{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:NTUK22NDO6PHQM36L3P2P5ENUQ","short_pith_number":"pith:NTUK22ND","canonical_record":{"source":{"id":"1703.04070","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-12T04:59:15Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"a7b2a3bdb7270900ae60dcf68b5127207470b56899b5f16b771b3831c4cb9ad5","abstract_canon_sha256":"ede97811747c36f85a3b26e1978f0955e816d8dc3e34befc5603a12d011b3f74"},"schema_version":"1.0"},"canonical_sha256":"6ce8ad69a3779e78337e5edfa7f48da435660dc8cb3199e8f88ed1e699e11df3","source":{"kind":"arxiv","id":"1703.04070","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.04070","created_at":"2026-05-18T00:40:23Z"},{"alias_kind":"arxiv_version","alias_value":"1703.04070v2","created_at":"2026-05-18T00:40:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04070","created_at":"2026-05-18T00:40:23Z"},{"alias_kind":"pith_short_12","alias_value":"NTUK22NDO6PH","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"NTUK22NDO6PHQM36","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"NTUK22ND","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:NTUK22NDO6PHQM36L3P2P5ENUQ","target":"record","payload":{"canonical_record":{"source":{"id":"1703.04070","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-12T04:59:15Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"a7b2a3bdb7270900ae60dcf68b5127207470b56899b5f16b771b3831c4cb9ad5","abstract_canon_sha256":"ede97811747c36f85a3b26e1978f0955e816d8dc3e34befc5603a12d011b3f74"},"schema_version":"1.0"},"canonical_sha256":"6ce8ad69a3779e78337e5edfa7f48da435660dc8cb3199e8f88ed1e699e11df3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:23.861368Z","signature_b64":"GpOnP87RxlIBxU/MUss85/lxvxHcASJC0YLJ9GpxxfxIjVA8keddNeE+8Y3mmeei1oNeCOXL5ZJg9CNZmRgHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ce8ad69a3779e78337e5edfa7f48da435660dc8cb3199e8f88ed1e699e11df3","last_reissued_at":"2026-05-18T00:40:23.860831Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:23.860831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.04070","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":"2026-05-18T00:40:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S15y+5mQrzx7wCTqQX1kkEVK9rNitnf1PQGnGK9dP42pG9uJ5iAt7XCGcQjPIPOxj8uI3rEI6Blo3ZkIHkvzDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T07:04:34.560725Z"},"content_sha256":"0d7280c63f15529bf8e1ce08b92d3b89167f7faf12f3f3b0093ca081171b93b5","schema_version":"1.0","event_id":"sha256:0d7280c63f15529bf8e1ce08b92d3b89167f7faf12f3f3b0093ca081171b93b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:NTUK22NDO6PHQM36L3P2P5ENUQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prediction and Control with Temporal Segment Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Igor Mordatch, Nikhil Mishra, Pieter Abbeel","submitted_at":"2017-03-12T04:59:15Z","abstract_excerpt":"We introduce a method for learning the dynamics of complex nonlinear systems based on deep generative models over temporal segments of states and actions. Unlike dynamics models that operate over individual discrete timesteps, we learn the distribution over future state trajectories conditioned on past state, past action, and planned future action trajectories, as well as a latent prior over action trajectories. Our approach is based on convolutional autoregressive models and variational autoencoders. It makes stable and accurate predictions over long horizons for complex, stochastic systems, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.04070","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":""},"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":"2026-05-18T00:40:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xNC1s/FuIokNI1hyVaOzqWNReaqrTQbRDqnDU/K9aYc5NzOrIbCpWaqCjt0SA9NYcbfWjF3WpJJr3Y20nTBkCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T07:04:34.561483Z"},"content_sha256":"13d6108a37c5875b9ba85a57b5d5b8a389e916230ff6eb3db444afe019d80544","schema_version":"1.0","event_id":"sha256:13d6108a37c5875b9ba85a57b5d5b8a389e916230ff6eb3db444afe019d80544"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NTUK22NDO6PHQM36L3P2P5ENUQ/bundle.json","state_url":"https://pith.science/pith/NTUK22NDO6PHQM36L3P2P5ENUQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NTUK22NDO6PHQM36L3P2P5ENUQ/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":"2026-06-10T07:04:34Z","links":{"resolver":"https://pith.science/pith/NTUK22NDO6PHQM36L3P2P5ENUQ","bundle":"https://pith.science/pith/NTUK22NDO6PHQM36L3P2P5ENUQ/bundle.json","state":"https://pith.science/pith/NTUK22NDO6PHQM36L3P2P5ENUQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NTUK22NDO6PHQM36L3P2P5ENUQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:NTUK22NDO6PHQM36L3P2P5ENUQ","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":"ede97811747c36f85a3b26e1978f0955e816d8dc3e34befc5603a12d011b3f74","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-12T04:59:15Z","title_canon_sha256":"a7b2a3bdb7270900ae60dcf68b5127207470b56899b5f16b771b3831c4cb9ad5"},"schema_version":"1.0","source":{"id":"1703.04070","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.04070","created_at":"2026-05-18T00:40:23Z"},{"alias_kind":"arxiv_version","alias_value":"1703.04070v2","created_at":"2026-05-18T00:40:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04070","created_at":"2026-05-18T00:40:23Z"},{"alias_kind":"pith_short_12","alias_value":"NTUK22NDO6PH","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"NTUK22NDO6PHQM36","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"NTUK22ND","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:13d6108a37c5875b9ba85a57b5d5b8a389e916230ff6eb3db444afe019d80544","target":"graph","created_at":"2026-05-18T00:40:23Z","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":"We introduce a method for learning the dynamics of complex nonlinear systems based on deep generative models over temporal segments of states and actions. Unlike dynamics models that operate over individual discrete timesteps, we learn the distribution over future state trajectories conditioned on past state, past action, and planned future action trajectories, as well as a latent prior over action trajectories. Our approach is based on convolutional autoregressive models and variational autoencoders. It makes stable and accurate predictions over long horizons for complex, stochastic systems, ","authors_text":"Igor Mordatch, Nikhil Mishra, Pieter Abbeel","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-12T04:59:15Z","title":"Prediction and Control with Temporal Segment Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.04070","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":"sha256:0d7280c63f15529bf8e1ce08b92d3b89167f7faf12f3f3b0093ca081171b93b5","target":"record","created_at":"2026-05-18T00:40:23Z","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":"ede97811747c36f85a3b26e1978f0955e816d8dc3e34befc5603a12d011b3f74","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-12T04:59:15Z","title_canon_sha256":"a7b2a3bdb7270900ae60dcf68b5127207470b56899b5f16b771b3831c4cb9ad5"},"schema_version":"1.0","source":{"id":"1703.04070","kind":"arxiv","version":2}},"canonical_sha256":"6ce8ad69a3779e78337e5edfa7f48da435660dc8cb3199e8f88ed1e699e11df3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ce8ad69a3779e78337e5edfa7f48da435660dc8cb3199e8f88ed1e699e11df3","first_computed_at":"2026-05-18T00:40:23.860831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:23.860831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GpOnP87RxlIBxU/MUss85/lxvxHcASJC0YLJ9GpxxfxIjVA8keddNeE+8Y3mmeei1oNeCOXL5ZJg9CNZmRgHDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:23.861368Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.04070","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d7280c63f15529bf8e1ce08b92d3b89167f7faf12f3f3b0093ca081171b93b5","sha256:13d6108a37c5875b9ba85a57b5d5b8a389e916230ff6eb3db444afe019d80544"],"state_sha256":"2c4531036bed1c5db13f7391bd5c1491671c013e434c8db9e354e21926dd39e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"smJx2E/EUG0i4VDmS5kctXhv3ND78VkGn61kyrV8ySqiAu9ZgOX7Us+ckRh/7Kib7Dj+AkrzX9k3s8WcmQdQCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T07:04:34.564626Z","bundle_sha256":"0b259c62c62d66c602e6eec4efcbdfa6dffe88554a1d62af60a0c2c1e4c844ef"}}