{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2006:UZR6VDT5YGEIAC42NZP2DONDTZ","short_pith_number":"pith:UZR6VDT5","canonical_record":{"source":{"id":"physics/0607046","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"physics.bio-ph","submitted_at":"2006-07-06T04:16:57Z","cross_cats_sorted":["physics.comp-ph"],"title_canon_sha256":"ba88f393a4abe6359da9776ce2f7af20efd6e432dce8908483363d513b3f9fd9","abstract_canon_sha256":"d3c6871301788d2610d767df903569d95f949541f92806848ad17ec074bc36b2"},"schema_version":"1.0"},"canonical_sha256":"a663ea8e7dc188800b9a6e5fa1b9a39e69bf3438eb75b84c02d4088f8e4eff2c","source":{"kind":"arxiv","id":"physics/0607046","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"physics/0607046","created_at":"2026-07-04T14:56:11Z"},{"alias_kind":"arxiv_version","alias_value":"physics/0607046v1","created_at":"2026-07-04T14:56:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.physics/0607046","created_at":"2026-07-04T14:56:11Z"},{"alias_kind":"pith_short_12","alias_value":"UZR6VDT5YGEI","created_at":"2026-07-04T14:56:11Z"},{"alias_kind":"pith_short_16","alias_value":"UZR6VDT5YGEIAC42","created_at":"2026-07-04T14:56:11Z"},{"alias_kind":"pith_short_8","alias_value":"UZR6VDT5","created_at":"2026-07-04T14:56:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2006:UZR6VDT5YGEIAC42NZP2DONDTZ","target":"record","payload":{"canonical_record":{"source":{"id":"physics/0607046","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"physics.bio-ph","submitted_at":"2006-07-06T04:16:57Z","cross_cats_sorted":["physics.comp-ph"],"title_canon_sha256":"ba88f393a4abe6359da9776ce2f7af20efd6e432dce8908483363d513b3f9fd9","abstract_canon_sha256":"d3c6871301788d2610d767df903569d95f949541f92806848ad17ec074bc36b2"},"schema_version":"1.0"},"canonical_sha256":"a663ea8e7dc188800b9a6e5fa1b9a39e69bf3438eb75b84c02d4088f8e4eff2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T14:56:11.824546Z","signature_b64":"s5NfKAu84u80t4FvuWFfK1XsiL7Cvo0dsPeFbTqSJ1JzN6BCCtbQFLXytoSo1mJUsM2HulNYMVeOK1tDC9DUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a663ea8e7dc188800b9a6e5fa1b9a39e69bf3438eb75b84c02d4088f8e4eff2c","last_reissued_at":"2026-07-04T14:56:11.824134Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T14:56:11.824134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"physics/0607046","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":"2026-07-04T14:56:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IAqmBEci/FuPM2ofdfrmond2OgUL7xVRrTKkfyxlpl/aItEDCSFl1kla3usdXfMBpqr9nJ3/Xpv0Fvg/JNE3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T16:41:24.784115Z"},"content_sha256":"21f51f231083944ca8ec41345fa7287fad933e53e4ca242d6cd1de8a13246c01","schema_version":"1.0","event_id":"sha256:21f51f231083944ca8ec41345fa7287fad933e53e4ca242d6cd1de8a13246c01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2006:UZR6VDT5YGEIAC42NZP2DONDTZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Global Algorithm for Training Multilayer Neural Networks","license":"","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"physics.bio-ph","authors_text":"Hong Zhao, Tao Jin","submitted_at":"2006-07-06T04:16:57Z","abstract_excerpt":"We present a global algorithm for training multilayer neural networks in this Letter. The algorithm is focused on controlling the local fields of neurons induced by the input of samples by random adaptations of the synaptic weights. Unlike the backpropagation algorithm, the networks may have discrete-state weights, and may apply either differentiable or nondifferentiable neural transfer functions. A two-layer network is trained as an example to separate a linearly inseparable set of samples into two categories, and its powerful generalization capacity is emphasized. The extension to more gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"physics/0607046","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/physics/0607046/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T14:56:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ny3ajJy1MqDxpXDnO9w9qNhtlPz7q2jj/ESXy+uIlxRbvJHcLhj1eCd30Fj7zRjLaZbbOnazEgQUv8Z0owYsBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T16:41:24.784461Z"},"content_sha256":"41f7708f31424a2e7d40cb5c0b22641da4aab7db7a36fadbcb58fb1850d8eb09","schema_version":"1.0","event_id":"sha256:41f7708f31424a2e7d40cb5c0b22641da4aab7db7a36fadbcb58fb1850d8eb09"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UZR6VDT5YGEIAC42NZP2DONDTZ/bundle.json","state_url":"https://pith.science/pith/UZR6VDT5YGEIAC42NZP2DONDTZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UZR6VDT5YGEIAC42NZP2DONDTZ/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":"2026-07-31T16:41:24Z","links":{"resolver":"https://pith.science/pith/UZR6VDT5YGEIAC42NZP2DONDTZ","bundle":"https://pith.science/pith/UZR6VDT5YGEIAC42NZP2DONDTZ/bundle.json","state":"https://pith.science/pith/UZR6VDT5YGEIAC42NZP2DONDTZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UZR6VDT5YGEIAC42NZP2DONDTZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2006:UZR6VDT5YGEIAC42NZP2DONDTZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d3c6871301788d2610d767df903569d95f949541f92806848ad17ec074bc36b2","cross_cats_sorted":["physics.comp-ph"],"license":"","primary_cat":"physics.bio-ph","submitted_at":"2006-07-06T04:16:57Z","title_canon_sha256":"ba88f393a4abe6359da9776ce2f7af20efd6e432dce8908483363d513b3f9fd9"},"schema_version":"1.0","source":{"id":"physics/0607046","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"physics/0607046","created_at":"2026-07-04T14:56:11Z"},{"alias_kind":"arxiv_version","alias_value":"physics/0607046v1","created_at":"2026-07-04T14:56:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.physics/0607046","created_at":"2026-07-04T14:56:11Z"},{"alias_kind":"pith_short_12","alias_value":"UZR6VDT5YGEI","created_at":"2026-07-04T14:56:11Z"},{"alias_kind":"pith_short_16","alias_value":"UZR6VDT5YGEIAC42","created_at":"2026-07-04T14:56:11Z"},{"alias_kind":"pith_short_8","alias_value":"UZR6VDT5","created_at":"2026-07-04T14:56:11Z"}],"graph_snapshots":[{"event_id":"sha256:41f7708f31424a2e7d40cb5c0b22641da4aab7db7a36fadbcb58fb1850d8eb09","target":"graph","created_at":"2026-07-04T14:56:11Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/physics/0607046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a global algorithm for training multilayer neural networks in this Letter. The algorithm is focused on controlling the local fields of neurons induced by the input of samples by random adaptations of the synaptic weights. Unlike the backpropagation algorithm, the networks may have discrete-state weights, and may apply either differentiable or nondifferentiable neural transfer functions. A two-layer network is trained as an example to separate a linearly inseparable set of samples into two categories, and its powerful generalization capacity is emphasized. The extension to more gener","authors_text":"Hong Zhao, Tao Jin","cross_cats":["physics.comp-ph"],"headline":"","license":"","primary_cat":"physics.bio-ph","submitted_at":"2006-07-06T04:16:57Z","title":"A Global Algorithm for Training Multilayer Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"physics/0607046","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:21f51f231083944ca8ec41345fa7287fad933e53e4ca242d6cd1de8a13246c01","target":"record","created_at":"2026-07-04T14:56:11Z","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":"d3c6871301788d2610d767df903569d95f949541f92806848ad17ec074bc36b2","cross_cats_sorted":["physics.comp-ph"],"license":"","primary_cat":"physics.bio-ph","submitted_at":"2006-07-06T04:16:57Z","title_canon_sha256":"ba88f393a4abe6359da9776ce2f7af20efd6e432dce8908483363d513b3f9fd9"},"schema_version":"1.0","source":{"id":"physics/0607046","kind":"arxiv","version":1}},"canonical_sha256":"a663ea8e7dc188800b9a6e5fa1b9a39e69bf3438eb75b84c02d4088f8e4eff2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a663ea8e7dc188800b9a6e5fa1b9a39e69bf3438eb75b84c02d4088f8e4eff2c","first_computed_at":"2026-07-04T14:56:11.824134Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T14:56:11.824134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s5NfKAu84u80t4FvuWFfK1XsiL7Cvo0dsPeFbTqSJ1JzN6BCCtbQFLXytoSo1mJUsM2HulNYMVeOK1tDC9DUCg==","signature_status":"signed_v1","signed_at":"2026-07-04T14:56:11.824546Z","signed_message":"canonical_sha256_bytes"},"source_id":"physics/0607046","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21f51f231083944ca8ec41345fa7287fad933e53e4ca242d6cd1de8a13246c01","sha256:41f7708f31424a2e7d40cb5c0b22641da4aab7db7a36fadbcb58fb1850d8eb09"],"state_sha256":"c680e722b91a2f12d4382da4eaa1ca2a1292da3962eb8e4cc4d43e54b9b7efef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mo07u8GQ7PMHtHuagOIG4e/5NC+5vnmj/+i0/dEujF8nVGAFHZtKqSiyvZXRC2CNI29y6kSomv1RbolPxSKYBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T16:41:24.788111Z","bundle_sha256":"4aa3a6f22b816ee27fba094b95da0d921dd17145e4e4ed5f30001441b4712b4f"}}