{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CCIMCYXSW4TCDAPNT3NWPO5KY7","short_pith_number":"pith:CCIMCYXS","schema_version":"1.0","canonical_sha256":"1090c162f2b7262181ed9edb67bbaac7f2f60c99fc8d6ff000a04adb15d8c8a2","source":{"kind":"arxiv","id":"2106.10314","version":2},"attestation_state":"computed","paper":{"title":"Differentiable Particle Filtering without Modifying the Forward Pass","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Adam \\'Scibior, Frank Wood","submitted_at":"2021-06-18T18:58:52Z","abstract_excerpt":"Particle filters are not compatible with automatic differentiation due to the presence of discrete resampling steps. While known estimators for the score function, based on Fisher's identity, can be computed using particle filters, up to this point they required manual implementation. In this paper we show that such estimators can be computed using automatic differentiation, after introducing a simple correction to the particle weights. This correction utilizes the stop-gradient operator and does not modify the particle filter operation on the forward pass, while also being cheap and easy to c"},"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":"2106.10314","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2021-06-18T18:58:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"df2ace7f7731ae0208febf0c68ab5d3bd61de6217008f1086c7c73e6df285028","abstract_canon_sha256":"e8e0eb83f3a3a69f9a65406c090d289864772c64ede581ef0fc5edf47b0d794b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:42.995764Z","signature_b64":"TJ65eJMllOVALsH7hg10Vsxkv1ESr+ZaBpd8/u2AACZbumCKGo1ttjGtLCnakqfYGzyBLMCArZIf6928zD2YDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1090c162f2b7262181ed9edb67bbaac7f2f60c99fc8d6ff000a04adb15d8c8a2","last_reissued_at":"2026-07-05T03:23:42.995335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:42.995335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Particle Filtering without Modifying the Forward Pass","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Adam \\'Scibior, Frank Wood","submitted_at":"2021-06-18T18:58:52Z","abstract_excerpt":"Particle filters are not compatible with automatic differentiation due to the presence of discrete resampling steps. While known estimators for the score function, based on Fisher's identity, can be computed using particle filters, up to this point they required manual implementation. In this paper we show that such estimators can be computed using automatic differentiation, after introducing a simple correction to the particle weights. This correction utilizes the stop-gradient operator and does not modify the particle filter operation on the forward pass, while also being cheap and easy to c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.10314","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/2106.10314/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":"2106.10314","created_at":"2026-07-05T03:23:42.995392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.10314v2","created_at":"2026-07-05T03:23:42.995392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10314","created_at":"2026-07-05T03:23:42.995392+00:00"},{"alias_kind":"pith_short_12","alias_value":"CCIMCYXSW4TC","created_at":"2026-07-05T03:23:42.995392+00:00"},{"alias_kind":"pith_short_16","alias_value":"CCIMCYXSW4TCDAPN","created_at":"2026-07-05T03:23:42.995392+00:00"},{"alias_kind":"pith_short_8","alias_value":"CCIMCYXS","created_at":"2026-07-05T03:23:42.995392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21108","citing_title":"Efficient Learning of Deep State Space Models via Importance Smoothing","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21108","citing_title":"Efficient Learning of Deep State Space Models via Importance Smoothing","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CCIMCYXSW4TCDAPNT3NWPO5KY7","json":"https://pith.science/pith/CCIMCYXSW4TCDAPNT3NWPO5KY7.json","graph_json":"https://pith.science/api/pith-number/CCIMCYXSW4TCDAPNT3NWPO5KY7/graph.json","events_json":"https://pith.science/api/pith-number/CCIMCYXSW4TCDAPNT3NWPO5KY7/events.json","paper":"https://pith.science/paper/CCIMCYXS"},"agent_actions":{"view_html":"https://pith.science/pith/CCIMCYXSW4TCDAPNT3NWPO5KY7","download_json":"https://pith.science/pith/CCIMCYXSW4TCDAPNT3NWPO5KY7.json","view_paper":"https://pith.science/paper/CCIMCYXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.10314&json=true","fetch_graph":"https://pith.science/api/pith-number/CCIMCYXSW4TCDAPNT3NWPO5KY7/graph.json","fetch_events":"https://pith.science/api/pith-number/CCIMCYXSW4TCDAPNT3NWPO5KY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CCIMCYXSW4TCDAPNT3NWPO5KY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CCIMCYXSW4TCDAPNT3NWPO5KY7/action/storage_attestation","attest_author":"https://pith.science/pith/CCIMCYXSW4TCDAPNT3NWPO5KY7/action/author_attestation","sign_citation":"https://pith.science/pith/CCIMCYXSW4TCDAPNT3NWPO5KY7/action/citation_signature","submit_replication":"https://pith.science/pith/CCIMCYXSW4TCDAPNT3NWPO5KY7/action/replication_record"}},"created_at":"2026-07-05T03:23:42.995392+00:00","updated_at":"2026-07-05T03:23:42.995392+00:00"}