{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5FVJBW437AFZK7FXS7JOJIP5JL","short_pith_number":"pith:5FVJBW43","canonical_record":{"source":{"id":"1902.05542","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-02-14T18:54:54Z","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"title_canon_sha256":"49a4afa2e6167153842cd802e19d9de39b00f7cc490f8fbd93a451fff55f4f3d","abstract_canon_sha256":"760e7fb508b579cdfe3ab454165fe2327b1eb18c0484dd1ce37b9b91178210c9"},"schema_version":"1.0"},"canonical_sha256":"e96a90db9bf80b957cb797d2e4a1fd4ae10000c75f2e2282974100ca0d4fca91","source":{"kind":"arxiv","id":"1902.05542","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.05542","created_at":"2026-05-17T23:53:58Z"},{"alias_kind":"arxiv_version","alias_value":"1902.05542v1","created_at":"2026-05-17T23:53:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05542","created_at":"2026-05-17T23:53:58Z"},{"alias_kind":"pith_short_12","alias_value":"5FVJBW437AFZ","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5FVJBW437AFZK7FX","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5FVJBW43","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5FVJBW437AFZK7FXS7JOJIP5JL","target":"record","payload":{"canonical_record":{"source":{"id":"1902.05542","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-02-14T18:54:54Z","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"title_canon_sha256":"49a4afa2e6167153842cd802e19d9de39b00f7cc490f8fbd93a451fff55f4f3d","abstract_canon_sha256":"760e7fb508b579cdfe3ab454165fe2327b1eb18c0484dd1ce37b9b91178210c9"},"schema_version":"1.0"},"canonical_sha256":"e96a90db9bf80b957cb797d2e4a1fd4ae10000c75f2e2282974100ca0d4fca91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:58.404784Z","signature_b64":"EmRSTg6uXJwg2M1Cx+2CavIU0gnbwHcimwjaCivvXlju6eBlX+bCH/VNnhddPtoNd/oXM0h+EwHO7G4e7H1fCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e96a90db9bf80b957cb797d2e4a1fd4ae10000c75f2e2282974100ca0d4fca91","last_reissued_at":"2026-05-17T23:53:58.404139Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:58.404139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.05542","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":"2026-05-17T23:53:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jBkqCTCBawjJs7+rY+lTmuk0p7D1lEla5BfysirZA2G9+LE0cL9bWH4pLPDxZDT6Y/8SKo9b1f/s/an4DhNaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T00:52:39.249165Z"},"content_sha256":"be96920ecf99c06415759f394bd507ed5eec903d0ee4e82faa7d704e781e0067","schema_version":"1.0","event_id":"sha256:be96920ecf99c06415759f394bd507ed5eec903d0ee4e82faa7d704e781e0067"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5FVJBW437AFZK7FXS7JOJIP5JL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Visuomotor Control through Distributional Planning Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ML"],"primary_cat":"cs.RO","authors_text":"Chelsea Finn, Dorsa Sadigh, Gleb Shevchuk, Tianhe Yu","submitted_at":"2019-02-14T18:54:54Z","abstract_excerpt":"While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where aspects of the environment needed to compute progress are not directly accessible. To enable robots to autonomously learn skills, we instead consider the problem of reinforcement learning without access to rewards. We aim to learn an unsupervised embedding space under which the robot can measure progress towards a goal for itself. Our approach explicitly opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05542","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":"2026-05-17T23:53:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4BwIq+qDGh0oQvaugHGWJaFyunZ9b1snQCqGsI+IZFJvkIFCFvyC9Fcju4xebjGs6d61Zv9qyQ5VC3lWDIzYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T00:52:39.249543Z"},"content_sha256":"1194015b7ecee96e5725a5e95b0a6d9682b55f4ae60bb3e0fdeb901a3da21b0b","schema_version":"1.0","event_id":"sha256:1194015b7ecee96e5725a5e95b0a6d9682b55f4ae60bb3e0fdeb901a3da21b0b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5FVJBW437AFZK7FXS7JOJIP5JL/bundle.json","state_url":"https://pith.science/pith/5FVJBW437AFZK7FXS7JOJIP5JL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5FVJBW437AFZK7FXS7JOJIP5JL/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":"2026-05-19T00:52:39Z","links":{"resolver":"https://pith.science/pith/5FVJBW437AFZK7FXS7JOJIP5JL","bundle":"https://pith.science/pith/5FVJBW437AFZK7FXS7JOJIP5JL/bundle.json","state":"https://pith.science/pith/5FVJBW437AFZK7FXS7JOJIP5JL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5FVJBW437AFZK7FXS7JOJIP5JL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5FVJBW437AFZK7FXS7JOJIP5JL","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":"760e7fb508b579cdfe3ab454165fe2327b1eb18c0484dd1ce37b9b91178210c9","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-02-14T18:54:54Z","title_canon_sha256":"49a4afa2e6167153842cd802e19d9de39b00f7cc490f8fbd93a451fff55f4f3d"},"schema_version":"1.0","source":{"id":"1902.05542","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.05542","created_at":"2026-05-17T23:53:58Z"},{"alias_kind":"arxiv_version","alias_value":"1902.05542v1","created_at":"2026-05-17T23:53:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05542","created_at":"2026-05-17T23:53:58Z"},{"alias_kind":"pith_short_12","alias_value":"5FVJBW437AFZ","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5FVJBW437AFZK7FX","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5FVJBW43","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:1194015b7ecee96e5725a5e95b0a6d9682b55f4ae60bb3e0fdeb901a3da21b0b","target":"graph","created_at":"2026-05-17T23:53:58Z","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":"While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where aspects of the environment needed to compute progress are not directly accessible. To enable robots to autonomously learn skills, we instead consider the problem of reinforcement learning without access to rewards. We aim to learn an unsupervised embedding space under which the robot can measure progress towards a goal for itself. Our approach explicitly opt","authors_text":"Chelsea Finn, Dorsa Sadigh, Gleb Shevchuk, Tianhe Yu","cross_cats":["cs.CV","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-02-14T18:54:54Z","title":"Unsupervised Visuomotor Control through Distributional Planning Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05542","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:be96920ecf99c06415759f394bd507ed5eec903d0ee4e82faa7d704e781e0067","target":"record","created_at":"2026-05-17T23:53:58Z","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":"760e7fb508b579cdfe3ab454165fe2327b1eb18c0484dd1ce37b9b91178210c9","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-02-14T18:54:54Z","title_canon_sha256":"49a4afa2e6167153842cd802e19d9de39b00f7cc490f8fbd93a451fff55f4f3d"},"schema_version":"1.0","source":{"id":"1902.05542","kind":"arxiv","version":1}},"canonical_sha256":"e96a90db9bf80b957cb797d2e4a1fd4ae10000c75f2e2282974100ca0d4fca91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e96a90db9bf80b957cb797d2e4a1fd4ae10000c75f2e2282974100ca0d4fca91","first_computed_at":"2026-05-17T23:53:58.404139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:58.404139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EmRSTg6uXJwg2M1Cx+2CavIU0gnbwHcimwjaCivvXlju6eBlX+bCH/VNnhddPtoNd/oXM0h+EwHO7G4e7H1fCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:58.404784Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.05542","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be96920ecf99c06415759f394bd507ed5eec903d0ee4e82faa7d704e781e0067","sha256:1194015b7ecee96e5725a5e95b0a6d9682b55f4ae60bb3e0fdeb901a3da21b0b"],"state_sha256":"139449c281072cf27b226dcb8609926e1894e7bf484c0203c7c6b270a59cc010"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EpM0Yrlyiq6d9rCDg84qk2fptPNbW8yIvNHvClIVh/fBaEuhyOlcFiSE7gXS3UJTENyJBpYi+aldUsY2eGQRAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T00:52:39.250783Z","bundle_sha256":"7256a9e5c4de1b6cb9ddd5a6e0f807beb3bc267406fb0a00d67b843763e75ecb"}}