{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:F3P2XNJEGVNOFUFUX5HPI32BFI","short_pith_number":"pith:F3P2XNJE","canonical_record":{"source":{"id":"1707.04324","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-13T21:01:49Z","cross_cats_sorted":[],"title_canon_sha256":"84684bab0db14ea3ce752901041a39931f7445498619516849d920e6ca57f30b","abstract_canon_sha256":"4ec47c52a05602996d8ba23760fa4760db132d47934464f9d5ad846f8b7d3348"},"schema_version":"1.0"},"canonical_sha256":"2edfabb524355ae2d0b4bf4ef46f412a1370e8dba64ac023c337f6d4431f2455","source":{"kind":"arxiv","id":"1707.04324","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.04324","created_at":"2026-05-18T00:40:18Z"},{"alias_kind":"arxiv_version","alias_value":"1707.04324v1","created_at":"2026-05-18T00:40:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.04324","created_at":"2026-05-18T00:40:18Z"},{"alias_kind":"pith_short_12","alias_value":"F3P2XNJEGVNO","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"F3P2XNJEGVNOFUFU","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"F3P2XNJE","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:F3P2XNJEGVNOFUFUX5HPI32BFI","target":"record","payload":{"canonical_record":{"source":{"id":"1707.04324","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-13T21:01:49Z","cross_cats_sorted":[],"title_canon_sha256":"84684bab0db14ea3ce752901041a39931f7445498619516849d920e6ca57f30b","abstract_canon_sha256":"4ec47c52a05602996d8ba23760fa4760db132d47934464f9d5ad846f8b7d3348"},"schema_version":"1.0"},"canonical_sha256":"2edfabb524355ae2d0b4bf4ef46f412a1370e8dba64ac023c337f6d4431f2455","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:18.641362Z","signature_b64":"xAwGdt8b8yNQwuEMVjOWJ8MU5MdYCxSjOjHt9RB40hkNBr1VByl9x7rxyA1d37a3HwLjDlIFHJrUsiG5hLXJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2edfabb524355ae2d0b4bf4ef46f412a1370e8dba64ac023c337f6d4431f2455","last_reissued_at":"2026-05-18T00:40:18.640669Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:18.640669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.04324","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":"2026-05-18T00:40:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AcqQhaIlaJrNJNhLyrZLe2pyYqoZl2CLeQsLha7W+W00h4XslOaH0oRxq1LwDrt5lGdFAV0YfFOPSN0cVucwBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T14:39:55.520832Z"},"content_sha256":"a0d73fb56d31f116ca248da4872f82dde6b6ffd29059637cece9273c55028290","schema_version":"1.0","event_id":"sha256:a0d73fb56d31f116ca248da4872f82dde6b6ffd29059637cece9273c55028290"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:F3P2XNJEGVNOFUFUX5HPI32BFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tensor-Based Backpropagation in Neural Networks with Non-Sequential Input","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Huang, Hirsh R. Agarwal","submitted_at":"2017-07-13T21:01:49Z","abstract_excerpt":"Neural networks have been able to achieve groundbreaking accuracy at tasks conventionally considered only doable by humans. Using stochastic gradient descent, optimization in many dimensions is made possible, albeit at a relatively high computational cost. By splitting training data into batches, networks can be distributed and trained vastly more efficiently and with minimal accuracy loss. We have explored the mathematics behind efficiently implementing tensor-based batch backpropagation algorithms. A common approach to batch training is iterating over batch items individually. Explicitly usi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.04324","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":""},"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":"2026-05-18T00:40:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J+i5o0U2s4rVU8Xh73zK8S10jWE8geGe+JPkWqe2FxNf4lHKd/wZGXtKr4iZ9zBADQ6XTEO6F+93OoQ+6cjLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T14:39:55.521171Z"},"content_sha256":"42dc84fede3bcda3ff87eccd04ad428111cfec30a5de4fb20f4851148a027186","schema_version":"1.0","event_id":"sha256:42dc84fede3bcda3ff87eccd04ad428111cfec30a5de4fb20f4851148a027186"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F3P2XNJEGVNOFUFUX5HPI32BFI/bundle.json","state_url":"https://pith.science/pith/F3P2XNJEGVNOFUFUX5HPI32BFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F3P2XNJEGVNOFUFUX5HPI32BFI/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":"2026-06-08T14:39:55Z","links":{"resolver":"https://pith.science/pith/F3P2XNJEGVNOFUFUX5HPI32BFI","bundle":"https://pith.science/pith/F3P2XNJEGVNOFUFUX5HPI32BFI/bundle.json","state":"https://pith.science/pith/F3P2XNJEGVNOFUFUX5HPI32BFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F3P2XNJEGVNOFUFUX5HPI32BFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:F3P2XNJEGVNOFUFUX5HPI32BFI","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":"4ec47c52a05602996d8ba23760fa4760db132d47934464f9d5ad846f8b7d3348","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-13T21:01:49Z","title_canon_sha256":"84684bab0db14ea3ce752901041a39931f7445498619516849d920e6ca57f30b"},"schema_version":"1.0","source":{"id":"1707.04324","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.04324","created_at":"2026-05-18T00:40:18Z"},{"alias_kind":"arxiv_version","alias_value":"1707.04324v1","created_at":"2026-05-18T00:40:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.04324","created_at":"2026-05-18T00:40:18Z"},{"alias_kind":"pith_short_12","alias_value":"F3P2XNJEGVNO","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"F3P2XNJEGVNOFUFU","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"F3P2XNJE","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:42dc84fede3bcda3ff87eccd04ad428111cfec30a5de4fb20f4851148a027186","target":"graph","created_at":"2026-05-18T00:40:18Z","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":"Neural networks have been able to achieve groundbreaking accuracy at tasks conventionally considered only doable by humans. Using stochastic gradient descent, optimization in many dimensions is made possible, albeit at a relatively high computational cost. By splitting training data into batches, networks can be distributed and trained vastly more efficiently and with minimal accuracy loss. We have explored the mathematics behind efficiently implementing tensor-based batch backpropagation algorithms. A common approach to batch training is iterating over batch items individually. Explicitly usi","authors_text":"Andrew Huang, Hirsh R. Agarwal","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-13T21:01:49Z","title":"Tensor-Based Backpropagation in Neural Networks with Non-Sequential Input"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.04324","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:a0d73fb56d31f116ca248da4872f82dde6b6ffd29059637cece9273c55028290","target":"record","created_at":"2026-05-18T00:40:18Z","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":"4ec47c52a05602996d8ba23760fa4760db132d47934464f9d5ad846f8b7d3348","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-13T21:01:49Z","title_canon_sha256":"84684bab0db14ea3ce752901041a39931f7445498619516849d920e6ca57f30b"},"schema_version":"1.0","source":{"id":"1707.04324","kind":"arxiv","version":1}},"canonical_sha256":"2edfabb524355ae2d0b4bf4ef46f412a1370e8dba64ac023c337f6d4431f2455","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2edfabb524355ae2d0b4bf4ef46f412a1370e8dba64ac023c337f6d4431f2455","first_computed_at":"2026-05-18T00:40:18.640669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:18.640669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xAwGdt8b8yNQwuEMVjOWJ8MU5MdYCxSjOjHt9RB40hkNBr1VByl9x7rxyA1d37a3HwLjDlIFHJrUsiG5hLXJCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:18.641362Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.04324","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0d73fb56d31f116ca248da4872f82dde6b6ffd29059637cece9273c55028290","sha256:42dc84fede3bcda3ff87eccd04ad428111cfec30a5de4fb20f4851148a027186"],"state_sha256":"090f3547ed9cc120573f79d2c9d1d8d3ae9a2ef9b58724fc156ffcead5392ad3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gBIEwQ8FDad07in/l7S68tqhBODNfyOaVmE/Oq4hP+tiPGMtfDqthqxN1+7WOMiF9a/tjpShsMYCB5W4S43GDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T14:39:55.523040Z","bundle_sha256":"c3b598360bc31fe2ee5c3c587dd7d3465e8ec53abc31154fd86ff984cc0b9be6"}}