{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BG75XWBPN2OEXNG2FNGLJPMUTJ","short_pith_number":"pith:BG75XWBP","canonical_record":{"source":{"id":"2602.23050","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-26T14:35:45Z","cross_cats_sorted":[],"title_canon_sha256":"3f1c67df284d31d3fde07e1603dac7470593ade01cf346e912d1d635c58de052","abstract_canon_sha256":"d62ce93f4c0c7c31e8f2b8a9cb3fb599371a192d1472f08344d4ebbfea3ad772"},"schema_version":"1.0"},"canonical_sha256":"09bfdbd82f6e9c4bb4da2b4cb4bd949a4edce4dec394e0bbd920d25e38fd4174","source":{"kind":"arxiv","id":"2602.23050","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.23050","created_at":"2026-07-31T01:33:17Z"},{"alias_kind":"arxiv_version","alias_value":"2602.23050v2","created_at":"2026-07-31T01:33:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.23050","created_at":"2026-07-31T01:33:17Z"},{"alias_kind":"pith_short_12","alias_value":"BG75XWBPN2OE","created_at":"2026-07-31T01:33:17Z"},{"alias_kind":"pith_short_16","alias_value":"BG75XWBPN2OEXNG2","created_at":"2026-07-31T01:33:17Z"},{"alias_kind":"pith_short_8","alias_value":"BG75XWBP","created_at":"2026-07-31T01:33:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BG75XWBPN2OEXNG2FNGLJPMUTJ","target":"record","payload":{"canonical_record":{"source":{"id":"2602.23050","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-26T14:35:45Z","cross_cats_sorted":[],"title_canon_sha256":"3f1c67df284d31d3fde07e1603dac7470593ade01cf346e912d1d635c58de052","abstract_canon_sha256":"d62ce93f4c0c7c31e8f2b8a9cb3fb599371a192d1472f08344d4ebbfea3ad772"},"schema_version":"1.0"},"canonical_sha256":"09bfdbd82f6e9c4bb4da2b4cb4bd949a4edce4dec394e0bbd920d25e38fd4174","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09bfdbd82f6e9c4bb4da2b4cb4bd949a4edce4dec394e0bbd920d25e38fd4174","last_reissued_at":"2026-07-31T01:33:17.858719Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:33:17.858719Z"},"source_kind":"arxiv","source_id":"2602.23050","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:33:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pYWSBiVhtarYJhmjTVFuAJCAzS/tFrAsLXHi8fZ/LHEY5fAU/dOOyc/tQ++DGvyVtMSa47t5+N/Sm3JbU5+cCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T16:10:44.011833Z"},"content_sha256":"3b5770220d774bbe604cd03e0a3edd5c2748aad74151b90ca0e29611e196d65b","schema_version":"1.0","event_id":"sha256:3b5770220d774bbe604cd03e0a3edd5c2748aad74151b90ca0e29611e196d65b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BG75XWBPN2OEXNG2FNGLJPMUTJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Latent Matters: Learning Deep State-Space Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexej Klushyn, Botond Cseke, Maximilian Soelch, Patrick van der Smagt, Richard Kurle","submitted_at":"2026-02-26T14:35:45Z","abstract_excerpt":"Deep state-space models (DSSMs) enable temporal predictions by learning the underlying dynamics of observed sequence data. They are often trained by maximising the evidence lower bound. However, as we show, this does not ensure the model actually learns the underlying dynamics. We therefore propose a constrained optimisation framework as a general approach for training DSSMs. Building upon this, we introduce the extended Kalman VAE (EKVAE), which combines amortised variational inference with classic Bayesian filtering/smoothing to model dynamics more accurately than RNN-based DSSMs. Our result"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.23050","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/2602.23050/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:33:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ILvZtaOHeQ0BNMWdlgaj8rDm+Vq3URfXgdvlzJEZ9L/9mfr9piezCh5q0pRxugGAZQpFE6y1HOJw6CZmmtNzAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T16:10:44.012457Z"},"content_sha256":"c3753a5b4f21ef960414b25ccd36fc81b51ff626353d1a96c4fb7305216d2249","schema_version":"1.0","event_id":"sha256:c3753a5b4f21ef960414b25ccd36fc81b51ff626353d1a96c4fb7305216d2249"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BG75XWBPN2OEXNG2FNGLJPMUTJ/bundle.json","state_url":"https://pith.science/pith/BG75XWBPN2OEXNG2FNGLJPMUTJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BG75XWBPN2OEXNG2FNGLJPMUTJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-23T16:10:44Z","links":{"resolver":"https://pith.science/pith/BG75XWBPN2OEXNG2FNGLJPMUTJ","bundle":"https://pith.science/pith/BG75XWBPN2OEXNG2FNGLJPMUTJ/bundle.json","state":"https://pith.science/pith/BG75XWBPN2OEXNG2FNGLJPMUTJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BG75XWBPN2OEXNG2FNGLJPMUTJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BG75XWBPN2OEXNG2FNGLJPMUTJ","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":"d62ce93f4c0c7c31e8f2b8a9cb3fb599371a192d1472f08344d4ebbfea3ad772","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-26T14:35:45Z","title_canon_sha256":"3f1c67df284d31d3fde07e1603dac7470593ade01cf346e912d1d635c58de052"},"schema_version":"1.0","source":{"id":"2602.23050","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.23050","created_at":"2026-07-31T01:33:17Z"},{"alias_kind":"arxiv_version","alias_value":"2602.23050v2","created_at":"2026-07-31T01:33:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.23050","created_at":"2026-07-31T01:33:17Z"},{"alias_kind":"pith_short_12","alias_value":"BG75XWBPN2OE","created_at":"2026-07-31T01:33:17Z"},{"alias_kind":"pith_short_16","alias_value":"BG75XWBPN2OEXNG2","created_at":"2026-07-31T01:33:17Z"},{"alias_kind":"pith_short_8","alias_value":"BG75XWBP","created_at":"2026-07-31T01:33:17Z"}],"graph_snapshots":[{"event_id":"sha256:c3753a5b4f21ef960414b25ccd36fc81b51ff626353d1a96c4fb7305216d2249","target":"graph","created_at":"2026-07-31T01:33:17Z","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/2602.23050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep state-space models (DSSMs) enable temporal predictions by learning the underlying dynamics of observed sequence data. They are often trained by maximising the evidence lower bound. However, as we show, this does not ensure the model actually learns the underlying dynamics. We therefore propose a constrained optimisation framework as a general approach for training DSSMs. Building upon this, we introduce the extended Kalman VAE (EKVAE), which combines amortised variational inference with classic Bayesian filtering/smoothing to model dynamics more accurately than RNN-based DSSMs. Our result","authors_text":"Alexej Klushyn, Botond Cseke, Maximilian Soelch, Patrick van der Smagt, Richard Kurle","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-26T14:35:45Z","title":"Latent Matters: Learning Deep State-Space Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.23050","kind":"arxiv","version":2},"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":"sha256:3b5770220d774bbe604cd03e0a3edd5c2748aad74151b90ca0e29611e196d65b","target":"record","created_at":"2026-07-31T01:33:17Z","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":"d62ce93f4c0c7c31e8f2b8a9cb3fb599371a192d1472f08344d4ebbfea3ad772","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-26T14:35:45Z","title_canon_sha256":"3f1c67df284d31d3fde07e1603dac7470593ade01cf346e912d1d635c58de052"},"schema_version":"1.0","source":{"id":"2602.23050","kind":"arxiv","version":2}},"canonical_sha256":"09bfdbd82f6e9c4bb4da2b4cb4bd949a4edce4dec394e0bbd920d25e38fd4174","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09bfdbd82f6e9c4bb4da2b4cb4bd949a4edce4dec394e0bbd920d25e38fd4174","first_computed_at":"2026-07-31T01:33:17.858719Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:33:17.858719Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2602.23050","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b5770220d774bbe604cd03e0a3edd5c2748aad74151b90ca0e29611e196d65b","sha256:c3753a5b4f21ef960414b25ccd36fc81b51ff626353d1a96c4fb7305216d2249"],"state_sha256":"c3a0ee0057fd277ac286c09c5379264eee530ebeb4b3a89ca50212f6403d4dd7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Cv2eJtSxeSJzrE/r5tMF8xG8qi0REyvOWpdsSbdhDCyaO0ML2BEMYn+4htgFXAdKqs8ZYompnUrXCXkEuMGCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T16:10:44.016974Z","bundle_sha256":"15004a977e089352baba3a7283c848447b7c6204f577530defcbfd84d6a85f66"}}