{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YBEIPUNKWV3OZQKCMTMNTIPNOT","short_pith_number":"pith:YBEIPUNK","canonical_record":{"source":{"id":"1912.03579","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-08T00:08:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"484da4f00e0a5eda7f5bb34b1a4d39a24416515fcad763185dab0be25ec99b8c","abstract_canon_sha256":"1797e70a6f7c48d2dff786480c690c844e09799e0e5e7904cbd6b3d34b46d117"},"schema_version":"1.0"},"canonical_sha256":"c04887d1aab576ecc14264d8d9a1ed74cc16aeb36cb4414eed6f0d5b661d4574","source":{"kind":"arxiv","id":"1912.03579","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.03579","created_at":"2026-07-05T00:24:46Z"},{"alias_kind":"arxiv_version","alias_value":"1912.03579v1","created_at":"2026-07-05T00:24:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03579","created_at":"2026-07-05T00:24:46Z"},{"alias_kind":"pith_short_12","alias_value":"YBEIPUNKWV3O","created_at":"2026-07-05T00:24:46Z"},{"alias_kind":"pith_short_16","alias_value":"YBEIPUNKWV3OZQKC","created_at":"2026-07-05T00:24:46Z"},{"alias_kind":"pith_short_8","alias_value":"YBEIPUNK","created_at":"2026-07-05T00:24:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YBEIPUNKWV3OZQKCMTMNTIPNOT","target":"record","payload":{"canonical_record":{"source":{"id":"1912.03579","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-08T00:08:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"484da4f00e0a5eda7f5bb34b1a4d39a24416515fcad763185dab0be25ec99b8c","abstract_canon_sha256":"1797e70a6f7c48d2dff786480c690c844e09799e0e5e7904cbd6b3d34b46d117"},"schema_version":"1.0"},"canonical_sha256":"c04887d1aab576ecc14264d8d9a1ed74cc16aeb36cb4414eed6f0d5b661d4574","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:46.749136Z","signature_b64":"IVKWNhHL50naci/6pXIuZili+LxipXf4ka5ML57ZJiu8Q26/KKNTRnEaYmbx7yGVA0obPKl+luLVd3kYqyoXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c04887d1aab576ecc14264d8d9a1ed74cc16aeb36cb4414eed6f0d5b661d4574","last_reissued_at":"2026-07-05T00:24:46.748798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:46.748798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.03579","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":"2026-07-05T00:24:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BEDSSCjJ3IuE1HAcO3+nYzpRlZwUYi2ZCYdeRBSiY+PdgIkHCnf1Z/2RPm1TE9/wxvMYoPh3o6B+VYNv2moiBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:11:27.065467Z"},"content_sha256":"58610059e72e70f51e93459bd0ef7679448e4213a82c3326a1e311627ecd02e6","schema_version":"1.0","event_id":"sha256:58610059e72e70f51e93459bd0ef7679448e4213a82c3326a1e311627ecd02e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YBEIPUNKWV3OZQKCMTMNTIPNOT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Networks with Cheap Differential Operators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Duvenaud, Ricky T. Q. Chen","submitted_at":"2019-12-08T00:08:50Z","abstract_excerpt":"Gradients of neural networks can be computed efficiently for any architecture, but some applications require differential operators with higher time complexity. We describe a family of restricted neural network architectures that allow efficient computation of a family of differential operators involving dimension-wise derivatives, used in cases such as computing the divergence. Our proposed architecture has a Jacobian matrix composed of diagonal and hollow (non-diagonal) components. We can then modify the backward computation graph to extract dimension-wise derivatives efficiently with automa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.03579","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/1912.03579/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":"2026-07-05T00:24:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9KtbCFy/Lb1V6RHmi19JD/8Ct+pxHzUqbo1Z5lJBs3xKg/v8Sr8xuKMQCX59HbQEG4+/HLrcdcRp/qZo/9YLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:11:27.066060Z"},"content_sha256":"3c03eb5d8e77f295888f54417d044318f5ae114510d3b0f5bba675e66d19f2b1","schema_version":"1.0","event_id":"sha256:3c03eb5d8e77f295888f54417d044318f5ae114510d3b0f5bba675e66d19f2b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YBEIPUNKWV3OZQKCMTMNTIPNOT/bundle.json","state_url":"https://pith.science/pith/YBEIPUNKWV3OZQKCMTMNTIPNOT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YBEIPUNKWV3OZQKCMTMNTIPNOT/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":"2026-08-03T22:11:27Z","links":{"resolver":"https://pith.science/pith/YBEIPUNKWV3OZQKCMTMNTIPNOT","bundle":"https://pith.science/pith/YBEIPUNKWV3OZQKCMTMNTIPNOT/bundle.json","state":"https://pith.science/pith/YBEIPUNKWV3OZQKCMTMNTIPNOT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YBEIPUNKWV3OZQKCMTMNTIPNOT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YBEIPUNKWV3OZQKCMTMNTIPNOT","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":"1797e70a6f7c48d2dff786480c690c844e09799e0e5e7904cbd6b3d34b46d117","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-08T00:08:50Z","title_canon_sha256":"484da4f00e0a5eda7f5bb34b1a4d39a24416515fcad763185dab0be25ec99b8c"},"schema_version":"1.0","source":{"id":"1912.03579","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.03579","created_at":"2026-07-05T00:24:46Z"},{"alias_kind":"arxiv_version","alias_value":"1912.03579v1","created_at":"2026-07-05T00:24:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03579","created_at":"2026-07-05T00:24:46Z"},{"alias_kind":"pith_short_12","alias_value":"YBEIPUNKWV3O","created_at":"2026-07-05T00:24:46Z"},{"alias_kind":"pith_short_16","alias_value":"YBEIPUNKWV3OZQKC","created_at":"2026-07-05T00:24:46Z"},{"alias_kind":"pith_short_8","alias_value":"YBEIPUNK","created_at":"2026-07-05T00:24:46Z"}],"graph_snapshots":[{"event_id":"sha256:3c03eb5d8e77f295888f54417d044318f5ae114510d3b0f5bba675e66d19f2b1","target":"graph","created_at":"2026-07-05T00:24:46Z","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/1912.03579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gradients of neural networks can be computed efficiently for any architecture, but some applications require differential operators with higher time complexity. We describe a family of restricted neural network architectures that allow efficient computation of a family of differential operators involving dimension-wise derivatives, used in cases such as computing the divergence. Our proposed architecture has a Jacobian matrix composed of diagonal and hollow (non-diagonal) components. We can then modify the backward computation graph to extract dimension-wise derivatives efficiently with automa","authors_text":"David Duvenaud, Ricky T. Q. Chen","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-08T00:08:50Z","title":"Neural Networks with Cheap Differential Operators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.03579","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":"sha256:58610059e72e70f51e93459bd0ef7679448e4213a82c3326a1e311627ecd02e6","target":"record","created_at":"2026-07-05T00:24:46Z","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":"1797e70a6f7c48d2dff786480c690c844e09799e0e5e7904cbd6b3d34b46d117","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-08T00:08:50Z","title_canon_sha256":"484da4f00e0a5eda7f5bb34b1a4d39a24416515fcad763185dab0be25ec99b8c"},"schema_version":"1.0","source":{"id":"1912.03579","kind":"arxiv","version":1}},"canonical_sha256":"c04887d1aab576ecc14264d8d9a1ed74cc16aeb36cb4414eed6f0d5b661d4574","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c04887d1aab576ecc14264d8d9a1ed74cc16aeb36cb4414eed6f0d5b661d4574","first_computed_at":"2026-07-05T00:24:46.748798Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:24:46.748798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IVKWNhHL50naci/6pXIuZili+LxipXf4ka5ML57ZJiu8Q26/KKNTRnEaYmbx7yGVA0obPKl+luLVd3kYqyoXAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:24:46.749136Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.03579","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58610059e72e70f51e93459bd0ef7679448e4213a82c3326a1e311627ecd02e6","sha256:3c03eb5d8e77f295888f54417d044318f5ae114510d3b0f5bba675e66d19f2b1"],"state_sha256":"b48e6b161ec2ad12fab3a3d868234fb4912dbf5918b4b74b30260ae04873579a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DCroTCIq4JkyTPl8wkmg9E+keT9Sgr1a2RqwzLdwRqMRXwUWSLw26Z9Y8ZiGzmWcLYb9wVP/6ZaJyq4OR8VCCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:11:27.071206Z","bundle_sha256":"5fd78d9e3222736c0dd867add438ba6e8dd9427fe39b91f72ab22e43ca04f3f5"}}