{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:7CJR2KIZ2RMCECN4R3KJY4NDJO","short_pith_number":"pith:7CJR2KIZ","schema_version":"1.0","canonical_sha256":"f8931d2919d4582209bc8ed49c71a34b9613959c8febccc17135bb86dcf40286","source":{"kind":"arxiv","id":"1506.05254","version":3},"attestation_state":"computed","paper":{"title":"Gradient Estimation Using Stochastic Computation Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"John Schulman, Nicolas Heess, Pieter Abbeel, Theophane Weber","submitted_at":"2015-06-17T09:32:31Z","abstract_excerpt":"In a variety of problems originating in supervised, unsupervised, and reinforcement learning, the loss function is defined by an expectation over a collection of random variables, which might be part of a probabilistic model or the external world. Estimating the gradient of this loss function, using samples, lies at the core of gradient-based learning algorithms for these problems. We introduce the formalism of stochastic computation graphs---directed acyclic graphs that include both deterministic functions and conditional probability distributions---and describe how to easily and automaticall"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1506.05254","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-17T09:32:31Z","cross_cats_sorted":[],"title_canon_sha256":"1e1c5fb02f369b566d83590b9e347ade36cb7e3c9bdb6d64367ec26c10eec4b8","abstract_canon_sha256":"0b20285c7ae3ce300100c39519413d7018fe787a8c1866019132b7eb6f9a4630"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:23:24.024289Z","signature_b64":"HFng/W3RVRa2e14sQmByqECrsf14HyYp8l0LjD2V76xabS0neJqy/D4qunabA29EMiYoG00+I9yhPMsT1S1LDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8931d2919d4582209bc8ed49c71a34b9613959c8febccc17135bb86dcf40286","last_reissued_at":"2026-05-18T01:23:24.023533Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:23:24.023533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Estimation Using Stochastic Computation Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"John Schulman, Nicolas Heess, Pieter Abbeel, Theophane Weber","submitted_at":"2015-06-17T09:32:31Z","abstract_excerpt":"In a variety of problems originating in supervised, unsupervised, and reinforcement learning, the loss function is defined by an expectation over a collection of random variables, which might be part of a probabilistic model or the external world. Estimating the gradient of this loss function, using samples, lies at the core of gradient-based learning algorithms for these problems. We introduce the formalism of stochastic computation graphs---directed acyclic graphs that include both deterministic functions and conditional probability distributions---and describe how to easily and automaticall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.05254","kind":"arxiv","version":3},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1506.05254","created_at":"2026-05-18T01:23:24.023658+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.05254v3","created_at":"2026-05-18T01:23:24.023658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.05254","created_at":"2026-05-18T01:23:24.023658+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CJR2KIZ2RMC","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CJR2KIZ2RMCECN4","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CJR2KIZ","created_at":"2026-05-18T12:29:07.941421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.06077","citing_title":"Evolvability ES: Scalable and Direct Optimization of Evolvability","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7CJR2KIZ2RMCECN4R3KJY4NDJO","json":"https://pith.science/pith/7CJR2KIZ2RMCECN4R3KJY4NDJO.json","graph_json":"https://pith.science/api/pith-number/7CJR2KIZ2RMCECN4R3KJY4NDJO/graph.json","events_json":"https://pith.science/api/pith-number/7CJR2KIZ2RMCECN4R3KJY4NDJO/events.json","paper":"https://pith.science/paper/7CJR2KIZ"},"agent_actions":{"view_html":"https://pith.science/pith/7CJR2KIZ2RMCECN4R3KJY4NDJO","download_json":"https://pith.science/pith/7CJR2KIZ2RMCECN4R3KJY4NDJO.json","view_paper":"https://pith.science/paper/7CJR2KIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.05254&json=true","fetch_graph":"https://pith.science/api/pith-number/7CJR2KIZ2RMCECN4R3KJY4NDJO/graph.json","fetch_events":"https://pith.science/api/pith-number/7CJR2KIZ2RMCECN4R3KJY4NDJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CJR2KIZ2RMCECN4R3KJY4NDJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CJR2KIZ2RMCECN4R3KJY4NDJO/action/storage_attestation","attest_author":"https://pith.science/pith/7CJR2KIZ2RMCECN4R3KJY4NDJO/action/author_attestation","sign_citation":"https://pith.science/pith/7CJR2KIZ2RMCECN4R3KJY4NDJO/action/citation_signature","submit_replication":"https://pith.science/pith/7CJR2KIZ2RMCECN4R3KJY4NDJO/action/replication_record"}},"created_at":"2026-05-18T01:23:24.023658+00:00","updated_at":"2026-05-18T01:23:24.023658+00:00"}