{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:DYG6EROHZ4SDCCGPIKZQR6LOY3","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":"d0d63e5735b2985aac9f13d4c32df855af1bd882f07fda433912394a412375ce","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-22T04:50:47Z","title_canon_sha256":"9ef724a9d97df5c23b1211facbf7bb6b1a5e95b7ced73142c4cdce17f520d30c"},"schema_version":"1.0","source":{"id":"1702.06676","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.06676","created_at":"2026-05-18T00:49:01Z"},{"alias_kind":"arxiv_version","alias_value":"1702.06676v2","created_at":"2026-05-18T00:49:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.06676","created_at":"2026-05-18T00:49:01Z"},{"alias_kind":"pith_short_12","alias_value":"DYG6EROHZ4SD","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"DYG6EROHZ4SDCCGP","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"DYG6EROH","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:012a0bf8910b497487c82538128dc417cc4b2b64351dd3b4cfd0f74367244517","target":"graph","created_at":"2026-05-18T00:49:01Z","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 by which a generative model learning the joint distribution between actions and future states can be used to automatically infer a control scheme for any desired reward function, which may be altered on the fly without retraining the model. In this method, the problem of action selection is reduced to one of gradient descent on the latent space of the generative model, with the model itself providing the means of evaluating outcomes and finding the gradient, much like how the reward network in Deep Q-Networks (DQN) provides gradient information for the action generator. U","authors_text":"Nicholas Guttenberg, Ryota Kanai, Yen Yu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-22T04:50:47Z","title":"Counterfactual Control for Free from Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.06676","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":"sha256:3b202d758feeaa20d6a708bef1b732cd45b369ac238f582f5cea4988e00b887e","target":"record","created_at":"2026-05-18T00:49:01Z","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":"d0d63e5735b2985aac9f13d4c32df855af1bd882f07fda433912394a412375ce","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-22T04:50:47Z","title_canon_sha256":"9ef724a9d97df5c23b1211facbf7bb6b1a5e95b7ced73142c4cdce17f520d30c"},"schema_version":"1.0","source":{"id":"1702.06676","kind":"arxiv","version":2}},"canonical_sha256":"1e0de245c7cf243108cf42b308f96ec6d1266b64ef5d37dddf940a9d8f991d48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e0de245c7cf243108cf42b308f96ec6d1266b64ef5d37dddf940a9d8f991d48","first_computed_at":"2026-05-18T00:49:01.983341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:49:01.983341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IhjT4FpmP2Uu0f1wtcavlzFsL3/71huapygXXMNBPvaxfVc9qiWd9enItIP5QENJobYWhUWxKKfYOb2U9lmgAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:49:01.984056Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.06676","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b202d758feeaa20d6a708bef1b732cd45b369ac238f582f5cea4988e00b887e","sha256:012a0bf8910b497487c82538128dc417cc4b2b64351dd3b4cfd0f74367244517"],"state_sha256":"0dd925c0f0dd46341981d1f0068ba90fc3882d591f3407a0fb3017baaf941e4e"}