{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:OC4OKTSN6UO5B5EEQGFAVJHSRA","short_pith_number":"pith:OC4OKTSN","canonical_record":{"source":{"id":"1906.05030","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T09:39:05Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1f78964d4ed571beb01a0ca68da62468cf58fa62cd0ff20f236e3ae43865183f","abstract_canon_sha256":"71686d05b8c0ac08f96970b1e019fa5ce8c8b9be7d2de9738c64e85f740d90f7"},"schema_version":"1.0"},"canonical_sha256":"70b8e54e4df51dd0f484818a0aa4f28822cd1ab822d8ab3392111511b578c83e","source":{"kind":"arxiv","id":"1906.05030","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05030","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05030v2","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05030","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"pith_short_12","alias_value":"OC4OKTSN6UO5","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"pith_short_16","alias_value":"OC4OKTSN6UO5B5EE","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"pith_short_8","alias_value":"OC4OKTSN","created_at":"2026-07-05T00:35:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:OC4OKTSN6UO5B5EEQGFAVJHSRA","target":"record","payload":{"canonical_record":{"source":{"id":"1906.05030","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T09:39:05Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1f78964d4ed571beb01a0ca68da62468cf58fa62cd0ff20f236e3ae43865183f","abstract_canon_sha256":"71686d05b8c0ac08f96970b1e019fa5ce8c8b9be7d2de9738c64e85f740d90f7"},"schema_version":"1.0"},"canonical_sha256":"70b8e54e4df51dd0f484818a0aa4f28822cd1ab822d8ab3392111511b578c83e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:44.364760Z","signature_b64":"I55geu+CNW4SghtHAgVzBTV0HFEo4QhU0/S1zj5O7R6F/7cl9o9E9eCuBHuRjn3o00nh4hAu8Wv2aKfY7Sf1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70b8e54e4df51dd0f484818a0aa4f28822cd1ab822d8ab3392111511b578c83e","last_reissued_at":"2026-07-05T00:35:44.364251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:44.364251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.05030","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:35:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S3v43EKVVuOo9GIP5tlbq8AYk+wARHxqsffyHV1YcWr4/ej38PLWb72B8e8cHpWPKRS27KvP9RE5IqD8nYqeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:27:04.709116Z"},"content_sha256":"9b7b024a9c741177e2bf74eb62aa49343fa442712a5cba21c7a20ff1c6dd3166","schema_version":"1.0","event_id":"sha256:9b7b024a9c741177e2bf74eb62aa49343fa442712a5cba21c7a20ff1c6dd3166"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:OC4OKTSN6UO5B5EEQGFAVJHSRA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast Task Inference with Variational Intrinsic Successor Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andre Barreto, David Warde-Farley, Steven Hansen, Tom Van de Wiele, Volodymyr Mnih, Will Dabney","submitted_at":"2019-06-12T09:39:05Z","abstract_excerpt":"It has been established that diverse behaviors spanning the controllable subspace of an Markov decision process can be trained by rewarding a policy for being distinguishable from other policies \\citep{gregor2016variational, eysenbach2018diversity, warde2018unsupervised}. However, one limitation of this formulation is generalizing behaviors beyond the finite set being explicitly learned, as is needed for use on subsequent tasks. Successor features \\citep{dayan93improving, barreto2017successor} provide an appealing solution to this generalization problem, but require defining the reward functio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05030","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1906.05030/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:35:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NnEOz2rFavG3VUwowahEzIT+BemZ3XIQtI/nmk75+eFx5DoTOaRvxE/kQkqlw+HEMEI9HkSW8UZ80heZNsAeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:27:04.709494Z"},"content_sha256":"99ffeb24dd8c598e2d63357ce8c5743a4b51c1f30e12cb6911054f7a43f5338b","schema_version":"1.0","event_id":"sha256:99ffeb24dd8c598e2d63357ce8c5743a4b51c1f30e12cb6911054f7a43f5338b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OC4OKTSN6UO5B5EEQGFAVJHSRA/bundle.json","state_url":"https://pith.science/pith/OC4OKTSN6UO5B5EEQGFAVJHSRA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OC4OKTSN6UO5B5EEQGFAVJHSRA/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":"2026-08-03T19:27:04Z","links":{"resolver":"https://pith.science/pith/OC4OKTSN6UO5B5EEQGFAVJHSRA","bundle":"https://pith.science/pith/OC4OKTSN6UO5B5EEQGFAVJHSRA/bundle.json","state":"https://pith.science/pith/OC4OKTSN6UO5B5EEQGFAVJHSRA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OC4OKTSN6UO5B5EEQGFAVJHSRA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:OC4OKTSN6UO5B5EEQGFAVJHSRA","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":"71686d05b8c0ac08f96970b1e019fa5ce8c8b9be7d2de9738c64e85f740d90f7","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T09:39:05Z","title_canon_sha256":"1f78964d4ed571beb01a0ca68da62468cf58fa62cd0ff20f236e3ae43865183f"},"schema_version":"1.0","source":{"id":"1906.05030","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05030","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05030v2","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05030","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"pith_short_12","alias_value":"OC4OKTSN6UO5","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"pith_short_16","alias_value":"OC4OKTSN6UO5B5EE","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"pith_short_8","alias_value":"OC4OKTSN","created_at":"2026-07-05T00:35:44Z"}],"graph_snapshots":[{"event_id":"sha256:99ffeb24dd8c598e2d63357ce8c5743a4b51c1f30e12cb6911054f7a43f5338b","target":"graph","created_at":"2026-07-05T00:35:44Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1906.05030/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It has been established that diverse behaviors spanning the controllable subspace of an Markov decision process can be trained by rewarding a policy for being distinguishable from other policies \\citep{gregor2016variational, eysenbach2018diversity, warde2018unsupervised}. However, one limitation of this formulation is generalizing behaviors beyond the finite set being explicitly learned, as is needed for use on subsequent tasks. Successor features \\citep{dayan93improving, barreto2017successor} provide an appealing solution to this generalization problem, but require defining the reward functio","authors_text":"Andre Barreto, David Warde-Farley, Steven Hansen, Tom Van de Wiele, Volodymyr Mnih, Will Dabney","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T09:39:05Z","title":"Fast Task Inference with Variational Intrinsic Successor Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05030","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":"sha256:9b7b024a9c741177e2bf74eb62aa49343fa442712a5cba21c7a20ff1c6dd3166","target":"record","created_at":"2026-07-05T00:35:44Z","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":"71686d05b8c0ac08f96970b1e019fa5ce8c8b9be7d2de9738c64e85f740d90f7","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T09:39:05Z","title_canon_sha256":"1f78964d4ed571beb01a0ca68da62468cf58fa62cd0ff20f236e3ae43865183f"},"schema_version":"1.0","source":{"id":"1906.05030","kind":"arxiv","version":2}},"canonical_sha256":"70b8e54e4df51dd0f484818a0aa4f28822cd1ab822d8ab3392111511b578c83e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70b8e54e4df51dd0f484818a0aa4f28822cd1ab822d8ab3392111511b578c83e","first_computed_at":"2026-07-05T00:35:44.364251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:35:44.364251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I55geu+CNW4SghtHAgVzBTV0HFEo4QhU0/S1zj5O7R6F/7cl9o9E9eCuBHuRjn3o00nh4hAu8Wv2aKfY7Sf1AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:35:44.364760Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.05030","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b7b024a9c741177e2bf74eb62aa49343fa442712a5cba21c7a20ff1c6dd3166","sha256:99ffeb24dd8c598e2d63357ce8c5743a4b51c1f30e12cb6911054f7a43f5338b"],"state_sha256":"ebdcf316d5709c7fdc3640c72c5840d0360c313f8acc8cebe3c74f702715d0fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J6i6pot0bRJtENZbULvkVhGPKO9lRTupJecJxo7HFK6vAY/JYhmu5kCrGpjubytbitWVXloEiNm7Li1ozzJCDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:27:04.712136Z","bundle_sha256":"d1f3683b0b9ef0f0370a89517012e5e83313312a7f147d8e8375b17f8518d849"}}