{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:6TSTEHSLU2BBVJWNV5YXZMAEAH","short_pith_number":"pith:6TSTEHSL","canonical_record":{"source":{"id":"2210.14361","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-25T22:04:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e3bacab3b3c6689e0d29ef23a0204a86df5edfe87bc150c061efcb4562b4995e","abstract_canon_sha256":"cf83813c94a6460d69ad43f824d2bfb42e8669d38e3ae96ceff0567f509c1a9a"},"schema_version":"1.0"},"canonical_sha256":"f4e5321e4ba6821aa6cdaf717cb00401f3f7d05adc7f278a83964edaca491794","source":{"kind":"arxiv","id":"2210.14361","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.14361","created_at":"2026-07-05T08:46:15Z"},{"alias_kind":"arxiv_version","alias_value":"2210.14361v2","created_at":"2026-07-05T08:46:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14361","created_at":"2026-07-05T08:46:15Z"},{"alias_kind":"pith_short_12","alias_value":"6TSTEHSLU2BB","created_at":"2026-07-05T08:46:15Z"},{"alias_kind":"pith_short_16","alias_value":"6TSTEHSLU2BBVJWN","created_at":"2026-07-05T08:46:15Z"},{"alias_kind":"pith_short_8","alias_value":"6TSTEHSL","created_at":"2026-07-05T08:46:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:6TSTEHSLU2BBVJWNV5YXZMAEAH","target":"record","payload":{"canonical_record":{"source":{"id":"2210.14361","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-25T22:04:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e3bacab3b3c6689e0d29ef23a0204a86df5edfe87bc150c061efcb4562b4995e","abstract_canon_sha256":"cf83813c94a6460d69ad43f824d2bfb42e8669d38e3ae96ceff0567f509c1a9a"},"schema_version":"1.0"},"canonical_sha256":"f4e5321e4ba6821aa6cdaf717cb00401f3f7d05adc7f278a83964edaca491794","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:15.411194Z","signature_b64":"Dj8gBNMoKNKpBa+BBU/0iXAYEKhGRtGPefGJrlOQPmka/Qb4SCFuW9TW36tEF+TyDWnC5pM9QgUPXJChfuw+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4e5321e4ba6821aa6cdaf717cb00401f3f7d05adc7f278a83964edaca491794","last_reissued_at":"2026-07-05T08:46:15.410765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:15.410765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.14361","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":"2026-07-05T08:46:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BMMU63pElNomXjUVPJEmbnawHbFZ5UhxHTbwfndprRitUAESVxKBuunhPfFf58b74eA1Nv3F7nLld5BGbooJCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:09:31.672856Z"},"content_sha256":"0e946a97517892dd5d675e83fe2862a5279460864ffdf2e68d6d5cddc433a89f","schema_version":"1.0","event_id":"sha256:0e946a97517892dd5d675e83fe2862a5279460864ffdf2e68d6d5cddc433a89f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:6TSTEHSLU2BBVJWNV5YXZMAEAH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Auxiliary task discovery through generate-and-test","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam White, Banafsheh Rafiee, Jun Jin, Jun Luo, Richard Sutton, Sina Ghiassian","submitted_at":"2022-10-25T22:04:37Z","abstract_excerpt":"In this paper, we explore an approach to auxiliary task discovery in reinforcement learning based on ideas from representation learning. Auxiliary tasks tend to improve data efficiency by forcing the agent to learn auxiliary prediction and control objectives in addition to the main task of maximizing reward, and thus producing better representations. Typically these tasks are designed by people. Meta-learning offers a promising avenue for automatic task discovery; however, these methods are computationally expensive and challenging to tune in practice. In this paper, we explore a complementary"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14361","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/2210.14361/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":"2026-07-05T08:46:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dHnOHhR5Srirvre8u4yjymEO+1dFfRyV+ZvjUIL8a8Z4ZmIDzBBr0VBJZhq5OlrUUOX9iR4/vNh3BN/Vn1g4CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:09:31.673427Z"},"content_sha256":"a177da7c8c31aeee8a0d41836179ce9a134dccfd5a248c86e4ef05161911796c","schema_version":"1.0","event_id":"sha256:a177da7c8c31aeee8a0d41836179ce9a134dccfd5a248c86e4ef05161911796c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6TSTEHSLU2BBVJWNV5YXZMAEAH/bundle.json","state_url":"https://pith.science/pith/6TSTEHSLU2BBVJWNV5YXZMAEAH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6TSTEHSLU2BBVJWNV5YXZMAEAH/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":"2026-08-11T00:09:31Z","links":{"resolver":"https://pith.science/pith/6TSTEHSLU2BBVJWNV5YXZMAEAH","bundle":"https://pith.science/pith/6TSTEHSLU2BBVJWNV5YXZMAEAH/bundle.json","state":"https://pith.science/pith/6TSTEHSLU2BBVJWNV5YXZMAEAH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6TSTEHSLU2BBVJWNV5YXZMAEAH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6TSTEHSLU2BBVJWNV5YXZMAEAH","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":"cf83813c94a6460d69ad43f824d2bfb42e8669d38e3ae96ceff0567f509c1a9a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-25T22:04:37Z","title_canon_sha256":"e3bacab3b3c6689e0d29ef23a0204a86df5edfe87bc150c061efcb4562b4995e"},"schema_version":"1.0","source":{"id":"2210.14361","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.14361","created_at":"2026-07-05T08:46:15Z"},{"alias_kind":"arxiv_version","alias_value":"2210.14361v2","created_at":"2026-07-05T08:46:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14361","created_at":"2026-07-05T08:46:15Z"},{"alias_kind":"pith_short_12","alias_value":"6TSTEHSLU2BB","created_at":"2026-07-05T08:46:15Z"},{"alias_kind":"pith_short_16","alias_value":"6TSTEHSLU2BBVJWN","created_at":"2026-07-05T08:46:15Z"},{"alias_kind":"pith_short_8","alias_value":"6TSTEHSL","created_at":"2026-07-05T08:46:15Z"}],"graph_snapshots":[{"event_id":"sha256:a177da7c8c31aeee8a0d41836179ce9a134dccfd5a248c86e4ef05161911796c","target":"graph","created_at":"2026-07-05T08:46:15Z","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/2210.14361/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we explore an approach to auxiliary task discovery in reinforcement learning based on ideas from representation learning. Auxiliary tasks tend to improve data efficiency by forcing the agent to learn auxiliary prediction and control objectives in addition to the main task of maximizing reward, and thus producing better representations. Typically these tasks are designed by people. Meta-learning offers a promising avenue for automatic task discovery; however, these methods are computationally expensive and challenging to tune in practice. In this paper, we explore a complementary","authors_text":"Adam White, Banafsheh Rafiee, Jun Jin, Jun Luo, Richard Sutton, Sina Ghiassian","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-25T22:04:37Z","title":"Auxiliary task discovery through generate-and-test"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14361","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":"sha256:0e946a97517892dd5d675e83fe2862a5279460864ffdf2e68d6d5cddc433a89f","target":"record","created_at":"2026-07-05T08:46:15Z","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":"cf83813c94a6460d69ad43f824d2bfb42e8669d38e3ae96ceff0567f509c1a9a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-25T22:04:37Z","title_canon_sha256":"e3bacab3b3c6689e0d29ef23a0204a86df5edfe87bc150c061efcb4562b4995e"},"schema_version":"1.0","source":{"id":"2210.14361","kind":"arxiv","version":2}},"canonical_sha256":"f4e5321e4ba6821aa6cdaf717cb00401f3f7d05adc7f278a83964edaca491794","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4e5321e4ba6821aa6cdaf717cb00401f3f7d05adc7f278a83964edaca491794","first_computed_at":"2026-07-05T08:46:15.410765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:15.410765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dj8gBNMoKNKpBa+BBU/0iXAYEKhGRtGPefGJrlOQPmka/Qb4SCFuW9TW36tEF+TyDWnC5pM9QgUPXJChfuw+Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:15.411194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.14361","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e946a97517892dd5d675e83fe2862a5279460864ffdf2e68d6d5cddc433a89f","sha256:a177da7c8c31aeee8a0d41836179ce9a134dccfd5a248c86e4ef05161911796c"],"state_sha256":"31d542b1739b65839978be38c0c3eeb506a0d6bfb065061ca37ef91ccb14ec6e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZoHa4zETYdoO7MOUqUI5Hl0NSV2pllhOEYa3gdA5G/J8LdjidsSnj26B7GS29DjyhPtKr169EgTDWFa4AEdgBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T00:09:31.678654Z","bundle_sha256":"ef9d95ac65aeecb5f98bd65ec37cc187051a05e5810c876cb8ed661c33ebde43"}}