{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6CDLGOUAD2IQNB7ED2SQ5WV4YO","short_pith_number":"pith:6CDLGOUA","schema_version":"1.0","canonical_sha256":"f086b33a801e910687e41ea50edabcc393a8c7aa1331acc350b301d78d7124c6","source":{"kind":"arxiv","id":"2107.13349","version":3},"attestation_state":"computed","paper":{"title":"Self-Supervised Inference in State-Space Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Ruhe, Patrick Forr\\'e","submitted_at":"2021-07-28T13:26:14Z","abstract_excerpt":"We perform approximate inference in state-space models with nonlinear state transitions. Without parameterizing a generative model, we apply Bayesian update formulas using a local linearity approximation parameterized by neural networks. This comes accompanied by a maximum likelihood objective that requires no supervision via uncorrupt observations or ground truth latent states. The optimization backpropagates through a recursion similar to the classical Kalman filter and smoother. Additionally, using an approximate conditional independence, we can perform smoothing without having to parameter"},"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":"2107.13349","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-28T13:26:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9db2cc01cf30e282b3079d7665ff918c1b700fdef3bf37347e661771d66eb9c1","abstract_canon_sha256":"bb8f61c9324aff21a03f898c03f206ff78f8d9bc26717d7c476d1802ff2450a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:51:08.907624Z","signature_b64":"3rqWSCDrDbxjGOr4T8ReOK2mr7KR5c126UZj+EiO0XNVB3r66oK4oFusPofndcplwqLDzM9Z17XPLUFxdBHqDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f086b33a801e910687e41ea50edabcc393a8c7aa1331acc350b301d78d7124c6","last_reissued_at":"2026-07-05T03:51:08.907115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:51:08.907115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Inference in State-Space Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Ruhe, Patrick Forr\\'e","submitted_at":"2021-07-28T13:26:14Z","abstract_excerpt":"We perform approximate inference in state-space models with nonlinear state transitions. Without parameterizing a generative model, we apply Bayesian update formulas using a local linearity approximation parameterized by neural networks. This comes accompanied by a maximum likelihood objective that requires no supervision via uncorrupt observations or ground truth latent states. The optimization backpropagates through a recursion similar to the classical Kalman filter and smoother. Additionally, using an approximate conditional independence, we can perform smoothing without having to parameter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.13349","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/2107.13349/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":"2107.13349","created_at":"2026-07-05T03:51:08.907181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.13349v3","created_at":"2026-07-05T03:51:08.907181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.13349","created_at":"2026-07-05T03:51:08.907181+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CDLGOUAD2IQ","created_at":"2026-07-05T03:51:08.907181+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CDLGOUAD2IQNB7E","created_at":"2026-07-05T03:51:08.907181+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CDLGOUA","created_at":"2026-07-05T03:51:08.907181+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CDLGOUAD2IQNB7ED2SQ5WV4YO","json":"https://pith.science/pith/6CDLGOUAD2IQNB7ED2SQ5WV4YO.json","graph_json":"https://pith.science/api/pith-number/6CDLGOUAD2IQNB7ED2SQ5WV4YO/graph.json","events_json":"https://pith.science/api/pith-number/6CDLGOUAD2IQNB7ED2SQ5WV4YO/events.json","paper":"https://pith.science/paper/6CDLGOUA"},"agent_actions":{"view_html":"https://pith.science/pith/6CDLGOUAD2IQNB7ED2SQ5WV4YO","download_json":"https://pith.science/pith/6CDLGOUAD2IQNB7ED2SQ5WV4YO.json","view_paper":"https://pith.science/paper/6CDLGOUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.13349&json=true","fetch_graph":"https://pith.science/api/pith-number/6CDLGOUAD2IQNB7ED2SQ5WV4YO/graph.json","fetch_events":"https://pith.science/api/pith-number/6CDLGOUAD2IQNB7ED2SQ5WV4YO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CDLGOUAD2IQNB7ED2SQ5WV4YO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CDLGOUAD2IQNB7ED2SQ5WV4YO/action/storage_attestation","attest_author":"https://pith.science/pith/6CDLGOUAD2IQNB7ED2SQ5WV4YO/action/author_attestation","sign_citation":"https://pith.science/pith/6CDLGOUAD2IQNB7ED2SQ5WV4YO/action/citation_signature","submit_replication":"https://pith.science/pith/6CDLGOUAD2IQNB7ED2SQ5WV4YO/action/replication_record"}},"created_at":"2026-07-05T03:51:08.907181+00:00","updated_at":"2026-07-05T03:51:08.907181+00:00"}