{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7FGF6ENJRT6MEEPXARWKQDXGLV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"247b8cac77fa738d7d2effa924d448e3e2c89c2f41ae50cb6b19ee876f05ed7d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T12:41:50Z","title_canon_sha256":"e0a57cc3499b771904293ca83fa3729579bf02ae950563cec5d041e5773eedad"},"schema_version":"1.0","source":{"id":"2605.21108","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21108","created_at":"2026-05-21T01:05:37Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21108v1","created_at":"2026-05-21T01:05:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21108","created_at":"2026-05-21T01:05:37Z"},{"alias_kind":"pith_short_12","alias_value":"7FGF6ENJRT6M","created_at":"2026-05-21T01:05:37Z"},{"alias_kind":"pith_short_16","alias_value":"7FGF6ENJRT6MEEPX","created_at":"2026-05-21T01:05:37Z"},{"alias_kind":"pith_short_8","alias_value":"7FGF6ENJ","created_at":"2026-05-21T01:05:37Z"}],"graph_snapshots":[{"event_id":"sha256:9d15d8835fdf6350f9e59a9b1abe445fd592f92beaa3db3ea5f04df6b59e81c8","target":"graph","created_at":"2026-05-21T01:05:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.21108/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Latent state space systems are ubiquitous in statistical modelling, arising naturally when a time series is observed through a noisy measurement function, however training deep state space models (DSSM) at scale remains difficult. Two largely distinct strategies and literatures have developed around the training of DSSMs. Firstly, auto-encoding DSSMs train generative DSSMs by optimising a variational lower bound. Secondly, DSSMs trained by back-propagating the outputs of a classical sequential Monte Carlo algorithm (SMC). Such approaches can train DSSMs for discriminative as well as generative","authors_text":"John-Joseph Brady, Nikolas Nusken, Yunpeng Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T12:41:50Z","title":"Efficient Learning of Deep State Space Models via Importance Smoothing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21108","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e2b04fbcb5d8212f5b3f5a2af8654f4c94a37fb740ba14b1d016052728c674d6","target":"record","created_at":"2026-05-21T01:05:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"247b8cac77fa738d7d2effa924d448e3e2c89c2f41ae50cb6b19ee876f05ed7d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T12:41:50Z","title_canon_sha256":"e0a57cc3499b771904293ca83fa3729579bf02ae950563cec5d041e5773eedad"},"schema_version":"1.0","source":{"id":"2605.21108","kind":"arxiv","version":1}},"canonical_sha256":"f94c5f11a98cfcc211f7046ca80ee65d7fd91258dccce1d395785377bd7f5680","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f94c5f11a98cfcc211f7046ca80ee65d7fd91258dccce1d395785377bd7f5680","first_computed_at":"2026-05-21T01:05:37.798999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:37.798999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qHktWDHOMJn7hu1psPFYPlYMVTlVy76Z9+ned0Zsu2q02hinQuH5FZXRlRXTnq8yQBfy9RUTHI8yb5qcaS10BA==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:37.799592Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21108","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2b04fbcb5d8212f5b3f5a2af8654f4c94a37fb740ba14b1d016052728c674d6","sha256:9d15d8835fdf6350f9e59a9b1abe445fd592f92beaa3db3ea5f04df6b59e81c8"],"state_sha256":"7fd4ef436f61072e7cc2ed7c87cd35308298b94f256289ccd79520a70ab73ced"}