{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I66RJ3LOZRCMPVBDWV7TCP45HD","short_pith_number":"pith:I66RJ3LO","schema_version":"1.0","canonical_sha256":"47bd14ed6ecc44c7d423b57f313f9d38ee2bb0f4f077998db91a2a1254279899","source":{"kind":"arxiv","id":"2410.08125","version":1},"attestation_state":"computed","paper":{"title":"Generalizing Stochastic Smoothing for Differentiation and Gradient Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aashwin Mishra, Christian Borgelt, Felix Petersen, Stefano Ermon","submitted_at":"2024-10-10T17:10:00Z","abstract_excerpt":"We deal with the problem of gradient estimation for stochastic differentiable relaxations of algorithms, operators, simulators, and other non-differentiable functions. Stochastic smoothing conventionally perturbs the input of a non-differentiable function with a differentiable density distribution with full support, smoothing it and enabling gradient estimation. Our theory starts at first principles to derive stochastic smoothing with reduced assumptions, without requiring a differentiable density nor full support, and we present a general framework for relaxation and gradient estimation of no"},"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":"2410.08125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T17:10:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0cc1b0c4c6dfcf3d3d2838a5e664c00657d02e89791401d9046a792c82f63da6","abstract_canon_sha256":"762a6d5db289e22ead9bbfc3b424993524f490902625b6162b94bf01e256d6a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:48.866101Z","signature_b64":"/uX5kyH57UwqggvbYQSSgxQb5SwqKBsGR2e/qSHpxoceKW68DlxssDGcCvAC7Rrfu62idkVmOQz45FmhKkvkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47bd14ed6ecc44c7d423b57f313f9d38ee2bb0f4f077998db91a2a1254279899","last_reissued_at":"2026-07-05T09:18:48.865543Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:48.865543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalizing Stochastic Smoothing for Differentiation and Gradient Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aashwin Mishra, Christian Borgelt, Felix Petersen, Stefano Ermon","submitted_at":"2024-10-10T17:10:00Z","abstract_excerpt":"We deal with the problem of gradient estimation for stochastic differentiable relaxations of algorithms, operators, simulators, and other non-differentiable functions. Stochastic smoothing conventionally perturbs the input of a non-differentiable function with a differentiable density distribution with full support, smoothing it and enabling gradient estimation. Our theory starts at first principles to derive stochastic smoothing with reduced assumptions, without requiring a differentiable density nor full support, and we present a general framework for relaxation and gradient estimation of no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08125","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/2410.08125/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.08125","created_at":"2026-07-05T09:18:48.865601+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08125v1","created_at":"2026-07-05T09:18:48.865601+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08125","created_at":"2026-07-05T09:18:48.865601+00:00"},{"alias_kind":"pith_short_12","alias_value":"I66RJ3LOZRCM","created_at":"2026-07-05T09:18:48.865601+00:00"},{"alias_kind":"pith_short_16","alias_value":"I66RJ3LOZRCMPVBD","created_at":"2026-07-05T09:18:48.865601+00:00"},{"alias_kind":"pith_short_8","alias_value":"I66RJ3LO","created_at":"2026-07-05T09:18:48.865601+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I66RJ3LOZRCMPVBDWV7TCP45HD","json":"https://pith.science/pith/I66RJ3LOZRCMPVBDWV7TCP45HD.json","graph_json":"https://pith.science/api/pith-number/I66RJ3LOZRCMPVBDWV7TCP45HD/graph.json","events_json":"https://pith.science/api/pith-number/I66RJ3LOZRCMPVBDWV7TCP45HD/events.json","paper":"https://pith.science/paper/I66RJ3LO"},"agent_actions":{"view_html":"https://pith.science/pith/I66RJ3LOZRCMPVBDWV7TCP45HD","download_json":"https://pith.science/pith/I66RJ3LOZRCMPVBDWV7TCP45HD.json","view_paper":"https://pith.science/paper/I66RJ3LO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08125&json=true","fetch_graph":"https://pith.science/api/pith-number/I66RJ3LOZRCMPVBDWV7TCP45HD/graph.json","fetch_events":"https://pith.science/api/pith-number/I66RJ3LOZRCMPVBDWV7TCP45HD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I66RJ3LOZRCMPVBDWV7TCP45HD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I66RJ3LOZRCMPVBDWV7TCP45HD/action/storage_attestation","attest_author":"https://pith.science/pith/I66RJ3LOZRCMPVBDWV7TCP45HD/action/author_attestation","sign_citation":"https://pith.science/pith/I66RJ3LOZRCMPVBDWV7TCP45HD/action/citation_signature","submit_replication":"https://pith.science/pith/I66RJ3LOZRCMPVBDWV7TCP45HD/action/replication_record"}},"created_at":"2026-07-05T09:18:48.865601+00:00","updated_at":"2026-07-05T09:18:48.865601+00:00"}