{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CU2S3HGUR2UNEW7YXLKH4VFJ5C","short_pith_number":"pith:CU2S3HGU","schema_version":"1.0","canonical_sha256":"15352d9cd48ea8d25bf8bad47e54a9e88688c3bb5097dcafe0e60faa45c3e195","source":{"kind":"arxiv","id":"2607.08406","version":1},"attestation_state":"computed","paper":{"title":"Beyond Backpropagation: Monte Carlo Method Can Train Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hong Zhao","submitted_at":"2026-07-09T12:31:04Z","abstract_excerpt":"Backpropagation (BP) dominates deep learning training, but its reliance on gradients brings inherent troubles -- vanishing and exploding gradients. The pursuit of gradient-free methods has long been a goal in the field of artificial intelligence. This paper shows that indeed the simplest Monte Carlo algorithm implemented on a single GPU -- randomly mutate a parameter, keep it if the loss decreases, otherwise retry -- can practically train deep networks. This gradient-free method does not even need common techniques such as batch normalization or residual connections to directly train sufficien"},"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":"2607.08406","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T12:31:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9a086eb89c062bde6f0bfb34fae69b694778ae554b09d277cd1a9e9e93e6c12e","abstract_canon_sha256":"3a4a8490459ac0369da2728c4c595f4bd34838fec1cd1bfe772437c1e10a03d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:49.564696Z","signature_b64":"oWdPgL2ezuoaCes6xDObzG3o+fFoEVg4AUortQKLaMVmelLJW5nXkmtgk52p9nOYk181VPyA7tw1lKmFPW0yCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15352d9cd48ea8d25bf8bad47e54a9e88688c3bb5097dcafe0e60faa45c3e195","last_reissued_at":"2026-07-10T01:19:49.564273Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:49.564273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Backpropagation: Monte Carlo Method Can Train Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hong Zhao","submitted_at":"2026-07-09T12:31:04Z","abstract_excerpt":"Backpropagation (BP) dominates deep learning training, but its reliance on gradients brings inherent troubles -- vanishing and exploding gradients. The pursuit of gradient-free methods has long been a goal in the field of artificial intelligence. This paper shows that indeed the simplest Monte Carlo algorithm implemented on a single GPU -- randomly mutate a parameter, keep it if the loss decreases, otherwise retry -- can practically train deep networks. This gradient-free method does not even need common techniques such as batch normalization or residual connections to directly train sufficien"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08406","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/2607.08406/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":"2607.08406","created_at":"2026-07-10T01:19:49.564350+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08406v1","created_at":"2026-07-10T01:19:49.564350+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08406","created_at":"2026-07-10T01:19:49.564350+00:00"},{"alias_kind":"pith_short_12","alias_value":"CU2S3HGUR2UN","created_at":"2026-07-10T01:19:49.564350+00:00"},{"alias_kind":"pith_short_16","alias_value":"CU2S3HGUR2UNEW7Y","created_at":"2026-07-10T01:19:49.564350+00:00"},{"alias_kind":"pith_short_8","alias_value":"CU2S3HGU","created_at":"2026-07-10T01:19:49.564350+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/CU2S3HGUR2UNEW7YXLKH4VFJ5C","json":"https://pith.science/pith/CU2S3HGUR2UNEW7YXLKH4VFJ5C.json","graph_json":"https://pith.science/api/pith-number/CU2S3HGUR2UNEW7YXLKH4VFJ5C/graph.json","events_json":"https://pith.science/api/pith-number/CU2S3HGUR2UNEW7YXLKH4VFJ5C/events.json","paper":"https://pith.science/paper/CU2S3HGU"},"agent_actions":{"view_html":"https://pith.science/pith/CU2S3HGUR2UNEW7YXLKH4VFJ5C","download_json":"https://pith.science/pith/CU2S3HGUR2UNEW7YXLKH4VFJ5C.json","view_paper":"https://pith.science/paper/CU2S3HGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08406&json=true","fetch_graph":"https://pith.science/api/pith-number/CU2S3HGUR2UNEW7YXLKH4VFJ5C/graph.json","fetch_events":"https://pith.science/api/pith-number/CU2S3HGUR2UNEW7YXLKH4VFJ5C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CU2S3HGUR2UNEW7YXLKH4VFJ5C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CU2S3HGUR2UNEW7YXLKH4VFJ5C/action/storage_attestation","attest_author":"https://pith.science/pith/CU2S3HGUR2UNEW7YXLKH4VFJ5C/action/author_attestation","sign_citation":"https://pith.science/pith/CU2S3HGUR2UNEW7YXLKH4VFJ5C/action/citation_signature","submit_replication":"https://pith.science/pith/CU2S3HGUR2UNEW7YXLKH4VFJ5C/action/replication_record"}},"created_at":"2026-07-10T01:19:49.564350+00:00","updated_at":"2026-07-10T01:19:49.564350+00:00"}