{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OC4OKTSN6UO5B5EEQGFAVJHSRA","short_pith_number":"pith:OC4OKTSN","schema_version":"1.0","canonical_sha256":"70b8e54e4df51dd0f484818a0aa4f28822cd1ab822d8ab3392111511b578c83e","source":{"kind":"arxiv","id":"1906.05030","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1906.05030","created_at":"2026-07-05T00:35:44.364308+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.05030v2","created_at":"2026-07-05T00:35:44.364308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05030","created_at":"2026-07-05T00:35:44.364308+00:00"},{"alias_kind":"pith_short_12","alias_value":"OC4OKTSN6UO5","created_at":"2026-07-05T00:35:44.364308+00:00"},{"alias_kind":"pith_short_16","alias_value":"OC4OKTSN6UO5B5EE","created_at":"2026-07-05T00:35:44.364308+00:00"},{"alias_kind":"pith_short_8","alias_value":"OC4OKTSN","created_at":"2026-07-05T00:35:44.364308+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.08902","citing_title":"Intention-Conditioned Flow Occupancy Models","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OC4OKTSN6UO5B5EEQGFAVJHSRA","json":"https://pith.science/pith/OC4OKTSN6UO5B5EEQGFAVJHSRA.json","graph_json":"https://pith.science/api/pith-number/OC4OKTSN6UO5B5EEQGFAVJHSRA/graph.json","events_json":"https://pith.science/api/pith-number/OC4OKTSN6UO5B5EEQGFAVJHSRA/events.json","paper":"https://pith.science/paper/OC4OKTSN"},"agent_actions":{"view_html":"https://pith.science/pith/OC4OKTSN6UO5B5EEQGFAVJHSRA","download_json":"https://pith.science/pith/OC4OKTSN6UO5B5EEQGFAVJHSRA.json","view_paper":"https://pith.science/paper/OC4OKTSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.05030&json=true","fetch_graph":"https://pith.science/api/pith-number/OC4OKTSN6UO5B5EEQGFAVJHSRA/graph.json","fetch_events":"https://pith.science/api/pith-number/OC4OKTSN6UO5B5EEQGFAVJHSRA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OC4OKTSN6UO5B5EEQGFAVJHSRA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OC4OKTSN6UO5B5EEQGFAVJHSRA/action/storage_attestation","attest_author":"https://pith.science/pith/OC4OKTSN6UO5B5EEQGFAVJHSRA/action/author_attestation","sign_citation":"https://pith.science/pith/OC4OKTSN6UO5B5EEQGFAVJHSRA/action/citation_signature","submit_replication":"https://pith.science/pith/OC4OKTSN6UO5B5EEQGFAVJHSRA/action/replication_record"}},"created_at":"2026-07-05T00:35:44.364308+00:00","updated_at":"2026-07-05T00:35:44.364308+00:00"}