{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:CWLXI23FIOM4Z5CHYRVLKLFIFH","short_pith_number":"pith:CWLXI23F","canonical_record":{"source":{"id":"1502.05767","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SC","submitted_at":"2015-02-20T04:20:47Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"45c927b73689a4a77f04f0621592b0c2c76767469103ab38ab6575f085079931","abstract_canon_sha256":"b24bfccda4d4ac17fb09733cdf01dd5be52b89de714b78c7782bfb9417eff770"},"schema_version":"1.0"},"canonical_sha256":"1597746b654399ccf447c46ab52ca829f11e929f57b44d7a16bc17385d454487","source":{"kind":"arxiv","id":"1502.05767","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.05767","created_at":"2026-05-18T00:10:41Z"},{"alias_kind":"arxiv_version","alias_value":"1502.05767v4","created_at":"2026-05-18T00:10:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.05767","created_at":"2026-05-18T00:10:41Z"},{"alias_kind":"pith_short_12","alias_value":"CWLXI23FIOM4","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"CWLXI23FIOM4Z5CH","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"CWLXI23F","created_at":"2026-05-18T12:29:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:CWLXI23FIOM4Z5CHYRVLKLFIFH","target":"record","payload":{"canonical_record":{"source":{"id":"1502.05767","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SC","submitted_at":"2015-02-20T04:20:47Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"45c927b73689a4a77f04f0621592b0c2c76767469103ab38ab6575f085079931","abstract_canon_sha256":"b24bfccda4d4ac17fb09733cdf01dd5be52b89de714b78c7782bfb9417eff770"},"schema_version":"1.0"},"canonical_sha256":"1597746b654399ccf447c46ab52ca829f11e929f57b44d7a16bc17385d454487","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:41.820987Z","signature_b64":"32D9ZadDjFtedLgg1nwPvDvn47M6aYF4nDYM8i9ZrgGuASSvvmhgEAb9fFsU8xjGR6QheXTYPJpqIXZFKxEiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1597746b654399ccf447c46ab52ca829f11e929f57b44d7a16bc17385d454487","last_reissued_at":"2026-05-18T00:10:41.820390Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:41.820390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1502.05767","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:10:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XiUOQFiJtXqd+1HOrMCBUGxwRttX+rcOz5tkwGHbK9PHdIQNDxpJh+OI3bIkhjyUmCSQOeTNNUEwoi9s2QyhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T15:55:45.993717Z"},"content_sha256":"1dcc41b99c55a15c9de843c3b999a0f050b6652015a7a46ca79917d2abae4805","schema_version":"1.0","event_id":"sha256:1dcc41b99c55a15c9de843c3b999a0f050b6652015a7a46ca79917d2abae4805"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:CWLXI23FIOM4Z5CHYRVLKLFIFH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic differentiation in machine learning: a survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.SC","authors_text":"Alexey Andreyevich Radul, Atilim Gunes Baydin, Barak A. Pearlmutter, Jeffrey Mark Siskind","submitted_at":"2015-02-20T04:20:47Z","abstract_excerpt":"Derivatives, mostly in the form of gradients and Hessians, are ubiquitous in machine learning. Automatic differentiation (AD), also called algorithmic differentiation or simply \"autodiff\", is a family of techniques similar to but more general than backpropagation for efficiently and accurately evaluating derivatives of numeric functions expressed as computer programs. AD is a small but established field with applications in areas including computational fluid dynamics, atmospheric sciences, and engineering design optimization. Until very recently, the fields of machine learning and AD have lar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.05767","kind":"arxiv","version":4},"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":"2026-05-18T00:10:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GUuZ8c94b7OubHpfEl5Ozft2CzAs7E5dHQJjfl9WVeCCFMYTZMgYIIiivACpwUSiE+55prxnGtvUW2IrmlyVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T15:55:45.994064Z"},"content_sha256":"aa189abf2b6731c8528fca353fd899e47cc67c7736171f023b688bbe261b1f2c","schema_version":"1.0","event_id":"sha256:aa189abf2b6731c8528fca353fd899e47cc67c7736171f023b688bbe261b1f2c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CWLXI23FIOM4Z5CHYRVLKLFIFH/bundle.json","state_url":"https://pith.science/pith/CWLXI23FIOM4Z5CHYRVLKLFIFH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CWLXI23FIOM4Z5CHYRVLKLFIFH/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":"2026-06-01T15:55:45Z","links":{"resolver":"https://pith.science/pith/CWLXI23FIOM4Z5CHYRVLKLFIFH","bundle":"https://pith.science/pith/CWLXI23FIOM4Z5CHYRVLKLFIFH/bundle.json","state":"https://pith.science/pith/CWLXI23FIOM4Z5CHYRVLKLFIFH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CWLXI23FIOM4Z5CHYRVLKLFIFH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:CWLXI23FIOM4Z5CHYRVLKLFIFH","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":"b24bfccda4d4ac17fb09733cdf01dd5be52b89de714b78c7782bfb9417eff770","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SC","submitted_at":"2015-02-20T04:20:47Z","title_canon_sha256":"45c927b73689a4a77f04f0621592b0c2c76767469103ab38ab6575f085079931"},"schema_version":"1.0","source":{"id":"1502.05767","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.05767","created_at":"2026-05-18T00:10:41Z"},{"alias_kind":"arxiv_version","alias_value":"1502.05767v4","created_at":"2026-05-18T00:10:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.05767","created_at":"2026-05-18T00:10:41Z"},{"alias_kind":"pith_short_12","alias_value":"CWLXI23FIOM4","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"CWLXI23FIOM4Z5CH","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"CWLXI23F","created_at":"2026-05-18T12:29:17Z"}],"graph_snapshots":[{"event_id":"sha256:aa189abf2b6731c8528fca353fd899e47cc67c7736171f023b688bbe261b1f2c","target":"graph","created_at":"2026-05-18T00:10:41Z","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":"Derivatives, mostly in the form of gradients and Hessians, are ubiquitous in machine learning. Automatic differentiation (AD), also called algorithmic differentiation or simply \"autodiff\", is a family of techniques similar to but more general than backpropagation for efficiently and accurately evaluating derivatives of numeric functions expressed as computer programs. AD is a small but established field with applications in areas including computational fluid dynamics, atmospheric sciences, and engineering design optimization. Until very recently, the fields of machine learning and AD have lar","authors_text":"Alexey Andreyevich Radul, Atilim Gunes Baydin, Barak A. Pearlmutter, Jeffrey Mark Siskind","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SC","submitted_at":"2015-02-20T04:20:47Z","title":"Automatic differentiation in machine learning: a survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.05767","kind":"arxiv","version":4},"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":"sha256:1dcc41b99c55a15c9de843c3b999a0f050b6652015a7a46ca79917d2abae4805","target":"record","created_at":"2026-05-18T00:10:41Z","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":"b24bfccda4d4ac17fb09733cdf01dd5be52b89de714b78c7782bfb9417eff770","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SC","submitted_at":"2015-02-20T04:20:47Z","title_canon_sha256":"45c927b73689a4a77f04f0621592b0c2c76767469103ab38ab6575f085079931"},"schema_version":"1.0","source":{"id":"1502.05767","kind":"arxiv","version":4}},"canonical_sha256":"1597746b654399ccf447c46ab52ca829f11e929f57b44d7a16bc17385d454487","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1597746b654399ccf447c46ab52ca829f11e929f57b44d7a16bc17385d454487","first_computed_at":"2026-05-18T00:10:41.820390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:41.820390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"32D9ZadDjFtedLgg1nwPvDvn47M6aYF4nDYM8i9ZrgGuASSvvmhgEAb9fFsU8xjGR6QheXTYPJpqIXZFKxEiAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:41.820987Z","signed_message":"canonical_sha256_bytes"},"source_id":"1502.05767","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1dcc41b99c55a15c9de843c3b999a0f050b6652015a7a46ca79917d2abae4805","sha256:aa189abf2b6731c8528fca353fd899e47cc67c7736171f023b688bbe261b1f2c"],"state_sha256":"e1a39d6fd5d9910630d5db6c261e930eec470a777dda8ce2c5f944b1efa0be40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G+cRhRGi6KWg8dvFW/+ybdVUhutsVNbEBiyfKsb9cZgeHu9oDNMBrR+1TyhU2ozRASTg0RM92ti5jyW9LKPGBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T15:55:45.996045Z","bundle_sha256":"84f93e7be07807dd0cd568da198fbad4bd294838e2811b74636caf50663e37e8"}}