{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VCCBKFHNOW4RCV5QNHD6SEHK6T","short_pith_number":"pith:VCCBKFHN","schema_version":"1.0","canonical_sha256":"a8841514ed75b91157b069c7e910eaf4f5a6b022d5fce015892dcd0814ba4846","source":{"kind":"arxiv","id":"2004.11938","version":1},"attestation_state":"computed","paper":{"title":"Towards Differentiable Resampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kevin Murphy, Michael Zhu, Rico Jonschkowski","submitted_at":"2020-04-24T18:37:17Z","abstract_excerpt":"Resampling is a key component of sample-based recursive state estimation in particle filters. Recent work explores differentiable particle filters for end-to-end learning. However, resampling remains a challenge in these works, as it is inherently non-differentiable. We address this challenge by replacing traditional resampling with a learned neural network resampler. We present a novel network architecture, the particle transformer, and train it for particle resampling using a likelihood-based loss function over sets of particles. Incorporated into a differentiable particle filter, our model "},"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":"2004.11938","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-24T18:37:17Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"143bbfcb248a0d49a02fc36e916815f053a9ece0425a97da95b5a3dfe9004544","abstract_canon_sha256":"11c330d60e6460da41752a82a16a13f49a0495461fd1cda25e00bb896bea12b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:25.100037Z","signature_b64":"WnSQA5576VJtiGHLVFa89Xdw1ksxmwC2SD/xr9GulbZ6uIfPGJcS9aSwZN1StMEqmyxdpGCmyHKPNU1cj1EWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8841514ed75b91157b069c7e910eaf4f5a6b022d5fce015892dcd0814ba4846","last_reissued_at":"2026-07-05T00:58:25.099655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:25.099655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Differentiable Resampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kevin Murphy, Michael Zhu, Rico Jonschkowski","submitted_at":"2020-04-24T18:37:17Z","abstract_excerpt":"Resampling is a key component of sample-based recursive state estimation in particle filters. Recent work explores differentiable particle filters for end-to-end learning. However, resampling remains a challenge in these works, as it is inherently non-differentiable. We address this challenge by replacing traditional resampling with a learned neural network resampler. We present a novel network architecture, the particle transformer, and train it for particle resampling using a likelihood-based loss function over sets of particles. Incorporated into a differentiable particle filter, our model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.11938","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/2004.11938/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":"2004.11938","created_at":"2026-07-05T00:58:25.099709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.11938v1","created_at":"2026-07-05T00:58:25.099709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.11938","created_at":"2026-07-05T00:58:25.099709+00:00"},{"alias_kind":"pith_short_12","alias_value":"VCCBKFHNOW4R","created_at":"2026-07-05T00:58:25.099709+00:00"},{"alias_kind":"pith_short_16","alias_value":"VCCBKFHNOW4RCV5Q","created_at":"2026-07-05T00:58:25.099709+00:00"},{"alias_kind":"pith_short_8","alias_value":"VCCBKFHN","created_at":"2026-07-05T00:58:25.099709+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15638","citing_title":"Learning state and proposal dynamics in state-space models using differentiable particle filters and neural networks","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VCCBKFHNOW4RCV5QNHD6SEHK6T","json":"https://pith.science/pith/VCCBKFHNOW4RCV5QNHD6SEHK6T.json","graph_json":"https://pith.science/api/pith-number/VCCBKFHNOW4RCV5QNHD6SEHK6T/graph.json","events_json":"https://pith.science/api/pith-number/VCCBKFHNOW4RCV5QNHD6SEHK6T/events.json","paper":"https://pith.science/paper/VCCBKFHN"},"agent_actions":{"view_html":"https://pith.science/pith/VCCBKFHNOW4RCV5QNHD6SEHK6T","download_json":"https://pith.science/pith/VCCBKFHNOW4RCV5QNHD6SEHK6T.json","view_paper":"https://pith.science/paper/VCCBKFHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.11938&json=true","fetch_graph":"https://pith.science/api/pith-number/VCCBKFHNOW4RCV5QNHD6SEHK6T/graph.json","fetch_events":"https://pith.science/api/pith-number/VCCBKFHNOW4RCV5QNHD6SEHK6T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VCCBKFHNOW4RCV5QNHD6SEHK6T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VCCBKFHNOW4RCV5QNHD6SEHK6T/action/storage_attestation","attest_author":"https://pith.science/pith/VCCBKFHNOW4RCV5QNHD6SEHK6T/action/author_attestation","sign_citation":"https://pith.science/pith/VCCBKFHNOW4RCV5QNHD6SEHK6T/action/citation_signature","submit_replication":"https://pith.science/pith/VCCBKFHNOW4RCV5QNHD6SEHK6T/action/replication_record"}},"created_at":"2026-07-05T00:58:25.099709+00:00","updated_at":"2026-07-05T00:58:25.099709+00:00"}