{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:GZHKW2TSW3WVHS5QMAUYKCRSO5","short_pith_number":"pith:GZHKW2TS","canonical_record":{"source":{"id":"1807.09341","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-24T20:46:05Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE","cs.RO","stat.ML"],"title_canon_sha256":"ae5c2c45294dcf0c2e15c44b656a23a0b77199528892f5755b4cf80168b915fe","abstract_canon_sha256":"2a00d4103ed2a82dbb7c5875c936588a583eb2be62f7a0e3c3ae802868d4f3ec"},"schema_version":"1.0"},"canonical_sha256":"364eab6a72b6ed53cbb06029850a32776a9a350a9203d6a37482bdb22802d973","source":{"kind":"arxiv","id":"1807.09341","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.09341","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"arxiv_version","alias_value":"1807.09341v1","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09341","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"pith_short_12","alias_value":"GZHKW2TSW3WV","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GZHKW2TSW3WVHS5Q","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GZHKW2TS","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:GZHKW2TSW3WVHS5QMAUYKCRSO5","target":"record","payload":{"canonical_record":{"source":{"id":"1807.09341","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-24T20:46:05Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE","cs.RO","stat.ML"],"title_canon_sha256":"ae5c2c45294dcf0c2e15c44b656a23a0b77199528892f5755b4cf80168b915fe","abstract_canon_sha256":"2a00d4103ed2a82dbb7c5875c936588a583eb2be62f7a0e3c3ae802868d4f3ec"},"schema_version":"1.0"},"canonical_sha256":"364eab6a72b6ed53cbb06029850a32776a9a350a9203d6a37482bdb22802d973","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:46.640700Z","signature_b64":"R0chndqXqkijWgkbvUdvK7kevEG1kWTsUtDL+P3piKSvVFzWnSmCzjKCjEv1koNZeJ8kTs8VHZxwH3Wt8WSgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"364eab6a72b6ed53cbb06029850a32776a9a350a9203d6a37482bdb22802d973","last_reissued_at":"2026-05-18T00:09:46.640044Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:46.640044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.09341","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:09:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YIlO4DYQoshgPc5KCsuhbXI79n0Cy3rVozZ0Z6GVs1spwx52mmJqO8cIAiRcRyvurFN6sTWH9aIwuyw4pzo4CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T00:11:49.480470Z"},"content_sha256":"984da80fd42ad985d7453065cbaf103a65ab265e29bd72ab0641acd4975360c4","schema_version":"1.0","event_id":"sha256:984da80fd42ad985d7453065cbaf103a65ab265e29bd72ab0641acd4975360c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:GZHKW2TSW3WVHS5QMAUYKCRSO5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Plannable Representations with Causal InfoGAN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aviv Tamar, Ge Yang, Pieter Abbeel, Stuart Russell, Thanard Kurutach","submitted_at":"2018-07-24T20:46:05Z","abstract_excerpt":"In recent years, deep generative models have been shown to 'imagine' convincing high-dimensional observations such as images, audio, and even video, learning directly from raw data. In this work, we ask how to imagine goal-directed visual plans -- a plausible sequence of observations that transition a dynamical system from its current configuration to a desired goal state, which can later be used as a reference trajectory for control. We focus on systems with high-dimensional observations, such as images, and propose an approach that naturally combines representation learning and planning. Our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09341","kind":"arxiv","version":1},"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":"2026-05-18T00:09:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ji8+13LbjYZxVV3re4IWfIIdQrjq84sy2PujjEUuBzcoyPPQNOwxhJqI2U5TUamPWsCPjY/UXwmoKorSSQ8XDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T00:11:49.481144Z"},"content_sha256":"d7bc0805c860cf119c5ac5b005dc57e907eedd78df19e7c016cdf5bfb152acc2","schema_version":"1.0","event_id":"sha256:d7bc0805c860cf119c5ac5b005dc57e907eedd78df19e7c016cdf5bfb152acc2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GZHKW2TSW3WVHS5QMAUYKCRSO5/bundle.json","state_url":"https://pith.science/pith/GZHKW2TSW3WVHS5QMAUYKCRSO5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GZHKW2TSW3WVHS5QMAUYKCRSO5/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":"2026-06-11T00:11:49Z","links":{"resolver":"https://pith.science/pith/GZHKW2TSW3WVHS5QMAUYKCRSO5","bundle":"https://pith.science/pith/GZHKW2TSW3WVHS5QMAUYKCRSO5/bundle.json","state":"https://pith.science/pith/GZHKW2TSW3WVHS5QMAUYKCRSO5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GZHKW2TSW3WVHS5QMAUYKCRSO5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GZHKW2TSW3WVHS5QMAUYKCRSO5","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":"2a00d4103ed2a82dbb7c5875c936588a583eb2be62f7a0e3c3ae802868d4f3ec","cross_cats_sorted":["cs.AI","cs.CV","cs.NE","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-24T20:46:05Z","title_canon_sha256":"ae5c2c45294dcf0c2e15c44b656a23a0b77199528892f5755b4cf80168b915fe"},"schema_version":"1.0","source":{"id":"1807.09341","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.09341","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"arxiv_version","alias_value":"1807.09341v1","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09341","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"pith_short_12","alias_value":"GZHKW2TSW3WV","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GZHKW2TSW3WVHS5Q","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GZHKW2TS","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:d7bc0805c860cf119c5ac5b005dc57e907eedd78df19e7c016cdf5bfb152acc2","target":"graph","created_at":"2026-05-18T00:09:46Z","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":"In recent years, deep generative models have been shown to 'imagine' convincing high-dimensional observations such as images, audio, and even video, learning directly from raw data. In this work, we ask how to imagine goal-directed visual plans -- a plausible sequence of observations that transition a dynamical system from its current configuration to a desired goal state, which can later be used as a reference trajectory for control. We focus on systems with high-dimensional observations, such as images, and propose an approach that naturally combines representation learning and planning. Our","authors_text":"Aviv Tamar, Ge Yang, Pieter Abbeel, Stuart Russell, Thanard Kurutach","cross_cats":["cs.AI","cs.CV","cs.NE","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-24T20:46:05Z","title":"Learning Plannable Representations with Causal InfoGAN"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09341","kind":"arxiv","version":1},"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":"sha256:984da80fd42ad985d7453065cbaf103a65ab265e29bd72ab0641acd4975360c4","target":"record","created_at":"2026-05-18T00:09:46Z","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":"2a00d4103ed2a82dbb7c5875c936588a583eb2be62f7a0e3c3ae802868d4f3ec","cross_cats_sorted":["cs.AI","cs.CV","cs.NE","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-24T20:46:05Z","title_canon_sha256":"ae5c2c45294dcf0c2e15c44b656a23a0b77199528892f5755b4cf80168b915fe"},"schema_version":"1.0","source":{"id":"1807.09341","kind":"arxiv","version":1}},"canonical_sha256":"364eab6a72b6ed53cbb06029850a32776a9a350a9203d6a37482bdb22802d973","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"364eab6a72b6ed53cbb06029850a32776a9a350a9203d6a37482bdb22802d973","first_computed_at":"2026-05-18T00:09:46.640044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:46.640044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R0chndqXqkijWgkbvUdvK7kevEG1kWTsUtDL+P3piKSvVFzWnSmCzjKCjEv1koNZeJ8kTs8VHZxwH3Wt8WSgDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:46.640700Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.09341","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:984da80fd42ad985d7453065cbaf103a65ab265e29bd72ab0641acd4975360c4","sha256:d7bc0805c860cf119c5ac5b005dc57e907eedd78df19e7c016cdf5bfb152acc2"],"state_sha256":"cb4e3504f21a62153ba3e444e65e74b3cf8f092690e26bd7a979126cd8b32fb0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AhHXXDhtlcW4mQ7z83T1r+kOTHmGnWEZDteqVFRTe9avR+HNR7LZRPfzMoGwgAMS7oKVg7fxXJ0alqvM5XkSAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T00:11:49.485028Z","bundle_sha256":"a3edc871da005f3e7dd3e0307925f11205374e52cfe0bda6cf4b245401ed0280"}}