{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5T2R5WAOP5RLATRZA5B2YMEW3J","short_pith_number":"pith:5T2R5WAO","canonical_record":{"source":{"id":"1905.10457","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T21:43:40Z","cross_cats_sorted":["math.NA","stat.ML"],"title_canon_sha256":"3e2f6a79a60cc201dc97a595bb493b591a08a415ef08c770f6599d17bc476c40","abstract_canon_sha256":"b4f4ca99654a5b6f07159db9304c9e48ac99fbfa870f09dbc5eb3c568d36b2eb"},"schema_version":"1.0"},"canonical_sha256":"ecf51ed80e7f62b04e390743ac3096da7319251085350892653b43b0cfc47ed7","source":{"kind":"arxiv","id":"1905.10457","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10457","created_at":"2026-05-17T23:44:53Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10457v2","created_at":"2026-05-17T23:44:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10457","created_at":"2026-05-17T23:44:53Z"},{"alias_kind":"pith_short_12","alias_value":"5T2R5WAOP5RL","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5T2R5WAOP5RLATRZ","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5T2R5WAO","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5T2R5WAOP5RLATRZA5B2YMEW3J","target":"record","payload":{"canonical_record":{"source":{"id":"1905.10457","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T21:43:40Z","cross_cats_sorted":["math.NA","stat.ML"],"title_canon_sha256":"3e2f6a79a60cc201dc97a595bb493b591a08a415ef08c770f6599d17bc476c40","abstract_canon_sha256":"b4f4ca99654a5b6f07159db9304c9e48ac99fbfa870f09dbc5eb3c568d36b2eb"},"schema_version":"1.0"},"canonical_sha256":"ecf51ed80e7f62b04e390743ac3096da7319251085350892653b43b0cfc47ed7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:53.594036Z","signature_b64":"Ur8tmJW9LAsNE5/4qywqyA1cd07JXHSalz/2nChoXTuSJ4kp8Sc/czqHqDCUnXQRRVSJwBFPpsyYCPPGVzlJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecf51ed80e7f62b04e390743ac3096da7319251085350892653b43b0cfc47ed7","last_reissued_at":"2026-05-17T23:44:53.593399Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:53.593399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.10457","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4nPDu7iTunxJ4tUQQSsIl3shKKP2O7otKeijI7ZX3CqoosKWmXAmNsydpavXE/ddbCeGIBsD7wO5S5rpLSa+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T09:25:40.972207Z"},"content_sha256":"f806fcfa3d9c135c508dc68054d2caba18bec57021a871e842273394f74bc74e","schema_version":"1.0","event_id":"sha256:f806fcfa3d9c135c508dc68054d2caba18bec57021a871e842273394f74bc74e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5T2R5WAOP5RLATRZA5B2YMEW3J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Polynomial-Based Approach for Architectural Design and Learning with Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Clayton G. Webster, Joseph Daws Jr.","submitted_at":"2019-05-24T21:43:40Z","abstract_excerpt":"In this effort we propose a novel approach for reconstructing multivariate functions from training data, by identifying both a suitable network architecture and an initialization using polynomial-based approximations. Training deep neural networks using gradient descent can be interpreted as moving the set of network parameters along the loss landscape in order to minimize the loss functional. The initialization of parameters is important for iterative training methods based on descent. Our procedure produces a network whose initial state is a polynomial representation of the training data. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10457","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:44:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jlP7swQGDV7eQa7YqB8fmZFUkpxxXWcJ1k6KqP67/WAvowp8osRkmbE6QMBVMQkJ8KZmMQWqR6ngWxwDLBBJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T09:25:40.972574Z"},"content_sha256":"1c2ea71a6b48d1d2a6776e447e87d35b62617b477be0814dfcbde7e3391ab8f4","schema_version":"1.0","event_id":"sha256:1c2ea71a6b48d1d2a6776e447e87d35b62617b477be0814dfcbde7e3391ab8f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5T2R5WAOP5RLATRZA5B2YMEW3J/bundle.json","state_url":"https://pith.science/pith/5T2R5WAOP5RLATRZA5B2YMEW3J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5T2R5WAOP5RLATRZA5B2YMEW3J/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":"2026-06-20T09:25:40Z","links":{"resolver":"https://pith.science/pith/5T2R5WAOP5RLATRZA5B2YMEW3J","bundle":"https://pith.science/pith/5T2R5WAOP5RLATRZA5B2YMEW3J/bundle.json","state":"https://pith.science/pith/5T2R5WAOP5RLATRZA5B2YMEW3J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5T2R5WAOP5RLATRZA5B2YMEW3J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5T2R5WAOP5RLATRZA5B2YMEW3J","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":"b4f4ca99654a5b6f07159db9304c9e48ac99fbfa870f09dbc5eb3c568d36b2eb","cross_cats_sorted":["math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T21:43:40Z","title_canon_sha256":"3e2f6a79a60cc201dc97a595bb493b591a08a415ef08c770f6599d17bc476c40"},"schema_version":"1.0","source":{"id":"1905.10457","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10457","created_at":"2026-05-17T23:44:53Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10457v2","created_at":"2026-05-17T23:44:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10457","created_at":"2026-05-17T23:44:53Z"},{"alias_kind":"pith_short_12","alias_value":"5T2R5WAOP5RL","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5T2R5WAOP5RLATRZ","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5T2R5WAO","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:1c2ea71a6b48d1d2a6776e447e87d35b62617b477be0814dfcbde7e3391ab8f4","target":"graph","created_at":"2026-05-17T23:44:53Z","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"},"paper":{"abstract_excerpt":"In this effort we propose a novel approach for reconstructing multivariate functions from training data, by identifying both a suitable network architecture and an initialization using polynomial-based approximations. Training deep neural networks using gradient descent can be interpreted as moving the set of network parameters along the loss landscape in order to minimize the loss functional. The initialization of parameters is important for iterative training methods based on descent. Our procedure produces a network whose initial state is a polynomial representation of the training data. Th","authors_text":"Clayton G. Webster, Joseph Daws Jr.","cross_cats":["math.NA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T21:43:40Z","title":"A Polynomial-Based Approach for Architectural Design and Learning with Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10457","kind":"arxiv","version":2},"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:f806fcfa3d9c135c508dc68054d2caba18bec57021a871e842273394f74bc74e","target":"record","created_at":"2026-05-17T23:44:53Z","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":"b4f4ca99654a5b6f07159db9304c9e48ac99fbfa870f09dbc5eb3c568d36b2eb","cross_cats_sorted":["math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T21:43:40Z","title_canon_sha256":"3e2f6a79a60cc201dc97a595bb493b591a08a415ef08c770f6599d17bc476c40"},"schema_version":"1.0","source":{"id":"1905.10457","kind":"arxiv","version":2}},"canonical_sha256":"ecf51ed80e7f62b04e390743ac3096da7319251085350892653b43b0cfc47ed7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecf51ed80e7f62b04e390743ac3096da7319251085350892653b43b0cfc47ed7","first_computed_at":"2026-05-17T23:44:53.593399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:53.593399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ur8tmJW9LAsNE5/4qywqyA1cd07JXHSalz/2nChoXTuSJ4kp8Sc/czqHqDCUnXQRRVSJwBFPpsyYCPPGVzlJBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:53.594036Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10457","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f806fcfa3d9c135c508dc68054d2caba18bec57021a871e842273394f74bc74e","sha256:1c2ea71a6b48d1d2a6776e447e87d35b62617b477be0814dfcbde7e3391ab8f4"],"state_sha256":"83453565e0893244100f30ebcd794da460af051d68f138b7ebc40088a0101c06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PPmsWqm5tG44NaiGWlkLFcPsYXmIKOTJU/BS2lh7uUzY7aMUzw4oLiRyYprDTJQyuWlto4vUfxSw5wMHVeSdCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T09:25:40.974554Z","bundle_sha256":"588d23ffccd49929cf807a9688911f64a2e469d109b027b25ff02f0a4bbf901f"}}