{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PBKZCNZ4SYHOHCM56LKBYH67TV","short_pith_number":"pith:PBKZCNZ4","schema_version":"1.0","canonical_sha256":"785591373c960ee3899df2d41c1fdf9d7adb2f372e3cfe190b03139885cc74ad","source":{"kind":"arxiv","id":"2412.05667","version":3},"attestation_state":"computed","paper":{"title":"Training neural networks without backpropagation using particles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Deepak Kumar","submitted_at":"2024-12-07T14:30:48Z","abstract_excerpt":"Neural networks are a group of neurons stacked together in multiple layers to mimic the biological neurons in a human brain. Neural networks have been trained using the backpropagation algorithm based on gradient descent strategy for several decades. Several variants have been developed to improve the backpropagation algorithm. The loss function for the neural network is optimized through backpropagation, but several local minima exist in the manifold of the constructed neural network. We obtain several solutions matching the minima. The gradient descent strategy cannot avoid the problem of lo"},"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":"2412.05667","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2024-12-07T14:30:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6ba7dcf4eab5d762e8720ce0141486fac0b9a324787f2f584975149faa4d49b7","abstract_canon_sha256":"d59ee42a167c83c24a579d357debd0010c6183aa891a18ecc6ff95a045e9f048"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:29.560900Z","signature_b64":"lWZrZoNKnens3TgHmrtoX4HeKXoBZzQZOZJGzJoHzcRIbBJgDxcT5X6Xda00/g+QFTF2WCAWIY7cnpzv+BWSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"785591373c960ee3899df2d41c1fdf9d7adb2f372e3cfe190b03139885cc74ad","last_reissued_at":"2026-07-05T10:51:29.560426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:29.560426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training neural networks without backpropagation using particles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Deepak Kumar","submitted_at":"2024-12-07T14:30:48Z","abstract_excerpt":"Neural networks are a group of neurons stacked together in multiple layers to mimic the biological neurons in a human brain. Neural networks have been trained using the backpropagation algorithm based on gradient descent strategy for several decades. Several variants have been developed to improve the backpropagation algorithm. The loss function for the neural network is optimized through backpropagation, but several local minima exist in the manifold of the constructed neural network. We obtain several solutions matching the minima. The gradient descent strategy cannot avoid the problem of lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05667","kind":"arxiv","version":3},"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/2412.05667/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":"2412.05667","created_at":"2026-07-05T10:51:29.560481+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05667v3","created_at":"2026-07-05T10:51:29.560481+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05667","created_at":"2026-07-05T10:51:29.560481+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBKZCNZ4SYHO","created_at":"2026-07-05T10:51:29.560481+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBKZCNZ4SYHOHCM5","created_at":"2026-07-05T10:51:29.560481+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBKZCNZ4","created_at":"2026-07-05T10:51:29.560481+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/PBKZCNZ4SYHOHCM56LKBYH67TV","json":"https://pith.science/pith/PBKZCNZ4SYHOHCM56LKBYH67TV.json","graph_json":"https://pith.science/api/pith-number/PBKZCNZ4SYHOHCM56LKBYH67TV/graph.json","events_json":"https://pith.science/api/pith-number/PBKZCNZ4SYHOHCM56LKBYH67TV/events.json","paper":"https://pith.science/paper/PBKZCNZ4"},"agent_actions":{"view_html":"https://pith.science/pith/PBKZCNZ4SYHOHCM56LKBYH67TV","download_json":"https://pith.science/pith/PBKZCNZ4SYHOHCM56LKBYH67TV.json","view_paper":"https://pith.science/paper/PBKZCNZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05667&json=true","fetch_graph":"https://pith.science/api/pith-number/PBKZCNZ4SYHOHCM56LKBYH67TV/graph.json","fetch_events":"https://pith.science/api/pith-number/PBKZCNZ4SYHOHCM56LKBYH67TV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBKZCNZ4SYHOHCM56LKBYH67TV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBKZCNZ4SYHOHCM56LKBYH67TV/action/storage_attestation","attest_author":"https://pith.science/pith/PBKZCNZ4SYHOHCM56LKBYH67TV/action/author_attestation","sign_citation":"https://pith.science/pith/PBKZCNZ4SYHOHCM56LKBYH67TV/action/citation_signature","submit_replication":"https://pith.science/pith/PBKZCNZ4SYHOHCM56LKBYH67TV/action/replication_record"}},"created_at":"2026-07-05T10:51:29.560481+00:00","updated_at":"2026-07-05T10:51:29.560481+00:00"}