{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OKL4XS4HVU3VXGMFFHATIZ3IOP","short_pith_number":"pith:OKL4XS4H","schema_version":"1.0","canonical_sha256":"7297cbcb87ad375b998529c134676873cd8944e63c552c926b8746e5281e493f","source":{"kind":"arxiv","id":"2505.23369","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Spectral Backpropagation for Efficient Neural Network Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mannmohan Muthuraman","submitted_at":"2025-05-29T11:47:50Z","abstract_excerpt":"Dynamic Spectral Backpropagation (DSBP) enhances neural network training under resource constraints by projecting gradients onto principal eigenvectors, reducing complexity and promoting flat minima. Five extensions are proposed, dynamic spectral inference, spectral architecture optimization, spectral meta learning, spectral transfer regularization, and Lie algebra inspired dynamics, to address challenges in robustness, fewshot learning, and hardware efficiency. Supported by a third order stochastic differential equation (SDE) and a PAC Bayes limit, DSBP outperforms Sharpness Aware Minimizatio"},"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":"2505.23369","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T11:47:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a1dc2f85d81ce43e2d5f54373ff93df9c5a66628ad9284dc6b87a3d5aa09d57","abstract_canon_sha256":"2379d53eb8f517f5d9a8ee115fab06ca308e5648f9c256b33dcd3aca14ccaa38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:00.423792Z","signature_b64":"JAYucyElA7nbLdV6ReBanpUmltfyGuDRNuyEKEU/p6wCaQT0TFNghedp8GY+RKbH/dP51MXAjW+h826uaFYCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7297cbcb87ad375b998529c134676873cd8944e63c552c926b8746e5281e493f","last_reissued_at":"2026-07-05T11:12:00.423259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:00.423259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Spectral Backpropagation for Efficient Neural Network Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mannmohan Muthuraman","submitted_at":"2025-05-29T11:47:50Z","abstract_excerpt":"Dynamic Spectral Backpropagation (DSBP) enhances neural network training under resource constraints by projecting gradients onto principal eigenvectors, reducing complexity and promoting flat minima. Five extensions are proposed, dynamic spectral inference, spectral architecture optimization, spectral meta learning, spectral transfer regularization, and Lie algebra inspired dynamics, to address challenges in robustness, fewshot learning, and hardware efficiency. Supported by a third order stochastic differential equation (SDE) and a PAC Bayes limit, DSBP outperforms Sharpness Aware Minimizatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23369","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/2505.23369/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":"2505.23369","created_at":"2026-07-05T11:12:00.423339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23369v1","created_at":"2026-07-05T11:12:00.423339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23369","created_at":"2026-07-05T11:12:00.423339+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKL4XS4HVU3V","created_at":"2026-07-05T11:12:00.423339+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKL4XS4HVU3VXGMF","created_at":"2026-07-05T11:12:00.423339+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKL4XS4H","created_at":"2026-07-05T11:12:00.423339+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/OKL4XS4HVU3VXGMFFHATIZ3IOP","json":"https://pith.science/pith/OKL4XS4HVU3VXGMFFHATIZ3IOP.json","graph_json":"https://pith.science/api/pith-number/OKL4XS4HVU3VXGMFFHATIZ3IOP/graph.json","events_json":"https://pith.science/api/pith-number/OKL4XS4HVU3VXGMFFHATIZ3IOP/events.json","paper":"https://pith.science/paper/OKL4XS4H"},"agent_actions":{"view_html":"https://pith.science/pith/OKL4XS4HVU3VXGMFFHATIZ3IOP","download_json":"https://pith.science/pith/OKL4XS4HVU3VXGMFFHATIZ3IOP.json","view_paper":"https://pith.science/paper/OKL4XS4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23369&json=true","fetch_graph":"https://pith.science/api/pith-number/OKL4XS4HVU3VXGMFFHATIZ3IOP/graph.json","fetch_events":"https://pith.science/api/pith-number/OKL4XS4HVU3VXGMFFHATIZ3IOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKL4XS4HVU3VXGMFFHATIZ3IOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKL4XS4HVU3VXGMFFHATIZ3IOP/action/storage_attestation","attest_author":"https://pith.science/pith/OKL4XS4HVU3VXGMFFHATIZ3IOP/action/author_attestation","sign_citation":"https://pith.science/pith/OKL4XS4HVU3VXGMFFHATIZ3IOP/action/citation_signature","submit_replication":"https://pith.science/pith/OKL4XS4HVU3VXGMFFHATIZ3IOP/action/replication_record"}},"created_at":"2026-07-05T11:12:00.423339+00:00","updated_at":"2026-07-05T11:12:00.423339+00:00"}