{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:TGXGQ4PCCLAM5TMLICJRO6A6DI","short_pith_number":"pith:TGXGQ4PC","canonical_record":{"source":{"id":"2007.10412","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-20T19:03:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4396c30e8ac9bbb433010864b4233a6d836bbb4c5966483063d2d107b87ba880","abstract_canon_sha256":"7c402ad1c258d3d6582352394fa4b17aa4e5c82b04162642504b45d174bf1485"},"schema_version":"1.0"},"canonical_sha256":"99ae6871e212c0cecd8b409317781e1a3c7c9e032988aad61ecbf6404a715b2b","source":{"kind":"arxiv","id":"2007.10412","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.10412","created_at":"2026-07-05T02:22:37Z"},{"alias_kind":"arxiv_version","alias_value":"2007.10412v2","created_at":"2026-07-05T02:22:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.10412","created_at":"2026-07-05T02:22:37Z"},{"alias_kind":"pith_short_12","alias_value":"TGXGQ4PCCLAM","created_at":"2026-07-05T02:22:37Z"},{"alias_kind":"pith_short_16","alias_value":"TGXGQ4PCCLAM5TML","created_at":"2026-07-05T02:22:37Z"},{"alias_kind":"pith_short_8","alias_value":"TGXGQ4PC","created_at":"2026-07-05T02:22:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:TGXGQ4PCCLAM5TMLICJRO6A6DI","target":"record","payload":{"canonical_record":{"source":{"id":"2007.10412","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-20T19:03:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4396c30e8ac9bbb433010864b4233a6d836bbb4c5966483063d2d107b87ba880","abstract_canon_sha256":"7c402ad1c258d3d6582352394fa4b17aa4e5c82b04162642504b45d174bf1485"},"schema_version":"1.0"},"canonical_sha256":"99ae6871e212c0cecd8b409317781e1a3c7c9e032988aad61ecbf6404a715b2b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:37.222192Z","signature_b64":"dn52DTO5fUhKaPq84xDYIa+CmEH5L6G75xdhWrvnHi4UnqoO79UGYjvOK1RbcYct8OxKogXU+VnBPA4vXhnTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99ae6871e212c0cecd8b409317781e1a3c7c9e032988aad61ecbf6404a715b2b","last_reissued_at":"2026-07-05T02:22:37.221651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:37.221651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.10412","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":"2026-07-05T02:22:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zEpDAJ26BP2m5iv34hlZ3nCBX2TqctvB51kX/yN0ZEoM6Lx0L8M0tQADLcugyI8YZTeXXVlS28RV8V8xtArdAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:25:22.650423Z"},"content_sha256":"7c344836273fa503bbc09bbf9a654e796d72ada34d75f73eb0d700ffa2595687","schema_version":"1.0","event_id":"sha256:7c344836273fa503bbc09bbf9a654e796d72ada34d75f73eb0d700ffa2595687"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:TGXGQ4PCCLAM5TMLICJRO6A6DI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Randomized Automatic Differentiation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Beatson, Deniz Oktay, Joshua Aduol, Nick McGreivy, Ryan P. Adams","submitted_at":"2020-07-20T19:03:44Z","abstract_excerpt":"The successes of deep learning, variational inference, and many other fields have been aided by specialized implementations of reverse-mode automatic differentiation (AD) to compute gradients of mega-dimensional objectives. The AD techniques underlying these tools were designed to compute exact gradients to numerical precision, but modern machine learning models are almost always trained with stochastic gradient descent. Why spend computation and memory on exact (minibatch) gradients only to use them for stochastic optimization? We develop a general framework and approach for randomized automa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.10412","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.10412/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":"2026-07-05T02:22:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kv3DpAB0eVJ4qaDJbSYXNySvCoG38qmbdsKo66XHuZjHWXce1ahrSpCRff1ZxA2Hq/pZ9kY5L6ZQq2IvdvmkDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:25:22.650903Z"},"content_sha256":"649565401c08301e7a222c6a18f8f89ca5db3a48b5b4f8fbafa6b3b75bf19a0f","schema_version":"1.0","event_id":"sha256:649565401c08301e7a222c6a18f8f89ca5db3a48b5b4f8fbafa6b3b75bf19a0f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TGXGQ4PCCLAM5TMLICJRO6A6DI/bundle.json","state_url":"https://pith.science/pith/TGXGQ4PCCLAM5TMLICJRO6A6DI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TGXGQ4PCCLAM5TMLICJRO6A6DI/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":"2026-08-15T21:25:22Z","links":{"resolver":"https://pith.science/pith/TGXGQ4PCCLAM5TMLICJRO6A6DI","bundle":"https://pith.science/pith/TGXGQ4PCCLAM5TMLICJRO6A6DI/bundle.json","state":"https://pith.science/pith/TGXGQ4PCCLAM5TMLICJRO6A6DI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TGXGQ4PCCLAM5TMLICJRO6A6DI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TGXGQ4PCCLAM5TMLICJRO6A6DI","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":"7c402ad1c258d3d6582352394fa4b17aa4e5c82b04162642504b45d174bf1485","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-20T19:03:44Z","title_canon_sha256":"4396c30e8ac9bbb433010864b4233a6d836bbb4c5966483063d2d107b87ba880"},"schema_version":"1.0","source":{"id":"2007.10412","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.10412","created_at":"2026-07-05T02:22:37Z"},{"alias_kind":"arxiv_version","alias_value":"2007.10412v2","created_at":"2026-07-05T02:22:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.10412","created_at":"2026-07-05T02:22:37Z"},{"alias_kind":"pith_short_12","alias_value":"TGXGQ4PCCLAM","created_at":"2026-07-05T02:22:37Z"},{"alias_kind":"pith_short_16","alias_value":"TGXGQ4PCCLAM5TML","created_at":"2026-07-05T02:22:37Z"},{"alias_kind":"pith_short_8","alias_value":"TGXGQ4PC","created_at":"2026-07-05T02:22:37Z"}],"graph_snapshots":[{"event_id":"sha256:649565401c08301e7a222c6a18f8f89ca5db3a48b5b4f8fbafa6b3b75bf19a0f","target":"graph","created_at":"2026-07-05T02:22:37Z","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/2007.10412/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The successes of deep learning, variational inference, and many other fields have been aided by specialized implementations of reverse-mode automatic differentiation (AD) to compute gradients of mega-dimensional objectives. The AD techniques underlying these tools were designed to compute exact gradients to numerical precision, but modern machine learning models are almost always trained with stochastic gradient descent. Why spend computation and memory on exact (minibatch) gradients only to use them for stochastic optimization? We develop a general framework and approach for randomized automa","authors_text":"Alex Beatson, Deniz Oktay, Joshua Aduol, Nick McGreivy, Ryan P. Adams","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-20T19:03:44Z","title":"Randomized Automatic Differentiation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.10412","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":"sha256:7c344836273fa503bbc09bbf9a654e796d72ada34d75f73eb0d700ffa2595687","target":"record","created_at":"2026-07-05T02:22:37Z","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":"7c402ad1c258d3d6582352394fa4b17aa4e5c82b04162642504b45d174bf1485","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-20T19:03:44Z","title_canon_sha256":"4396c30e8ac9bbb433010864b4233a6d836bbb4c5966483063d2d107b87ba880"},"schema_version":"1.0","source":{"id":"2007.10412","kind":"arxiv","version":2}},"canonical_sha256":"99ae6871e212c0cecd8b409317781e1a3c7c9e032988aad61ecbf6404a715b2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99ae6871e212c0cecd8b409317781e1a3c7c9e032988aad61ecbf6404a715b2b","first_computed_at":"2026-07-05T02:22:37.221651Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:22:37.221651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dn52DTO5fUhKaPq84xDYIa+CmEH5L6G75xdhWrvnHi4UnqoO79UGYjvOK1RbcYct8OxKogXU+VnBPA4vXhnTCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:22:37.222192Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.10412","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c344836273fa503bbc09bbf9a654e796d72ada34d75f73eb0d700ffa2595687","sha256:649565401c08301e7a222c6a18f8f89ca5db3a48b5b4f8fbafa6b3b75bf19a0f"],"state_sha256":"9c1de8b797056829bad3e39cf0fa10e77a3925174ffb7e3c2f038c9e2a66b6e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1uYVVPVYcvRbTl/GL7yefS2IMpF9wI1emsDDHO/KNn6NxE1AuRsapsXpWX6Td5CsyFacbU++SZBAUHlshY5QCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T21:25:22.655189Z","bundle_sha256":"65d09a521feb790f966c9c5169e9b01212a696e672ec22d00ccfec98790baa61"}}