{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:IFFFOYTLOE3GWTTR5G3UQGWUEF","short_pith_number":"pith:IFFFOYTL","canonical_record":{"source":{"id":"1907.02874","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-05T14:59:41Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"2ed198d37887f05cb8fa4e44d354c637452889a1e068e707fd4e0abb428a7fc7","abstract_canon_sha256":"0d809bd09c4d1866c497734d3eebbf008f74e597221655165ddc52442fb9654b"},"schema_version":"1.0"},"canonical_sha256":"414a57626b71366b4e71e9b7481ad421535b0547d7815d42440ac16a4e2591b8","source":{"kind":"arxiv","id":"1907.02874","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.02874","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"arxiv_version","alias_value":"1907.02874v1","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02874","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"pith_short_12","alias_value":"IFFFOYTLOE3G","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IFFFOYTLOE3GWTTR","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IFFFOYTL","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:IFFFOYTLOE3GWTTR5G3UQGWUEF","target":"record","payload":{"canonical_record":{"source":{"id":"1907.02874","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-05T14:59:41Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"2ed198d37887f05cb8fa4e44d354c637452889a1e068e707fd4e0abb428a7fc7","abstract_canon_sha256":"0d809bd09c4d1866c497734d3eebbf008f74e597221655165ddc52442fb9654b"},"schema_version":"1.0"},"canonical_sha256":"414a57626b71366b4e71e9b7481ad421535b0547d7815d42440ac16a4e2591b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:22.784219Z","signature_b64":"+DVE3BNt97mTUrTJ3RW/XhmcLxCNEcevwtUdZ0KWKdmjnAhr9HL4g9FB57tbbV9HZ0rftftTpmo1i+JafyQHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"414a57626b71366b4e71e9b7481ad421535b0547d7815d42440ac16a4e2591b8","last_reissued_at":"2026-05-17T23:41:22.783444Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:22.783444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.02874","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":"2026-05-17T23:41:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7EnQq80sg85TAxf2sdthaxs7dtnE3BB4N1d2MrM73HfYpda0VAvmMBHNs006/8RRrEFQHQM9ERFMV3Iq7G2cBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:38:25.639450Z"},"content_sha256":"124c46de8a7f7cdc2921e95073029e703a0ce72f1dd886507c193e97ca3f62ae","schema_version":"1.0","event_id":"sha256:124c46de8a7f7cdc2921e95073029e703a0ce72f1dd886507c193e97ca3f62ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:IFFFOYTLOE3GWTTR5G3UQGWUEF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attentive Multi-Task Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gino Brunner, Oliver Richter, Roger Wattenhofer, Timo Bram","submitted_at":"2019-07-05T14:59:41Z","abstract_excerpt":"Sharing knowledge between tasks is vital for efficient learning in a multi-task setting. However, most research so far has focused on the easier case where knowledge transfer is not harmful, i.e., where knowledge from one task cannot negatively impact the performance on another task. In contrast, we present an approach to multi-task deep reinforcement learning based on attention that does not require any a-priori assumptions about the relationships between tasks. Our attention network automatically groups task knowledge into sub-networks on a state level granularity. It thereby achieves positi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02874","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":"2026-05-17T23:41:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k2UtRwbhohwzMabq8d4RRandEaePE/o7FsQr9hsuBJAqOt8997UGAlbNWZQoHawbVglSvBXnAP+AMo//2/TuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:38:25.639984Z"},"content_sha256":"131685a7308c943583585c3f46dcc56716d2e30d4b996f0374596bad5c00ec04","schema_version":"1.0","event_id":"sha256:131685a7308c943583585c3f46dcc56716d2e30d4b996f0374596bad5c00ec04"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IFFFOYTLOE3GWTTR5G3UQGWUEF/bundle.json","state_url":"https://pith.science/pith/IFFFOYTLOE3GWTTR5G3UQGWUEF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IFFFOYTLOE3GWTTR5G3UQGWUEF/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":"2026-05-26T00:38:25Z","links":{"resolver":"https://pith.science/pith/IFFFOYTLOE3GWTTR5G3UQGWUEF","bundle":"https://pith.science/pith/IFFFOYTLOE3GWTTR5G3UQGWUEF/bundle.json","state":"https://pith.science/pith/IFFFOYTLOE3GWTTR5G3UQGWUEF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IFFFOYTLOE3GWTTR5G3UQGWUEF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IFFFOYTLOE3GWTTR5G3UQGWUEF","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":"0d809bd09c4d1866c497734d3eebbf008f74e597221655165ddc52442fb9654b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-05T14:59:41Z","title_canon_sha256":"2ed198d37887f05cb8fa4e44d354c637452889a1e068e707fd4e0abb428a7fc7"},"schema_version":"1.0","source":{"id":"1907.02874","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.02874","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"arxiv_version","alias_value":"1907.02874v1","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02874","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"pith_short_12","alias_value":"IFFFOYTLOE3G","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IFFFOYTLOE3GWTTR","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IFFFOYTL","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:131685a7308c943583585c3f46dcc56716d2e30d4b996f0374596bad5c00ec04","target":"graph","created_at":"2026-05-17T23:41:22Z","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":"Sharing knowledge between tasks is vital for efficient learning in a multi-task setting. However, most research so far has focused on the easier case where knowledge transfer is not harmful, i.e., where knowledge from one task cannot negatively impact the performance on another task. In contrast, we present an approach to multi-task deep reinforcement learning based on attention that does not require any a-priori assumptions about the relationships between tasks. Our attention network automatically groups task knowledge into sub-networks on a state level granularity. It thereby achieves positi","authors_text":"Gino Brunner, Oliver Richter, Roger Wattenhofer, Timo Bram","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-05T14:59:41Z","title":"Attentive Multi-Task Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02874","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":"sha256:124c46de8a7f7cdc2921e95073029e703a0ce72f1dd886507c193e97ca3f62ae","target":"record","created_at":"2026-05-17T23:41:22Z","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":"0d809bd09c4d1866c497734d3eebbf008f74e597221655165ddc52442fb9654b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-05T14:59:41Z","title_canon_sha256":"2ed198d37887f05cb8fa4e44d354c637452889a1e068e707fd4e0abb428a7fc7"},"schema_version":"1.0","source":{"id":"1907.02874","kind":"arxiv","version":1}},"canonical_sha256":"414a57626b71366b4e71e9b7481ad421535b0547d7815d42440ac16a4e2591b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"414a57626b71366b4e71e9b7481ad421535b0547d7815d42440ac16a4e2591b8","first_computed_at":"2026-05-17T23:41:22.783444Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:22.783444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+DVE3BNt97mTUrTJ3RW/XhmcLxCNEcevwtUdZ0KWKdmjnAhr9HL4g9FB57tbbV9HZ0rftftTpmo1i+JafyQHDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:22.784219Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.02874","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:124c46de8a7f7cdc2921e95073029e703a0ce72f1dd886507c193e97ca3f62ae","sha256:131685a7308c943583585c3f46dcc56716d2e30d4b996f0374596bad5c00ec04"],"state_sha256":"2ab50f0e208a7d4395cad55e98c1ab849a6602edbfbff87cc65580c545908dba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TveJaAmuAISsbXBtvz7HlXKWdw4+20HZuMtUzikxtEyybAM9X7ObVqV/EHvHdKvaAH6PKc6iKKZmvDHd1dYDAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T00:38:25.642819Z","bundle_sha256":"f8b70149c855ae502109b026a17057b19fce200ab65c1e7d441aa0b196efd2bc"}}