{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:4KAI5ADKR7RBPM4PFRRCEDEB3W","short_pith_number":"pith:4KAI5ADK","canonical_record":{"source":{"id":"1611.05397","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-16T18:21:29Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"87229cfef734bbdf23312fb0c8f8fd7b60bb64ae89b3435d0b42cde749fea964","abstract_canon_sha256":"01b0ca783d40f6e65b291f689034fc545882796f3f289e089142fdd63022f020"},"schema_version":"1.0"},"canonical_sha256":"e2808e806a8fe217b38f2c62220c81dd85a00a44fa9b96bae8870c11ca961def","source":{"kind":"arxiv","id":"1611.05397","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.05397","created_at":"2026-05-18T00:58:27Z"},{"alias_kind":"arxiv_version","alias_value":"1611.05397v1","created_at":"2026-05-18T00:58:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.05397","created_at":"2026-05-18T00:58:27Z"},{"alias_kind":"pith_short_12","alias_value":"4KAI5ADKR7RB","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"4KAI5ADKR7RBPM4P","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"4KAI5ADK","created_at":"2026-05-18T12:29:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:4KAI5ADKR7RBPM4PFRRCEDEB3W","target":"record","payload":{"canonical_record":{"source":{"id":"1611.05397","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-16T18:21:29Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"87229cfef734bbdf23312fb0c8f8fd7b60bb64ae89b3435d0b42cde749fea964","abstract_canon_sha256":"01b0ca783d40f6e65b291f689034fc545882796f3f289e089142fdd63022f020"},"schema_version":"1.0"},"canonical_sha256":"e2808e806a8fe217b38f2c62220c81dd85a00a44fa9b96bae8870c11ca961def","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:58:27.200647Z","signature_b64":"468xtJd05wUxqYkosWgXw5symZSuJFY9eESAIqgCWs702HmcBbMqIKRAmSs/AGi4PVr1gHEl2pEeucFIJdwAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2808e806a8fe217b38f2c62220c81dd85a00a44fa9b96bae8870c11ca961def","last_reissued_at":"2026-05-18T00:58:27.200013Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:58:27.200013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.05397","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":"2026-05-18T00:58:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vQluiumzJ8TM8SYgvfDGuDVYF0m018wnkGPa2kyMz/AnnKVAYq/zQlKnRd4vB3iOQ+Rdq6VxboZlekoYvm7RBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:20:12.010192Z"},"content_sha256":"1a3db7f98e4fe6ece199a361f14bfff0bdafda6c214278ee1d6207d89ea09a81","schema_version":"1.0","event_id":"sha256:1a3db7f98e4fe6ece199a361f14bfff0bdafda6c214278ee1d6207d89ea09a81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:4KAI5ADKR7RBPM4PFRRCEDEB3W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"David Silver, Joel Z Leibo, Koray Kavukcuoglu, Max Jaderberg, Tom Schaul, Volodymyr Mnih, Wojciech Marian Czarnecki","submitted_at":"2016-11-16T18:21:29Z","abstract_excerpt":"Deep reinforcement learning agents have achieved state-of-the-art results by directly maximising cumulative reward. However, environments contain a much wider variety of possible training signals. In this paper, we introduce an agent that also maximises many other pseudo-reward functions simultaneously by reinforcement learning. All of these tasks share a common representation that, like unsupervised learning, continues to develop in the absence of extrinsic rewards. We also introduce a novel mechanism for focusing this representation upon extrinsic rewards, so that learning can rapidly adapt "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.05397","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":"2026-05-18T00:58:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dr37wIfYEzMVlYzjpTULa89SHD4rDveEx1mpqZZtYn26gJMoNChOEDYeF3aKr7UnVHWlEDy5lJMjMuvCNRKJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:20:12.010796Z"},"content_sha256":"64d4f9168be1f400d1762c1607a8cf09d992994976486bd8f512ce4df6f68643","schema_version":"1.0","event_id":"sha256:64d4f9168be1f400d1762c1607a8cf09d992994976486bd8f512ce4df6f68643"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4KAI5ADKR7RBPM4PFRRCEDEB3W/bundle.json","state_url":"https://pith.science/pith/4KAI5ADKR7RBPM4PFRRCEDEB3W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4KAI5ADKR7RBPM4PFRRCEDEB3W/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":"2026-05-30T09:20:12Z","links":{"resolver":"https://pith.science/pith/4KAI5ADKR7RBPM4PFRRCEDEB3W","bundle":"https://pith.science/pith/4KAI5ADKR7RBPM4PFRRCEDEB3W/bundle.json","state":"https://pith.science/pith/4KAI5ADKR7RBPM4PFRRCEDEB3W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4KAI5ADKR7RBPM4PFRRCEDEB3W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:4KAI5ADKR7RBPM4PFRRCEDEB3W","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":"01b0ca783d40f6e65b291f689034fc545882796f3f289e089142fdd63022f020","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-16T18:21:29Z","title_canon_sha256":"87229cfef734bbdf23312fb0c8f8fd7b60bb64ae89b3435d0b42cde749fea964"},"schema_version":"1.0","source":{"id":"1611.05397","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.05397","created_at":"2026-05-18T00:58:27Z"},{"alias_kind":"arxiv_version","alias_value":"1611.05397v1","created_at":"2026-05-18T00:58:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.05397","created_at":"2026-05-18T00:58:27Z"},{"alias_kind":"pith_short_12","alias_value":"4KAI5ADKR7RB","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"4KAI5ADKR7RBPM4P","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"4KAI5ADK","created_at":"2026-05-18T12:29:58Z"}],"graph_snapshots":[{"event_id":"sha256:64d4f9168be1f400d1762c1607a8cf09d992994976486bd8f512ce4df6f68643","target":"graph","created_at":"2026-05-18T00:58:27Z","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":"Deep reinforcement learning agents have achieved state-of-the-art results by directly maximising cumulative reward. However, environments contain a much wider variety of possible training signals. In this paper, we introduce an agent that also maximises many other pseudo-reward functions simultaneously by reinforcement learning. All of these tasks share a common representation that, like unsupervised learning, continues to develop in the absence of extrinsic rewards. We also introduce a novel mechanism for focusing this representation upon extrinsic rewards, so that learning can rapidly adapt ","authors_text":"David Silver, Joel Z Leibo, Koray Kavukcuoglu, Max Jaderberg, Tom Schaul, Volodymyr Mnih, Wojciech Marian Czarnecki","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-16T18:21:29Z","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.05397","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":"sha256:1a3db7f98e4fe6ece199a361f14bfff0bdafda6c214278ee1d6207d89ea09a81","target":"record","created_at":"2026-05-18T00:58:27Z","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":"01b0ca783d40f6e65b291f689034fc545882796f3f289e089142fdd63022f020","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-16T18:21:29Z","title_canon_sha256":"87229cfef734bbdf23312fb0c8f8fd7b60bb64ae89b3435d0b42cde749fea964"},"schema_version":"1.0","source":{"id":"1611.05397","kind":"arxiv","version":1}},"canonical_sha256":"e2808e806a8fe217b38f2c62220c81dd85a00a44fa9b96bae8870c11ca961def","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2808e806a8fe217b38f2c62220c81dd85a00a44fa9b96bae8870c11ca961def","first_computed_at":"2026-05-18T00:58:27.200013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:58:27.200013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"468xtJd05wUxqYkosWgXw5symZSuJFY9eESAIqgCWs702HmcBbMqIKRAmSs/AGi4PVr1gHEl2pEeucFIJdwAAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:58:27.200647Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.05397","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a3db7f98e4fe6ece199a361f14bfff0bdafda6c214278ee1d6207d89ea09a81","sha256:64d4f9168be1f400d1762c1607a8cf09d992994976486bd8f512ce4df6f68643"],"state_sha256":"488a71f41f3b4402c4019b79a912e28511ea46e7ba219c61099049d8638f75a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jzXJLJWBKSoCo0iS+mEYgbNBQvLL0Ew0MNT1foZLXCvJSrltKD1UhWEFUW6NfcLOGNIzTlgBSLL7iGA4NYS+DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T09:20:12.014179Z","bundle_sha256":"e530257fdfdaaf0ff34fc3dc48bd4d1c5ae49a7642cc94e5a7c99b58e8194565"}}