{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:M6A3LSKMQ2OPD4GODNCZYESHI6","short_pith_number":"pith:M6A3LSKM","schema_version":"1.0","canonical_sha256":"6781b5c94c869cf1f0ce1b459c124747b215d6a6e3301ffc506a3df4ae15f9ca","source":{"kind":"arxiv","id":"2107.00488","version":3},"attestation_state":"computed","paper":{"title":"Differentiable Particle Filters through Conditional Normalizing Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Hao Wen, Xiongjie Chen, Yunpeng Li","submitted_at":"2021-07-01T14:31:27Z","abstract_excerpt":"Differentiable particle filters provide a flexible mechanism to adaptively train dynamic and measurement models by learning from observed data. However, most existing differentiable particle filters are within the bootstrap particle filtering framework and fail to incorporate the information from latest observations to construct better proposals. In this paper, we utilize conditional normalizing flows to construct proposal distributions for differentiable particle filters, enriching the distribution families that the proposal distributions can represent. In addition, normalizing flows are inco"},"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":"2107.00488","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-07-01T14:31:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"237e747918db2d6e1827ac708f3e4b01f226dd8cd874e920b61dd2b043d4bc17","abstract_canon_sha256":"4dbff52ed5a58c506726ef2fbc5ec6a094516409e1f4482d7ebb0578a41a1c2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:40.266748Z","signature_b64":"SbUqRAeBFtChkrOa3IGsOmsOWgp9WZBuYr65Bfx8ZJ5xk0opN79UEI9cABlfkqqhtgin+QmcJzA5EPoum4D/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6781b5c94c869cf1f0ce1b459c124747b215d6a6e3301ffc506a3df4ae15f9ca","last_reissued_at":"2026-07-05T03:30:40.266262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:40.266262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Particle Filters through Conditional Normalizing Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Hao Wen, Xiongjie Chen, Yunpeng Li","submitted_at":"2021-07-01T14:31:27Z","abstract_excerpt":"Differentiable particle filters provide a flexible mechanism to adaptively train dynamic and measurement models by learning from observed data. However, most existing differentiable particle filters are within the bootstrap particle filtering framework and fail to incorporate the information from latest observations to construct better proposals. In this paper, we utilize conditional normalizing flows to construct proposal distributions for differentiable particle filters, enriching the distribution families that the proposal distributions can represent. In addition, normalizing flows are inco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00488","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.00488/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":"2107.00488","created_at":"2026-07-05T03:30:40.266324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.00488v3","created_at":"2026-07-05T03:30:40.266324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00488","created_at":"2026-07-05T03:30:40.266324+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6A3LSKMQ2OP","created_at":"2026-07-05T03:30:40.266324+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6A3LSKMQ2OPD4GO","created_at":"2026-07-05T03:30:40.266324+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6A3LSKM","created_at":"2026-07-05T03:30:40.266324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.01339","citing_title":"Simultaneous Latent State Estimation and Latent Linear Dynamics Discovery from Image Observations","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M6A3LSKMQ2OPD4GODNCZYESHI6","json":"https://pith.science/pith/M6A3LSKMQ2OPD4GODNCZYESHI6.json","graph_json":"https://pith.science/api/pith-number/M6A3LSKMQ2OPD4GODNCZYESHI6/graph.json","events_json":"https://pith.science/api/pith-number/M6A3LSKMQ2OPD4GODNCZYESHI6/events.json","paper":"https://pith.science/paper/M6A3LSKM"},"agent_actions":{"view_html":"https://pith.science/pith/M6A3LSKMQ2OPD4GODNCZYESHI6","download_json":"https://pith.science/pith/M6A3LSKMQ2OPD4GODNCZYESHI6.json","view_paper":"https://pith.science/paper/M6A3LSKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.00488&json=true","fetch_graph":"https://pith.science/api/pith-number/M6A3LSKMQ2OPD4GODNCZYESHI6/graph.json","fetch_events":"https://pith.science/api/pith-number/M6A3LSKMQ2OPD4GODNCZYESHI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6A3LSKMQ2OPD4GODNCZYESHI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6A3LSKMQ2OPD4GODNCZYESHI6/action/storage_attestation","attest_author":"https://pith.science/pith/M6A3LSKMQ2OPD4GODNCZYESHI6/action/author_attestation","sign_citation":"https://pith.science/pith/M6A3LSKMQ2OPD4GODNCZYESHI6/action/citation_signature","submit_replication":"https://pith.science/pith/M6A3LSKMQ2OPD4GODNCZYESHI6/action/replication_record"}},"created_at":"2026-07-05T03:30:40.266324+00:00","updated_at":"2026-07-05T03:30:40.266324+00:00"}