{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PPGQRCMY3UMKK3FNP5QIZFNKJV","short_pith_number":"pith:PPGQRCMY","canonical_record":{"source":{"id":"1811.11359","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-28T02:35:24Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d35d0aa5a9a8377758d80c8d98ed88e1aadd401bede4bc759ddc140039f0f474","abstract_canon_sha256":"d2cf23a577c8a3f8e009a502704962a9b1e7160686149fa51d8984639addbadd"},"schema_version":"1.0"},"canonical_sha256":"7bcd088998dd18a56cad7f608c95aa4d530b915abc030376ae39ae8299de8751","source":{"kind":"arxiv","id":"1811.11359","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.11359","created_at":"2026-05-17T23:59:44Z"},{"alias_kind":"arxiv_version","alias_value":"1811.11359v1","created_at":"2026-05-17T23:59:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11359","created_at":"2026-05-17T23:59:44Z"},{"alias_kind":"pith_short_12","alias_value":"PPGQRCMY3UMK","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PPGQRCMY3UMKK3FN","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PPGQRCMY","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PPGQRCMY3UMKK3FNP5QIZFNKJV","target":"record","payload":{"canonical_record":{"source":{"id":"1811.11359","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-28T02:35:24Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d35d0aa5a9a8377758d80c8d98ed88e1aadd401bede4bc759ddc140039f0f474","abstract_canon_sha256":"d2cf23a577c8a3f8e009a502704962a9b1e7160686149fa51d8984639addbadd"},"schema_version":"1.0"},"canonical_sha256":"7bcd088998dd18a56cad7f608c95aa4d530b915abc030376ae39ae8299de8751","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:44.118885Z","signature_b64":"rZtb3hJTX6ErqG8EbxbujPJ6pkehCDPm11VmX1iiN3zWTdXZw5Q1I4vb1rYonLBdgwY22VmClidzJEOPVi23Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bcd088998dd18a56cad7f608c95aa4d530b915abc030376ae39ae8299de8751","last_reissued_at":"2026-05-17T23:59:44.118471Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:44.118471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.11359","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":"2026-05-17T23:59:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wq+YXzSSo7lM0jtJahw82b8kI7VwT4Z8VMk8w5ouc+Hjy8soYYoJ/X9OIz3oCAHDrLgYp9FFh8Qa2fE8T0cGAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:29:03.186127Z"},"content_sha256":"8a2ace13d7d170cdbb906bc29edaf2e358cab310c86af27e8466b7dce7d7d379","schema_version":"1.0","event_id":"sha256:8a2ace13d7d170cdbb906bc29edaf2e358cab310c86af27e8466b7dce7d7d379"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PPGQRCMY3UMKK3FNP5QIZFNKJV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Control Through Non-Parametric Discriminative Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Catalin Ionescu, David Warde-Farley, Steven Hansen, Tejas Kulkarni, Tom Van de Wiele, Volodymyr Mnih","submitted_at":"2018-11-28T02:35:24Z","abstract_excerpt":"Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve perceptually-specified goals using only a stream of observations and actions. Our agent simultaneously learns a goal-conditioned policy and a goal achievement reward function that measures how similar a state is to the goal state. This dual optimization leads to a co-operative game, giving rise to a learned reward function that reflects similarity in controllable asp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11359","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":"2026-05-17T23:59:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vLb7kAYMyy8dsB4JWOUwZrIISk4Lgcg9YSiqXDQ9OWhaZRXab16MZ4/bHEGPdxCfu4wlzEXe4MRj0KdMDA5FAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:29:03.186852Z"},"content_sha256":"d15e7262e11ca1b097c2ca7f293465b67f2ea8cbee8efe99679580bdba2a0921","schema_version":"1.0","event_id":"sha256:d15e7262e11ca1b097c2ca7f293465b67f2ea8cbee8efe99679580bdba2a0921"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PPGQRCMY3UMKK3FNP5QIZFNKJV/bundle.json","state_url":"https://pith.science/pith/PPGQRCMY3UMKK3FNP5QIZFNKJV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PPGQRCMY3UMKK3FNP5QIZFNKJV/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":"2026-05-26T01:29:03Z","links":{"resolver":"https://pith.science/pith/PPGQRCMY3UMKK3FNP5QIZFNKJV","bundle":"https://pith.science/pith/PPGQRCMY3UMKK3FNP5QIZFNKJV/bundle.json","state":"https://pith.science/pith/PPGQRCMY3UMKK3FNP5QIZFNKJV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PPGQRCMY3UMKK3FNP5QIZFNKJV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PPGQRCMY3UMKK3FNP5QIZFNKJV","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":"d2cf23a577c8a3f8e009a502704962a9b1e7160686149fa51d8984639addbadd","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-28T02:35:24Z","title_canon_sha256":"d35d0aa5a9a8377758d80c8d98ed88e1aadd401bede4bc759ddc140039f0f474"},"schema_version":"1.0","source":{"id":"1811.11359","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.11359","created_at":"2026-05-17T23:59:44Z"},{"alias_kind":"arxiv_version","alias_value":"1811.11359v1","created_at":"2026-05-17T23:59:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11359","created_at":"2026-05-17T23:59:44Z"},{"alias_kind":"pith_short_12","alias_value":"PPGQRCMY3UMK","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PPGQRCMY3UMKK3FN","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PPGQRCMY","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:d15e7262e11ca1b097c2ca7f293465b67f2ea8cbee8efe99679580bdba2a0921","target":"graph","created_at":"2026-05-17T23:59:44Z","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":"Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve perceptually-specified goals using only a stream of observations and actions. Our agent simultaneously learns a goal-conditioned policy and a goal achievement reward function that measures how similar a state is to the goal state. This dual optimization leads to a co-operative game, giving rise to a learned reward function that reflects similarity in controllable asp","authors_text":"Catalin Ionescu, David Warde-Farley, Steven Hansen, Tejas Kulkarni, Tom Van de Wiele, Volodymyr Mnih","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-28T02:35:24Z","title":"Unsupervised Control Through Non-Parametric Discriminative Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11359","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":"sha256:8a2ace13d7d170cdbb906bc29edaf2e358cab310c86af27e8466b7dce7d7d379","target":"record","created_at":"2026-05-17T23:59:44Z","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":"d2cf23a577c8a3f8e009a502704962a9b1e7160686149fa51d8984639addbadd","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-28T02:35:24Z","title_canon_sha256":"d35d0aa5a9a8377758d80c8d98ed88e1aadd401bede4bc759ddc140039f0f474"},"schema_version":"1.0","source":{"id":"1811.11359","kind":"arxiv","version":1}},"canonical_sha256":"7bcd088998dd18a56cad7f608c95aa4d530b915abc030376ae39ae8299de8751","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bcd088998dd18a56cad7f608c95aa4d530b915abc030376ae39ae8299de8751","first_computed_at":"2026-05-17T23:59:44.118471Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:44.118471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rZtb3hJTX6ErqG8EbxbujPJ6pkehCDPm11VmX1iiN3zWTdXZw5Q1I4vb1rYonLBdgwY22VmClidzJEOPVi23Cg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:44.118885Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.11359","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a2ace13d7d170cdbb906bc29edaf2e358cab310c86af27e8466b7dce7d7d379","sha256:d15e7262e11ca1b097c2ca7f293465b67f2ea8cbee8efe99679580bdba2a0921"],"state_sha256":"e0ed890f8efaf9b5e9f5b45a64524687fedc0d2a8f045b673884590f8c0723da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZIxX2UfT7ouaBLQBrtlofSbTGqzsWah5MJ2elC+WUGKp1xXWU8ZFnh6yCYGKOnQ4nVoZGxq8l9JWoFSgKvSPAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T01:29:03.190979Z","bundle_sha256":"8055d3e4dc461aef91e97a6187a85e85bd4e42c4923cedfa9c84232af6d32e98"}}