{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:HJP7NQZ6F3LT4YSJMNGFZVCO74","short_pith_number":"pith:HJP7NQZ6","canonical_record":{"source":{"id":"2210.11653","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-21T01:00:10Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"090f97878b3594e8cbee0d18f557959975d497878e2ef6427f5b2fe10fce8770","abstract_canon_sha256":"2133a1fe4e81e2453e03a15a784f48327856ae7a02e60e31bc6afd2a43cd8eb1"},"schema_version":"1.0"},"canonical_sha256":"3a5ff6c33e2ed73e6249634c5cd44eff33601207bc9d6cc20992dd3e473ca20d","source":{"kind":"arxiv","id":"2210.11653","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11653","created_at":"2026-07-05T05:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11653v1","created_at":"2026-07-05T05:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11653","created_at":"2026-07-05T05:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"HJP7NQZ6F3LT","created_at":"2026-07-05T05:08:56Z"},{"alias_kind":"pith_short_16","alias_value":"HJP7NQZ6F3LT4YSJ","created_at":"2026-07-05T05:08:56Z"},{"alias_kind":"pith_short_8","alias_value":"HJP7NQZ6","created_at":"2026-07-05T05:08:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:HJP7NQZ6F3LT4YSJMNGFZVCO74","target":"record","payload":{"canonical_record":{"source":{"id":"2210.11653","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-21T01:00:10Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"090f97878b3594e8cbee0d18f557959975d497878e2ef6427f5b2fe10fce8770","abstract_canon_sha256":"2133a1fe4e81e2453e03a15a784f48327856ae7a02e60e31bc6afd2a43cd8eb1"},"schema_version":"1.0"},"canonical_sha256":"3a5ff6c33e2ed73e6249634c5cd44eff33601207bc9d6cc20992dd3e473ca20d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:56.012289Z","signature_b64":"1K1NZhYTtinxW97yApyM2U27BqylE/RppGBKtz1aSocslV2JlnwUrPvypUJholIrcsuTrQ3j59tgqorpIMSWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a5ff6c33e2ed73e6249634c5cd44eff33601207bc9d6cc20992dd3e473ca20d","last_reissued_at":"2026-07-05T05:08:56.011819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:56.011819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.11653","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":"2026-07-05T05:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/xpjEeYvGLZKfaI2g+tHwxWYqOKI0XFdeB4/4j62QU36eK3NxAj4kYHhkWHSP9dm6ImFziZYnXBkhVIR5OhPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:52:12.758593Z"},"content_sha256":"528f424e32e032bde250a47af5a850a33631a65e7063e3ba8e8c65714651ad13","schema_version":"1.0","event_id":"sha256:528f424e32e032bde250a47af5a850a33631a65e7063e3ba8e8c65714651ad13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:HJP7NQZ6F3LT4YSJMNGFZVCO74","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PaCo: Parameter-Compositional Multi-Task Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Haichao Zhang, Lingfeng Sun, Masayoshi Tomizuka, Wei Xu","submitted_at":"2022-10-21T01:00:10Z","abstract_excerpt":"The purpose of multi-task reinforcement learning (MTRL) is to train a single policy that can be applied to a set of different tasks. Sharing parameters allows us to take advantage of the similarities among tasks. However, the gaps between contents and difficulties of different tasks bring us challenges on both which tasks should share the parameters and what parameters should be shared, as well as the optimization challenges due to parameter sharing. In this work, we introduce a parameter-compositional approach (PaCo) as an attempt to address these challenges. In this framework, a policy subsp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11653","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/2210.11653/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":"2026-07-05T05:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fmGlw5hGvh7W64h4MgNeOeCdGFjZI5EnFvFltzM2vBsjCOTTmiQm51s5oozGwMkuXEhCDmNwB1HffPidWkiwAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:52:12.759130Z"},"content_sha256":"274a4b73cc2400390df0a6b631a4ca5cea58d5dcaed7e88eea86d9595afaadad","schema_version":"1.0","event_id":"sha256:274a4b73cc2400390df0a6b631a4ca5cea58d5dcaed7e88eea86d9595afaadad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HJP7NQZ6F3LT4YSJMNGFZVCO74/bundle.json","state_url":"https://pith.science/pith/HJP7NQZ6F3LT4YSJMNGFZVCO74/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HJP7NQZ6F3LT4YSJMNGFZVCO74/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":"2026-08-10T09:52:12Z","links":{"resolver":"https://pith.science/pith/HJP7NQZ6F3LT4YSJMNGFZVCO74","bundle":"https://pith.science/pith/HJP7NQZ6F3LT4YSJMNGFZVCO74/bundle.json","state":"https://pith.science/pith/HJP7NQZ6F3LT4YSJMNGFZVCO74/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HJP7NQZ6F3LT4YSJMNGFZVCO74/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HJP7NQZ6F3LT4YSJMNGFZVCO74","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":"2133a1fe4e81e2453e03a15a784f48327856ae7a02e60e31bc6afd2a43cd8eb1","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-21T01:00:10Z","title_canon_sha256":"090f97878b3594e8cbee0d18f557959975d497878e2ef6427f5b2fe10fce8770"},"schema_version":"1.0","source":{"id":"2210.11653","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11653","created_at":"2026-07-05T05:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11653v1","created_at":"2026-07-05T05:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11653","created_at":"2026-07-05T05:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"HJP7NQZ6F3LT","created_at":"2026-07-05T05:08:56Z"},{"alias_kind":"pith_short_16","alias_value":"HJP7NQZ6F3LT4YSJ","created_at":"2026-07-05T05:08:56Z"},{"alias_kind":"pith_short_8","alias_value":"HJP7NQZ6","created_at":"2026-07-05T05:08:56Z"}],"graph_snapshots":[{"event_id":"sha256:274a4b73cc2400390df0a6b631a4ca5cea58d5dcaed7e88eea86d9595afaadad","target":"graph","created_at":"2026-07-05T05:08:56Z","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/2210.11653/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The purpose of multi-task reinforcement learning (MTRL) is to train a single policy that can be applied to a set of different tasks. Sharing parameters allows us to take advantage of the similarities among tasks. However, the gaps between contents and difficulties of different tasks bring us challenges on both which tasks should share the parameters and what parameters should be shared, as well as the optimization challenges due to parameter sharing. In this work, we introduce a parameter-compositional approach (PaCo) as an attempt to address these challenges. In this framework, a policy subsp","authors_text":"Haichao Zhang, Lingfeng Sun, Masayoshi Tomizuka, Wei Xu","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-21T01:00:10Z","title":"PaCo: Parameter-Compositional Multi-Task Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11653","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":"sha256:528f424e32e032bde250a47af5a850a33631a65e7063e3ba8e8c65714651ad13","target":"record","created_at":"2026-07-05T05:08:56Z","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":"2133a1fe4e81e2453e03a15a784f48327856ae7a02e60e31bc6afd2a43cd8eb1","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-21T01:00:10Z","title_canon_sha256":"090f97878b3594e8cbee0d18f557959975d497878e2ef6427f5b2fe10fce8770"},"schema_version":"1.0","source":{"id":"2210.11653","kind":"arxiv","version":1}},"canonical_sha256":"3a5ff6c33e2ed73e6249634c5cd44eff33601207bc9d6cc20992dd3e473ca20d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a5ff6c33e2ed73e6249634c5cd44eff33601207bc9d6cc20992dd3e473ca20d","first_computed_at":"2026-07-05T05:08:56.011819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:56.011819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1K1NZhYTtinxW97yApyM2U27BqylE/RppGBKtz1aSocslV2JlnwUrPvypUJholIrcsuTrQ3j59tgqorpIMSWCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:56.012289Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.11653","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:528f424e32e032bde250a47af5a850a33631a65e7063e3ba8e8c65714651ad13","sha256:274a4b73cc2400390df0a6b631a4ca5cea58d5dcaed7e88eea86d9595afaadad"],"state_sha256":"c4be1c43794dabff092df02dea94e0da2714d3058adf2d05f484677ea71603d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZDTZp5k1LdLdP2KUWswfju5d4oaPQ0gt8+XNAswZtkMsCrCFY6VAXIYpPZwrhVd0eG2ECtBCtZbwNYF03p7jBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:52:12.764106Z","bundle_sha256":"01f7c2cac0e602727ce55903dee85b43fd90619e1f0d177c49ab0486dbcb0d94"}}