{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:33Y5VFLAIQVCVPNCHKYGL5N36P","short_pith_number":"pith:33Y5VFLA","schema_version":"1.0","canonical_sha256":"def1da9560442a2abda23ab065f5bbf3fc303dc5365f1448b02a0883982784d2","source":{"kind":"arxiv","id":"2304.12567","version":1},"attestation_state":"computed","paper":{"title":"Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Charline Le Lan, Jesse Farebrother, Joshua Greaves, Marc G. Bellemare, Pablo Samuel Castro, Rishabh Agarwal, Ross Goroshin","submitted_at":"2023-04-25T04:25:08Z","abstract_excerpt":"Auxiliary tasks improve the representations learned by deep reinforcement learning agents. Analytically, their effect is reasonably well understood; in practice, however, their primary use remains in support of a main learning objective, rather than as a method for learning representations. This is perhaps surprising given that many auxiliary tasks are defined procedurally, and hence can be treated as an essentially infinite source of information about the environment. Based on this observation, we study the effectiveness of auxiliary tasks for learning rich representations, focusing on the se"},"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":"2304.12567","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T04:25:08Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1bb4bc2693ca0da8a361dfb8f61106f9c21475f8be8ebccb491e4530fb261be9","abstract_canon_sha256":"ff8743923898a6fffc84264d67d89021ea9c4a4ff6a9a0c5a4a0aa74c49f81fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:16.728561Z","signature_b64":"/0WmawvpLa8wMZzXx5ek6WB7l0rF0fhott6/hU7oK9CvFqQcBOl/ngqGw1nVM1jkrmxa1x8/H5bpw+d4TTmBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"def1da9560442a2abda23ab065f5bbf3fc303dc5365f1448b02a0883982784d2","last_reissued_at":"2026-07-05T06:05:16.728082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:16.728082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Charline Le Lan, Jesse Farebrother, Joshua Greaves, Marc G. Bellemare, Pablo Samuel Castro, Rishabh Agarwal, Ross Goroshin","submitted_at":"2023-04-25T04:25:08Z","abstract_excerpt":"Auxiliary tasks improve the representations learned by deep reinforcement learning agents. Analytically, their effect is reasonably well understood; in practice, however, their primary use remains in support of a main learning objective, rather than as a method for learning representations. This is perhaps surprising given that many auxiliary tasks are defined procedurally, and hence can be treated as an essentially infinite source of information about the environment. Based on this observation, we study the effectiveness of auxiliary tasks for learning rich representations, focusing on the se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12567","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.12567/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":"2304.12567","created_at":"2026-07-05T06:05:16.728153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.12567v1","created_at":"2026-07-05T06:05:16.728153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12567","created_at":"2026-07-05T06:05:16.728153+00:00"},{"alias_kind":"pith_short_12","alias_value":"33Y5VFLAIQVC","created_at":"2026-07-05T06:05:16.728153+00:00"},{"alias_kind":"pith_short_16","alias_value":"33Y5VFLAIQVCVPNC","created_at":"2026-07-05T06:05:16.728153+00:00"},{"alias_kind":"pith_short_8","alias_value":"33Y5VFLA","created_at":"2026-07-05T06:05:16.728153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.11975","citing_title":"Online Training and Pruning of Deep Reinforcement Learning Networks","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/33Y5VFLAIQVCVPNCHKYGL5N36P","json":"https://pith.science/pith/33Y5VFLAIQVCVPNCHKYGL5N36P.json","graph_json":"https://pith.science/api/pith-number/33Y5VFLAIQVCVPNCHKYGL5N36P/graph.json","events_json":"https://pith.science/api/pith-number/33Y5VFLAIQVCVPNCHKYGL5N36P/events.json","paper":"https://pith.science/paper/33Y5VFLA"},"agent_actions":{"view_html":"https://pith.science/pith/33Y5VFLAIQVCVPNCHKYGL5N36P","download_json":"https://pith.science/pith/33Y5VFLAIQVCVPNCHKYGL5N36P.json","view_paper":"https://pith.science/paper/33Y5VFLA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.12567&json=true","fetch_graph":"https://pith.science/api/pith-number/33Y5VFLAIQVCVPNCHKYGL5N36P/graph.json","fetch_events":"https://pith.science/api/pith-number/33Y5VFLAIQVCVPNCHKYGL5N36P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/33Y5VFLAIQVCVPNCHKYGL5N36P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/33Y5VFLAIQVCVPNCHKYGL5N36P/action/storage_attestation","attest_author":"https://pith.science/pith/33Y5VFLAIQVCVPNCHKYGL5N36P/action/author_attestation","sign_citation":"https://pith.science/pith/33Y5VFLAIQVCVPNCHKYGL5N36P/action/citation_signature","submit_replication":"https://pith.science/pith/33Y5VFLAIQVCVPNCHKYGL5N36P/action/replication_record"}},"created_at":"2026-07-05T06:05:16.728153+00:00","updated_at":"2026-07-05T06:05:16.728153+00:00"}