{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZZHLYY3X3F5WQ5RRYR5PF2JTFG","short_pith_number":"pith:ZZHLYY3X","canonical_record":{"source":{"id":"1909.11373","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T09:49:01Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1685eacd572c6a728666173dbc51ff212e29461727af0fff71cd1df5488ad93c","abstract_canon_sha256":"4da7db6c5caf93379f10ddfca6ba350c82116cc6eafe9a9695e5a679c60c7b71"},"schema_version":"1.0"},"canonical_sha256":"ce4ebc6377d97b687631c47af2e933298c0af9d875f0728cd1b81d89d6300335","source":{"kind":"arxiv","id":"1909.11373","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.11373","created_at":"2026-07-05T01:45:40Z"},{"alias_kind":"arxiv_version","alias_value":"1909.11373v6","created_at":"2026-07-05T01:45:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11373","created_at":"2026-07-05T01:45:40Z"},{"alias_kind":"pith_short_12","alias_value":"ZZHLYY3X3F5W","created_at":"2026-07-05T01:45:40Z"},{"alias_kind":"pith_short_16","alias_value":"ZZHLYY3X3F5WQ5RR","created_at":"2026-07-05T01:45:40Z"},{"alias_kind":"pith_short_8","alias_value":"ZZHLYY3X","created_at":"2026-07-05T01:45:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZZHLYY3X3F5WQ5RRYR5PF2JTFG","target":"record","payload":{"canonical_record":{"source":{"id":"1909.11373","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T09:49:01Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1685eacd572c6a728666173dbc51ff212e29461727af0fff71cd1df5488ad93c","abstract_canon_sha256":"4da7db6c5caf93379f10ddfca6ba350c82116cc6eafe9a9695e5a679c60c7b71"},"schema_version":"1.0"},"canonical_sha256":"ce4ebc6377d97b687631c47af2e933298c0af9d875f0728cd1b81d89d6300335","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:40.466977Z","signature_b64":"15OskB5/U1luCKFWEInWgRw0OebOcFU5GQDYwliKV3wz0wEkDVucYw5RIY7IiCjx5utQgiu0bFrvrHhdfLhtDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce4ebc6377d97b687631c47af2e933298c0af9d875f0728cd1b81d89d6300335","last_reissued_at":"2026-07-05T01:45:40.466584Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:40.466584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.11373","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:45:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B7/hcMfEjndTy8AzhvQNV/xm5sC7VkU/E5Fd3pvJ1mtdsXL6/jYH+Uzu7qLdk6ZDJ8PBidrizpvDVZmd7jwBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:16:29.804372Z"},"content_sha256":"8cd594251703a34db9df199830249ede7cf13201e64a312801eaf91b38bbccb9","schema_version":"1.0","event_id":"sha256:8cd594251703a34db9df199830249ede7cf13201e64a312801eaf91b38bbccb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZZHLYY3X3F5WQ5RRYR5PF2JTFG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-task Batch Reinforcement Learning with Metric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao Su, Henrik Iskov Christensen, Jiachen Li, Kamil Ciosek, Keith Ross, Minghua Liu, Quan Vuong, Shuang Liu","submitted_at":"2019-09-25T09:49:01Z","abstract_excerpt":"We tackle the Multi-task Batch Reinforcement Learning problem. Given multiple datasets collected from different tasks, we train a multi-task policy to perform well in unseen tasks sampled from the same distribution. The task identities of the unseen tasks are not provided. To perform well, the policy must infer the task identity from collected transitions by modelling its dependency on states, actions and rewards. Because the different datasets may have state-action distributions with large divergence, the task inference module can learn to ignore the rewards and spuriously correlate $\\textit{"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11373","kind":"arxiv","version":6},"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/1909.11373/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":"2026-07-05T01:45:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"buzfdKj53tf1CDKpFtDOH4BPzFoiP2HnKo172AjFCT5Dix988VqFd3aBYaeQWj+KFN1nBaRTzOFrNkqoeQPmCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:16:29.804904Z"},"content_sha256":"ea3eccfec52d5c603ca9cbcbf5459548e9d796c3d575740a63677d53e764dec3","schema_version":"1.0","event_id":"sha256:ea3eccfec52d5c603ca9cbcbf5459548e9d796c3d575740a63677d53e764dec3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZZHLYY3X3F5WQ5RRYR5PF2JTFG/bundle.json","state_url":"https://pith.science/pith/ZZHLYY3X3F5WQ5RRYR5PF2JTFG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZZHLYY3X3F5WQ5RRYR5PF2JTFG/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":"2026-08-05T23:16:29Z","links":{"resolver":"https://pith.science/pith/ZZHLYY3X3F5WQ5RRYR5PF2JTFG","bundle":"https://pith.science/pith/ZZHLYY3X3F5WQ5RRYR5PF2JTFG/bundle.json","state":"https://pith.science/pith/ZZHLYY3X3F5WQ5RRYR5PF2JTFG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZZHLYY3X3F5WQ5RRYR5PF2JTFG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZZHLYY3X3F5WQ5RRYR5PF2JTFG","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":"4da7db6c5caf93379f10ddfca6ba350c82116cc6eafe9a9695e5a679c60c7b71","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T09:49:01Z","title_canon_sha256":"1685eacd572c6a728666173dbc51ff212e29461727af0fff71cd1df5488ad93c"},"schema_version":"1.0","source":{"id":"1909.11373","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.11373","created_at":"2026-07-05T01:45:40Z"},{"alias_kind":"arxiv_version","alias_value":"1909.11373v6","created_at":"2026-07-05T01:45:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11373","created_at":"2026-07-05T01:45:40Z"},{"alias_kind":"pith_short_12","alias_value":"ZZHLYY3X3F5W","created_at":"2026-07-05T01:45:40Z"},{"alias_kind":"pith_short_16","alias_value":"ZZHLYY3X3F5WQ5RR","created_at":"2026-07-05T01:45:40Z"},{"alias_kind":"pith_short_8","alias_value":"ZZHLYY3X","created_at":"2026-07-05T01:45:40Z"}],"graph_snapshots":[{"event_id":"sha256:ea3eccfec52d5c603ca9cbcbf5459548e9d796c3d575740a63677d53e764dec3","target":"graph","created_at":"2026-07-05T01:45:40Z","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/1909.11373/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We tackle the Multi-task Batch Reinforcement Learning problem. Given multiple datasets collected from different tasks, we train a multi-task policy to perform well in unseen tasks sampled from the same distribution. The task identities of the unseen tasks are not provided. To perform well, the policy must infer the task identity from collected transitions by modelling its dependency on states, actions and rewards. Because the different datasets may have state-action distributions with large divergence, the task inference module can learn to ignore the rewards and spuriously correlate $\\textit{","authors_text":"Hao Su, Henrik Iskov Christensen, Jiachen Li, Kamil Ciosek, Keith Ross, Minghua Liu, Quan Vuong, Shuang Liu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T09:49:01Z","title":"Multi-task Batch Reinforcement Learning with Metric Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11373","kind":"arxiv","version":6},"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":"sha256:8cd594251703a34db9df199830249ede7cf13201e64a312801eaf91b38bbccb9","target":"record","created_at":"2026-07-05T01:45:40Z","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":"4da7db6c5caf93379f10ddfca6ba350c82116cc6eafe9a9695e5a679c60c7b71","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T09:49:01Z","title_canon_sha256":"1685eacd572c6a728666173dbc51ff212e29461727af0fff71cd1df5488ad93c"},"schema_version":"1.0","source":{"id":"1909.11373","kind":"arxiv","version":6}},"canonical_sha256":"ce4ebc6377d97b687631c47af2e933298c0af9d875f0728cd1b81d89d6300335","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce4ebc6377d97b687631c47af2e933298c0af9d875f0728cd1b81d89d6300335","first_computed_at":"2026-07-05T01:45:40.466584Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:40.466584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"15OskB5/U1luCKFWEInWgRw0OebOcFU5GQDYwliKV3wz0wEkDVucYw5RIY7IiCjx5utQgiu0bFrvrHhdfLhtDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:40.466977Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.11373","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cd594251703a34db9df199830249ede7cf13201e64a312801eaf91b38bbccb9","sha256:ea3eccfec52d5c603ca9cbcbf5459548e9d796c3d575740a63677d53e764dec3"],"state_sha256":"8cc5a25dfb70cbdaf0036a54220066aef28660a1ed37a56074c0b04a575bac60"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"30QlQtSgYSrDFm3M4trFpVMogbOmPgS+IhuBspEvY4n3TfafMxNbNx0/oTL0PIHVP/c7bOs9kh/iODM9h2FKDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:16:29.810612Z","bundle_sha256":"eb29ff277a8b54f43a5b54cedf0ab11759bc8d1de4fe0b59449627ebb3b29e15"}}