{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ST3GONLEYLNIJBDU52WCSUCS66","short_pith_number":"pith:ST3GONLE","schema_version":"1.0","canonical_sha256":"94f6673564c2da848474eeac295052f7b53c86eec25ab254c37e02a381328838","source":{"kind":"arxiv","id":"1802.05098","version":3},"attestation_state":"computed","paper":{"title":"DiCE: The Infinitely Differentiable Monte-Carlo Estimator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Eric P. Xing, Gregory Farquhar, Jakob Foerster, Maruan Al-Shedivat, Shimon Whiteson, Tim Rockt\\\"aschel","submitted_at":"2018-02-14T14:05:54Z","abstract_excerpt":"The score function estimator is widely used for estimating gradients of stochastic objectives in stochastic computation graphs (SCG), eg, in reinforcement learning and meta-learning. While deriving the first-order gradient estimators by differentiating a surrogate loss (SL) objective is computationally and conceptually simple, using the same approach for higher-order derivatives is more challenging. Firstly, analytically deriving and implementing such estimators is laborious and not compliant with automatic differentiation. Secondly, repeatedly applying SL to construct new objectives for each "},"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":"1802.05098","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T14:05:54Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"eaff8be5d2834a124df15236f87c6afc083e816cda56518464a37843ed7bee49","abstract_canon_sha256":"e7e455a62d86dad82a2e611726e71cee3027f87a7c00d35c8568a0c2d1357095"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:30.118156Z","signature_b64":"AIZYI7hZoEVY+IIYNUupXxbAA0gHiNyxxkWG2nnipQuqbiFdmK5q2EETvnI+SXdTT2944fDw1x4SYXwODrLQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94f6673564c2da848474eeac295052f7b53c86eec25ab254c37e02a381328838","last_reissued_at":"2026-05-18T00:01:30.117570Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:30.117570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiCE: The Infinitely Differentiable Monte-Carlo Estimator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Eric P. Xing, Gregory Farquhar, Jakob Foerster, Maruan Al-Shedivat, Shimon Whiteson, Tim Rockt\\\"aschel","submitted_at":"2018-02-14T14:05:54Z","abstract_excerpt":"The score function estimator is widely used for estimating gradients of stochastic objectives in stochastic computation graphs (SCG), eg, in reinforcement learning and meta-learning. While deriving the first-order gradient estimators by differentiating a surrogate loss (SL) objective is computationally and conceptually simple, using the same approach for higher-order derivatives is more challenging. Firstly, analytically deriving and implementing such estimators is laborious and not compliant with automatic differentiation. Secondly, repeatedly applying SL to construct new objectives for each "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05098","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":"1802.05098","created_at":"2026-05-18T00:01:30.117677+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.05098v3","created_at":"2026-05-18T00:01:30.117677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05098","created_at":"2026-05-18T00:01:30.117677+00:00"},{"alias_kind":"pith_short_12","alias_value":"ST3GONLEYLNI","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"ST3GONLEYLNIJBDU","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"ST3GONLE","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.01066","citing_title":"Language Models as Knowledge Bases?","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ST3GONLEYLNIJBDU52WCSUCS66","json":"https://pith.science/pith/ST3GONLEYLNIJBDU52WCSUCS66.json","graph_json":"https://pith.science/api/pith-number/ST3GONLEYLNIJBDU52WCSUCS66/graph.json","events_json":"https://pith.science/api/pith-number/ST3GONLEYLNIJBDU52WCSUCS66/events.json","paper":"https://pith.science/paper/ST3GONLE"},"agent_actions":{"view_html":"https://pith.science/pith/ST3GONLEYLNIJBDU52WCSUCS66","download_json":"https://pith.science/pith/ST3GONLEYLNIJBDU52WCSUCS66.json","view_paper":"https://pith.science/paper/ST3GONLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.05098&json=true","fetch_graph":"https://pith.science/api/pith-number/ST3GONLEYLNIJBDU52WCSUCS66/graph.json","fetch_events":"https://pith.science/api/pith-number/ST3GONLEYLNIJBDU52WCSUCS66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ST3GONLEYLNIJBDU52WCSUCS66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ST3GONLEYLNIJBDU52WCSUCS66/action/storage_attestation","attest_author":"https://pith.science/pith/ST3GONLEYLNIJBDU52WCSUCS66/action/author_attestation","sign_citation":"https://pith.science/pith/ST3GONLEYLNIJBDU52WCSUCS66/action/citation_signature","submit_replication":"https://pith.science/pith/ST3GONLEYLNIJBDU52WCSUCS66/action/replication_record"}},"created_at":"2026-05-18T00:01:30.117677+00:00","updated_at":"2026-05-18T00:01:30.117677+00:00"}