{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:Y5IJCI4E6R4VZXMN4PR7PYQVBZ","short_pith_number":"pith:Y5IJCI4E","canonical_record":{"source":{"id":"1906.04161","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T17:58:32Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO","stat.ML"],"title_canon_sha256":"888aa639785c3bab55febec3e7ed029a2e722f6fa012a0a7e84f680d8d4470d1","abstract_canon_sha256":"611e59093d54a27712d77f9fe8478d7316f49ffe8d0db7a1d39f8d345bc6d22b"},"schema_version":"1.0"},"canonical_sha256":"c750912384f4795cdd8de3e3f7e2150e78b5a052dc3cb5c2cbb8169c3b4e1ae2","source":{"kind":"arxiv","id":"1906.04161","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04161","created_at":"2026-05-17T23:43:43Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04161v1","created_at":"2026-05-17T23:43:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04161","created_at":"2026-05-17T23:43:43Z"},{"alias_kind":"pith_short_12","alias_value":"Y5IJCI4E6R4V","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"Y5IJCI4E6R4VZXMN","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"Y5IJCI4E","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:Y5IJCI4E6R4VZXMN4PR7PYQVBZ","target":"record","payload":{"canonical_record":{"source":{"id":"1906.04161","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T17:58:32Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO","stat.ML"],"title_canon_sha256":"888aa639785c3bab55febec3e7ed029a2e722f6fa012a0a7e84f680d8d4470d1","abstract_canon_sha256":"611e59093d54a27712d77f9fe8478d7316f49ffe8d0db7a1d39f8d345bc6d22b"},"schema_version":"1.0"},"canonical_sha256":"c750912384f4795cdd8de3e3f7e2150e78b5a052dc3cb5c2cbb8169c3b4e1ae2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:43.698402Z","signature_b64":"KN6LTlmdm8mMOOlQi9rginmZey+E4Ug1wRKHHL+S3TBR8EneHFIboCTyboyDxj+o6hP1HYqSwVTUhgpCQMOICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c750912384f4795cdd8de3e3f7e2150e78b5a052dc3cb5c2cbb8169c3b4e1ae2","last_reissued_at":"2026-05-17T23:43:43.697700Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:43.697700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.04161","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":"2026-05-17T23:43:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PlP76PjKhj02LsBfA48siUO1KLNLGgCKDF1Vpb/JFG7D+dxS5s0dLNqYwDYMrcq+DRFYwcD54EJkOjmzGpepCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T17:52:32.387152Z"},"content_sha256":"a93fac0a7383467fd6ad1aca342b1ce65ea8b8ba73f646d4763f92914e449b24","schema_version":"1.0","event_id":"sha256:a93fac0a7383467fd6ad1aca342b1ce65ea8b8ba73f646d4763f92914e449b24"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:Y5IJCI4E6R4VZXMN4PR7PYQVBZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Supervised Exploration via Disagreement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhinav Gupta, Deepak Pathak, Dhiraj Gandhi","submitted_at":"2019-06-10T17:58:32Z","abstract_excerpt":"Efficient exploration is a long-standing problem in sensorimotor learning. Major advances have been demonstrated in noise-free, non-stochastic domains such as video games and simulation. However, most of these formulations either get stuck in environments with stochastic dynamics or are too inefficient to be scalable to real robotics setups. In this paper, we propose a formulation for exploration inspired by the work in active learning literature. Specifically, we train an ensemble of dynamics models and incentivize the agent to explore such that the disagreement of those ensembles is maximize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04161","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":"2026-05-17T23:43:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/wNjM5DI5Fcnt861bZn/gLCpOpqsBTRNK+K93kyPm1izRY8bKJldAEGNyBX41VfhsPuLqkbC2JIEsWlq271+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T17:52:32.387643Z"},"content_sha256":"4d4de0d3c953b63e3b468178b0f69d29375c45517f00f072b62206b38393609a","schema_version":"1.0","event_id":"sha256:4d4de0d3c953b63e3b468178b0f69d29375c45517f00f072b62206b38393609a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y5IJCI4E6R4VZXMN4PR7PYQVBZ/bundle.json","state_url":"https://pith.science/pith/Y5IJCI4E6R4VZXMN4PR7PYQVBZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y5IJCI4E6R4VZXMN4PR7PYQVBZ/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":"2026-05-18T17:52:32Z","links":{"resolver":"https://pith.science/pith/Y5IJCI4E6R4VZXMN4PR7PYQVBZ","bundle":"https://pith.science/pith/Y5IJCI4E6R4VZXMN4PR7PYQVBZ/bundle.json","state":"https://pith.science/pith/Y5IJCI4E6R4VZXMN4PR7PYQVBZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y5IJCI4E6R4VZXMN4PR7PYQVBZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:Y5IJCI4E6R4VZXMN4PR7PYQVBZ","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":"611e59093d54a27712d77f9fe8478d7316f49ffe8d0db7a1d39f8d345bc6d22b","cross_cats_sorted":["cs.AI","cs.CV","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T17:58:32Z","title_canon_sha256":"888aa639785c3bab55febec3e7ed029a2e722f6fa012a0a7e84f680d8d4470d1"},"schema_version":"1.0","source":{"id":"1906.04161","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04161","created_at":"2026-05-17T23:43:43Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04161v1","created_at":"2026-05-17T23:43:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04161","created_at":"2026-05-17T23:43:43Z"},{"alias_kind":"pith_short_12","alias_value":"Y5IJCI4E6R4V","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"Y5IJCI4E6R4VZXMN","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"Y5IJCI4E","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:4d4de0d3c953b63e3b468178b0f69d29375c45517f00f072b62206b38393609a","target":"graph","created_at":"2026-05-17T23:43:43Z","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":"Efficient exploration is a long-standing problem in sensorimotor learning. Major advances have been demonstrated in noise-free, non-stochastic domains such as video games and simulation. However, most of these formulations either get stuck in environments with stochastic dynamics or are too inefficient to be scalable to real robotics setups. In this paper, we propose a formulation for exploration inspired by the work in active learning literature. Specifically, we train an ensemble of dynamics models and incentivize the agent to explore such that the disagreement of those ensembles is maximize","authors_text":"Abhinav Gupta, Deepak Pathak, Dhiraj Gandhi","cross_cats":["cs.AI","cs.CV","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T17:58:32Z","title":"Self-Supervised Exploration via Disagreement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04161","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:a93fac0a7383467fd6ad1aca342b1ce65ea8b8ba73f646d4763f92914e449b24","target":"record","created_at":"2026-05-17T23:43:43Z","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":"611e59093d54a27712d77f9fe8478d7316f49ffe8d0db7a1d39f8d345bc6d22b","cross_cats_sorted":["cs.AI","cs.CV","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T17:58:32Z","title_canon_sha256":"888aa639785c3bab55febec3e7ed029a2e722f6fa012a0a7e84f680d8d4470d1"},"schema_version":"1.0","source":{"id":"1906.04161","kind":"arxiv","version":1}},"canonical_sha256":"c750912384f4795cdd8de3e3f7e2150e78b5a052dc3cb5c2cbb8169c3b4e1ae2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c750912384f4795cdd8de3e3f7e2150e78b5a052dc3cb5c2cbb8169c3b4e1ae2","first_computed_at":"2026-05-17T23:43:43.697700Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:43.697700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KN6LTlmdm8mMOOlQi9rginmZey+E4Ug1wRKHHL+S3TBR8EneHFIboCTyboyDxj+o6hP1HYqSwVTUhgpCQMOICQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:43.698402Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.04161","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a93fac0a7383467fd6ad1aca342b1ce65ea8b8ba73f646d4763f92914e449b24","sha256:4d4de0d3c953b63e3b468178b0f69d29375c45517f00f072b62206b38393609a"],"state_sha256":"f0166eab443ff1c9df9591ca8eda690cd965ddc81f87f9ee90dc3936c0c00f12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cukgYPaRCBNrg/wjcyONPRiUH0kmPfQwAo4I5fmYBsnPHpokgKMJTAcqu7i8OYjSNGrxjZKHYICL6XmQJ104Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-18T17:52:32.389000Z","bundle_sha256":"ce9a3e1bb1098a2084bc98355a6d2f7cfe0c8731e31314c66e32af9227b07625"}}