjlb/zFAsq+EnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T12:29:45.325998Z"},"content_sha256":"d57a79400f3e0faff4009eb64d1a57a0a040fdd4da07ebece9dc0651315bbfad","schema_version":"1.0","event_id":"sha256:d57a79400f3e0faff4009eb64d1a57a0a040fdd4da07ebece9dc0651315bbfad"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:6M5JYGMHE6QY4AVQVT7TL2OX7Z","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2404.19756.URLhttps://arxiv.org/abs/2404.19756.Ilya) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"doi: 10.48550/arXiv. 2404.19756. URLhttps://arxiv.org/abs/2404.19756. Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization.ICLR,","arxiv_id":"2605.15463","detector":"doi_compliance","evidence":{"ref_index":12,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"doi: 10.48550/arXiv. 2404.19756. URLhttps://arxiv.org/abs/2404.19756. Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization.ICLR,","reconstructed_doi":"10.48550/arXiv.2404.19756.URLhttps://arxiv.org/abs/2404.19756.Ilya"},"severity":"advisory","ref_index":12,"audited_at":"2026-05-19T15:20:52.070923Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/arXiv.2404.19756.URLhttps://arxiv.org/abs/2404.19756.Ilya","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"52a2fbb76553cf5c3dda3871633ce503cac0cf94a088994100d51b645c499281","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":1832,"payload_sha256":"463138f923c6dedbb49dab61614ba38dd6fb7991bac2c473c7e26707cb7a5ec6","signature_b64":"vEINx6+KwhVcVLiXO5y3lRItwWnq4mCy7ehiEVaHHcYfCSbW7KaE4iVGfYftcldC0/+6aI4qL7ZcU78krmUYCg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T15:22:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1qRStbdKba0w5e5D9FxY14CCdZQCj0l9LENT8iOxN03A/ahQRg8IyybCc8AXlBcwsrxP+uasARah0Tvh2TZeCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T12:29:45.326288Z"},"content_sha256":"2c289dd7b3308ca434bc0d1ae8f1335da666a3bddef6c5f3d516ba8a69e2f1fd","schema_version":"1.0","event_id":"sha256:2c289dd7b3308ca434bc0d1ae8f1335da666a3bddef6c5f3d516ba8a69e2f1fd"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:6M5JYGMHE6QY4AVQVT7TL2OX7Z","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.3389/fdata.2024.12705377.URLhttps://pmc.ncbi.nlm.nih.gov/articles/PMC12705377/.Christopher) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"doi: 10.3389/fdata.2024.12705377. URLhttps://pmc.ncbi. nlm.nih.gov/articles/PMC12705377/. Christopher M. Bishop.Pattern Recognition and Machine Learning. Springer,","arxiv_id":"2605.15463","detector":"doi_compliance","evidence":{"ref_index":1,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"doi: 10.3389/fdata.2024.12705377. URLhttps://pmc.ncbi. nlm.nih.gov/articles/PMC12705377/. Christopher M. Bishop.Pattern Recognition and Machine Learning. Springer,","reconstructed_doi":"10.3389/fdata.2024.12705377.URLhttps://pmc.ncbi.nlm.nih.gov/articles/PMC12705377/.Christopher"},"severity":"advisory","ref_index":1,"audited_at":"2026-05-19T15:20:52.070923Z","event_type":"pith.integrity.v1","detected_doi":"10.3389/fdata.2024.12705377.URLhttps://pmc.ncbi.nlm.nih.gov/articles/PMC12705377/.Christopher","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"629329ea564cd0f0459072e970fa3e94d5c847e12933f7ac6d81b58ff79c4378","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":1831,"payload_sha256":"712a7a41c51c0ff9126aeb5ece0c6cfcaa811b73908c3af9b79523b055292d54","signature_b64":"Z5cm77TekMj3uzEOWaEhYUQ3vArOB8htvxgmQJivwv0YiMVY+CmRyBGO3PJihERewR9SOWXJiMSclIlVdkeHAg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T15:22:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oU7egX7D8YdtD/7y3Oz25oNJ4UyB4KyNLPZwPYuheMp376Ltj8PGxu/WPJSKeH2SdMhMUmxncl8cXnnWPJS3Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T12:29:45.326576Z"},"content_sha256":"9eb732931c3d65b5ae5e35724008abab501d0802f94387f3324f12955125b1ae","schema_version":"1.0","event_id":"sha256:9eb732931c3d65b5ae5e35724008abab501d0802f94387f3324f12955125b1ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6M5JYGMHE6QY4AVQVT7TL2OX7Z/bundle.json","state_url":"https://pith.science/pith/6M5JYGMHE6QY4AVQVT7TL2OX7Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6M5JYGMHE6QY4AVQVT7TL2OX7Z/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-21T12:29:45Z","links":{"resolver":"https://pith.science/pith/6M5JYGMHE6QY4AVQVT7TL2OX7Z","bundle":"https://pith.science/pith/6M5JYGMHE6QY4AVQVT7TL2OX7Z/bundle.json","state":"https://pith.science/pith/6M5JYGMHE6QY4AVQVT7TL2OX7Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6M5JYGMHE6QY4AVQVT7TL2OX7Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6M5JYGMHE6QY4AVQVT7TL2OX7Z","merge_version":"pith-open-graph-merge-v1","event_count":5,"valid_event_count":5,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"491b5f697383889b86ecee0b1434b3a25afae001d0cc677f359033aacfadee16","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T22:57:51Z","title_canon_sha256":"5b0ccb7fbf378ee7a75551319777d324302f0b7bc8417586774696849b46b0de"},"schema_version":"1.0","source":{"id":"2605.15463","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15463","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15463v1","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15463","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"pith_short_12","alias_value":"6M5JYGMHE6QY","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"pith_short_16","alias_value":"6M5JYGMHE6QY4AVQ","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"pith_short_8","alias_value":"6M5JYGMH","created_at":"2026-05-20T00:00:59Z"}],"graph_snapshots":[{"event_id":"sha256:35fc85589571d4bedec44e46bb5d70ee047acc6e5337bbdce71d0d8bb63eb940","target":"graph","created_at":"2026-05-20T00:00:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"ChainzRule outperformed standard models while using 15.5x fewer parameters; on MNIST it reduced peak gradient volatility by 23.1% and on Yelp Full it reached 70.17% accuracy under explicit DREG regularization."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the 'Fair Fight' benchmarks use identical training protocols, data splits, and hyperparameter tuning for baselines and that DREG preserves full representational capacity of the Polynomial Engine without post-hoc adjustments that favor the proposed model."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ChainzRule with DREG regularization claims 15.5x fewer parameters than standard models, 23.1% lower peak gradient volatility on MNIST, and 70.17% accuracy on Yelp Full ordinal regression."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"ChainzRule replaces standard activations with a Polynomial Engine under layer-wise Differential Regularization to cut parameters while lowering gradient volatility."}],"snapshot_sha256":"92c40e9e0ca01b61a125b47e2d70eddbbcc90a19008de0d8719b00df64acd19c"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f4beaf4a9ee756c5736ce9653a725b765873a57fc0acfbc1ac95c18a25845cc4"},"integrity":{"available":true,"clean":false,"detectors_run":[{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T15:49:42.263010Z","status":"completed","version":"0.1.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T15:31:17.727408Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T15:22:45.563444Z","status":"completed","version":"1.0.0"},{"findings_count":3,"name":"doi_compliance","ran_at":"2026-05-19T15:20:52.070923Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.095818Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.668972Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15463/integrity.json","findings":[{"audited_at":"2026-05-19T15:20:52.070923Z","detected_arxiv_id":null,"detected_doi":"10.48550/arXiv.2404.19756.URLhttps://arxiv.org/abs/2404.19756.Ilya","detector":"doi_compliance","finding_type":"recoverable_identifier","note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2404.19756.URLhttps://arxiv.org/abs/2404.19756.Ilya) was visible in the surrounding text but could not be confirmed against doi.org as printed.","ref_index":12,"severity":"advisory","verdict_class":"incontrovertible"},{"audited_at":"2026-05-19T15:20:52.070923Z","detected_arxiv_id":null,"detected_doi":"10.3389/fdata.2024.12705377.URLhttps://pmc.ncbi.nlm.nih.gov/articles/PMC12705377/.Christopher","detector":"doi_compliance","finding_type":"recoverable_identifier","note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.3389/fdata.2024.12705377.URLhttps://pmc.ncbi.nlm.nih.gov/articles/PMC12705377/.Christopher) was visible in the surrounding text but could not be confirmed against doi.org as printed.","ref_index":1,"severity":"advisory","verdict_class":"incontrovertible"},{"audited_at":"2026-05-19T15:20:52.070923Z","detected_arxiv_id":null,"detected_doi":"10.1016/j.jcp.2018.10","detector":"doi_compliance","finding_type":"unresolvable_identifier","note":"Identifier '10.1016/j.jcp.2018.10' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","ref_index":15,"severity":"critical","verdict_class":"cross_source"}],"snapshot_sha256":"985e09bec2773137751f8b4cdd398e596ef75e610e691afcaa7979dcf21584bd","summary":{"advisory":2,"by_detector":{"doi_compliance":{"advisory":2,"critical":1,"informational":0,"total":3}},"critical":1,"informational":0}},"paper":{"abstract_excerpt":"As machine learning models grow in complexity, they increasingly struggle with three conflicting demands: the need for high accuracy, the requirement for hardware efficiency, and the necessity of functional stability. Traditional architectures often achieve performance at the expense of spiky or unpredictable behavior, where small changes in input lead to massive swings in output -- a critical flaw for real-world deployment in sensitive environments. This paper introduces ChainzRule (CR), a novel neural architecture designed to harmonize these competing goals. ChainzRule replaces standard piec","authors_text":"Rowan Martnishn, Sean Anderson","cross_cats":[],"headline":"ChainzRule replaces standard activations with a Polynomial Engine under layer-wise Differential Regularization to cut parameters while lowering gradient volatility.","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T22:57:51Z","title":"Layer-wise Derivative Controlled Networks"},"references":{"count":19,"internal_anchors":14,"resolved_work":19,"sample":[{"cited_arxiv_id":"","doi":"10.3389/fdata.2024.12705377","is_internal_anchor":false,"ref_index":1,"title":"URLhttps://pmc.ncbi","work_id":"f73322c6-3a37-40bb-b630-b3dcdc9b3714","year":2024},{"cited_arxiv_id":"1806.07366","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Neural Ordinary Differential Equations","work_id":"d9298290-3e2a-4cb1-b26b-f4c4fcb3e744","year":null},{"cited_arxiv_id":"1806.07366","doi":"10.48550/arxiv.1806.07366","is_internal_anchor":true,"ref_index":3,"title":"Neural Ordinary Differential Equations","work_id":"d9298290-3e2a-4cb1-b26b-f4c4fcb3e744","year":null},{"cited_arxiv_id":"1704.08847","doi":"10.48550/arxiv.1704.08847","is_internal_anchor":true,"ref_index":4,"title":"Parseval Networks: Improving Robustness to Adversarial Examples","work_id":"08cc951c-cdf6-450a-b4bf-8ff4d8eb30a7","year":null},{"cited_arxiv_id":"1706.04859","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Sobolev training for neural networks","work_id":"06c95db5-4bad-4bd2-8e48-fa4bb81e9d78","year":null}],"snapshot_sha256":"4e1c658108e5fc989835f9cb8f2c52981a7547af80bd375e37866b80770e1c83"},"source":{"id":"2605.15463","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T15:15:55.955446Z","id":"9ddd24e0-118d-4901-bf6a-16f0671bcc6d","model_set":{"reader":"grok-4.3"},"one_line_summary":"ChainzRule with DREG regularization claims 15.5x fewer parameters than standard models, 23.1% lower peak gradient volatility on MNIST, and 70.17% accuracy on Yelp Full ordinal regression.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"ChainzRule replaces standard activations with a Polynomial Engine under layer-wise Differential Regularization to cut parameters while lowering gradient volatility.","strongest_claim":"ChainzRule outperformed standard models while using 15.5x fewer parameters; on MNIST it reduced peak gradient volatility by 23.1% and on Yelp Full it reached 70.17% accuracy under explicit DREG regularization.","weakest_assumption":"That the 'Fair Fight' benchmarks use identical training protocols, data splits, and hyperparameter tuning for baselines and that DREG preserves full representational capacity of the Polynomial Engine without post-hoc adjustments that favor the proposed model."}},"verdict_id":"9ddd24e0-118d-4901-bf6a-16f0671bcc6d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:439d021a9401a6692d143828463d5c3fca18fad814c7bc41555735ff848bb8b9","target":"record","created_at":"2026-05-20T00:00:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"491b5f697383889b86ecee0b1434b3a25afae001d0cc677f359033aacfadee16","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T22:57:51Z","title_canon_sha256":"5b0ccb7fbf378ee7a75551319777d324302f0b7bc8417586774696849b46b0de"},"schema_version":"1.0","source":{"id":"2605.15463","kind":"arxiv","version":1}},"canonical_sha256":"f33a9c198727a18e02b0acff35e9d7fe4dc3a3dd8501d8b2841897df6daa264a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f33a9c198727a18e02b0acff35e9d7fe4dc3a3dd8501d8b2841897df6daa264a","first_computed_at":"2026-05-20T00:00:59.852548Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:59.852548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"exxdfX0TTnHIaL2PaLBRBBYdxHK7z0lmi3x6sRgPICz68hZu3E75YDON+ku5VvypqyD1XxrM/mWkbdigrcCyDw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:59.853418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15463","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:2c289dd7b3308ca434bc0d1ae8f1335da666a3bddef6c5f3d516ba8a69e2f1fd","sha256:9eb732931c3d65b5ae5e35724008abab501d0802f94387f3324f12955125b1ae","sha256:d57a79400f3e0faff4009eb64d1a57a0a040fdd4da07ebece9dc0651315bbfad"]}],"invalid_events":[],"applied_event_ids":["sha256:439d021a9401a6692d143828463d5c3fca18fad814c7bc41555735ff848bb8b9","sha256:35fc85589571d4bedec44e46bb5d70ee047acc6e5337bbdce71d0d8bb63eb940"],"state_sha256":"373ff25aa2c79252ef3834f32c78630be82e01b808dcd4856db369feaa61784e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oe7JSI366gRTzuRcOnR7QHnsZa+UGTqz5pwEnzlBTt4KknfAgVh1BOhadQRMJ6TOkTE3fmp3/5udTBD7w0mMCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T12:29:45.329890Z","bundle_sha256":"c754c306dfed64ce93727c8aed75f55c4939e6ae13ea9f891bd3e26cbb352242"}}