{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:BKH6M6FTOZ3GLH5YX7CZQQFJ6S","short_pith_number":"pith:BKH6M6FT","canonical_record":{"source":{"id":"1502.02251","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-02-08T13:57:59Z","cross_cats_sorted":["cs.LG","cs.RO","cs.SY"],"title_canon_sha256":"c7b487b5e9ff08fcd8e859caa26841e9fe343ae3fad89f0b0c92cd19e7d83a90","abstract_canon_sha256":"cff366bd802d8570511f09907ecc98114e7b1da230dd1b85f03a34d15a5cb376"},"schema_version":"1.0"},"canonical_sha256":"0a8fe678b37676659fb8bfc59840a9f49669d742298bb7d78cfe8c5bdb9f5df6","source":{"kind":"arxiv","id":"1502.02251","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.02251","created_at":"2026-05-18T01:44:11Z"},{"alias_kind":"arxiv_version","alias_value":"1502.02251v3","created_at":"2026-05-18T01:44:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.02251","created_at":"2026-05-18T01:44:11Z"},{"alias_kind":"pith_short_12","alias_value":"BKH6M6FTOZ3G","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"BKH6M6FTOZ3GLH5Y","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"BKH6M6FT","created_at":"2026-05-18T12:29:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:BKH6M6FTOZ3GLH5YX7CZQQFJ6S","target":"record","payload":{"canonical_record":{"source":{"id":"1502.02251","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-02-08T13:57:59Z","cross_cats_sorted":["cs.LG","cs.RO","cs.SY"],"title_canon_sha256":"c7b487b5e9ff08fcd8e859caa26841e9fe343ae3fad89f0b0c92cd19e7d83a90","abstract_canon_sha256":"cff366bd802d8570511f09907ecc98114e7b1da230dd1b85f03a34d15a5cb376"},"schema_version":"1.0"},"canonical_sha256":"0a8fe678b37676659fb8bfc59840a9f49669d742298bb7d78cfe8c5bdb9f5df6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:44:11.383849Z","signature_b64":"XwFj5lqeEmXxRdkrqaeXVNKgTsSwp9kI9xDqynlBewRIRZeVjWYGFdECTV1M433tpyLU9EURZZKC0e89qk0gDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a8fe678b37676659fb8bfc59840a9f49669d742298bb7d78cfe8c5bdb9f5df6","last_reissued_at":"2026-05-18T01:44:11.383236Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:44:11.383236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1502.02251","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:44:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GLZ+WvjD7NJSui+FWjyKmDpdBKgSrhhAIKQ/QolD35MzzKQjlqAHSSbdvKTKqkeYyVzfSo4KtMXpVeRvutqhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:02:05.016292Z"},"content_sha256":"62b187cb0c098a118d139509fe86a2a5eecba414bec8a8526343e0320dea8c73","schema_version":"1.0","event_id":"sha256:62b187cb0c098a118d139509fe86a2a5eecba414bec8a8526343e0320dea8c73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:BKH6M6FTOZ3GLH5YX7CZQQFJ6S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Pixels to Torques: Policy Learning with Deep Dynamical Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO","cs.SY"],"primary_cat":"stat.ML","authors_text":"Marc Peter Deisenroth, Niklas Wahlstr\\\"om, Thomas B. Sch\\\"on","submitted_at":"2015-02-08T13:57:59Z","abstract_excerpt":"Data-efficient learning in continuous state-action spaces using very high-dimensional observations remains a key challenge in developing fully autonomous systems. In this paper, we consider one instance of this challenge, the pixels to torques problem, where an agent must learn a closed-loop control policy from pixel information only. We introduce a data-efficient, model-based reinforcement learning algorithm that learns such a closed-loop policy directly from pixel information. The key ingredient is a deep dynamical model that uses deep auto-encoders to learn a low-dimensional embedding of im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.02251","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":""},"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":"2026-05-18T01:44:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oKuuPxORzZUAQ8KePFlaOsjhCyUE0gGt++o5xkvE028LWwjNKVc7JvyD9x1DBoz7u8ic9tr0MBwxb8VhTQvzCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:02:05.016902Z"},"content_sha256":"4551ccca6e7d45e060094305fbd555a94e8614cc4f68c0367fe0706e00c12522","schema_version":"1.0","event_id":"sha256:4551ccca6e7d45e060094305fbd555a94e8614cc4f68c0367fe0706e00c12522"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BKH6M6FTOZ3GLH5YX7CZQQFJ6S/bundle.json","state_url":"https://pith.science/pith/BKH6M6FTOZ3GLH5YX7CZQQFJ6S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BKH6M6FTOZ3GLH5YX7CZQQFJ6S/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":"2026-06-07T06:02:05Z","links":{"resolver":"https://pith.science/pith/BKH6M6FTOZ3GLH5YX7CZQQFJ6S","bundle":"https://pith.science/pith/BKH6M6FTOZ3GLH5YX7CZQQFJ6S/bundle.json","state":"https://pith.science/pith/BKH6M6FTOZ3GLH5YX7CZQQFJ6S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BKH6M6FTOZ3GLH5YX7CZQQFJ6S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:BKH6M6FTOZ3GLH5YX7CZQQFJ6S","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":"cff366bd802d8570511f09907ecc98114e7b1da230dd1b85f03a34d15a5cb376","cross_cats_sorted":["cs.LG","cs.RO","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-02-08T13:57:59Z","title_canon_sha256":"c7b487b5e9ff08fcd8e859caa26841e9fe343ae3fad89f0b0c92cd19e7d83a90"},"schema_version":"1.0","source":{"id":"1502.02251","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.02251","created_at":"2026-05-18T01:44:11Z"},{"alias_kind":"arxiv_version","alias_value":"1502.02251v3","created_at":"2026-05-18T01:44:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.02251","created_at":"2026-05-18T01:44:11Z"},{"alias_kind":"pith_short_12","alias_value":"BKH6M6FTOZ3G","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"BKH6M6FTOZ3GLH5Y","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"BKH6M6FT","created_at":"2026-05-18T12:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:4551ccca6e7d45e060094305fbd555a94e8614cc4f68c0367fe0706e00c12522","target":"graph","created_at":"2026-05-18T01:44:11Z","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"},"paper":{"abstract_excerpt":"Data-efficient learning in continuous state-action spaces using very high-dimensional observations remains a key challenge in developing fully autonomous systems. In this paper, we consider one instance of this challenge, the pixels to torques problem, where an agent must learn a closed-loop control policy from pixel information only. We introduce a data-efficient, model-based reinforcement learning algorithm that learns such a closed-loop policy directly from pixel information. The key ingredient is a deep dynamical model that uses deep auto-encoders to learn a low-dimensional embedding of im","authors_text":"Marc Peter Deisenroth, Niklas Wahlstr\\\"om, Thomas B. Sch\\\"on","cross_cats":["cs.LG","cs.RO","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-02-08T13:57:59Z","title":"From Pixels to Torques: Policy Learning with Deep Dynamical Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.02251","kind":"arxiv","version":3},"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":"sha256:62b187cb0c098a118d139509fe86a2a5eecba414bec8a8526343e0320dea8c73","target":"record","created_at":"2026-05-18T01:44:11Z","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":"cff366bd802d8570511f09907ecc98114e7b1da230dd1b85f03a34d15a5cb376","cross_cats_sorted":["cs.LG","cs.RO","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-02-08T13:57:59Z","title_canon_sha256":"c7b487b5e9ff08fcd8e859caa26841e9fe343ae3fad89f0b0c92cd19e7d83a90"},"schema_version":"1.0","source":{"id":"1502.02251","kind":"arxiv","version":3}},"canonical_sha256":"0a8fe678b37676659fb8bfc59840a9f49669d742298bb7d78cfe8c5bdb9f5df6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a8fe678b37676659fb8bfc59840a9f49669d742298bb7d78cfe8c5bdb9f5df6","first_computed_at":"2026-05-18T01:44:11.383236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:44:11.383236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XwFj5lqeEmXxRdkrqaeXVNKgTsSwp9kI9xDqynlBewRIRZeVjWYGFdECTV1M433tpyLU9EURZZKC0e89qk0gDw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:44:11.383849Z","signed_message":"canonical_sha256_bytes"},"source_id":"1502.02251","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62b187cb0c098a118d139509fe86a2a5eecba414bec8a8526343e0320dea8c73","sha256:4551ccca6e7d45e060094305fbd555a94e8614cc4f68c0367fe0706e00c12522"],"state_sha256":"eaa33a0d2bf16cf4c923248beb92184bba61c3d046d57c4f5cc5243bd2ffcc19"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5WIGcxBM2AAX9ALZWfHcUB3hfA/jV4nJKVm/doRZHceEThNaCN1DN3yunHfoc3WNitTje4Rh2xFfm62ZakG8Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T06:02:05.020130Z","bundle_sha256":"2fdd7abeb2f02570f772f9af99f3d233c65a34a727d9de310575f547200057fb"}}