{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MMXD4PUQMQRMQA5RPM5M5S5XC5","short_pith_number":"pith:MMXD4PUQ","canonical_record":{"source":{"id":"2302.00671","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-01T18:58:20Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"88fc4744af2e95f5f9058ad23208a375b2eb01ef8f2c7467b5623ef24d5a71b1","abstract_canon_sha256":"3ca3c82007a8571481681fcc7f77f1d0f9afdc2bf9cd7bb24cce3dfab6e029d7"},"schema_version":"1.0"},"canonical_sha256":"632e3e3e906422c803b17b3acecbb71741b2a1b1a86939290a8dbd40a7f14163","source":{"kind":"arxiv","id":"2302.00671","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.00671","created_at":"2026-07-05T10:55:15Z"},{"alias_kind":"arxiv_version","alias_value":"2302.00671v3","created_at":"2026-07-05T10:55:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00671","created_at":"2026-07-05T10:55:15Z"},{"alias_kind":"pith_short_12","alias_value":"MMXD4PUQMQRM","created_at":"2026-07-05T10:55:15Z"},{"alias_kind":"pith_short_16","alias_value":"MMXD4PUQMQRMQA5R","created_at":"2026-07-05T10:55:15Z"},{"alias_kind":"pith_short_8","alias_value":"MMXD4PUQ","created_at":"2026-07-05T10:55:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MMXD4PUQMQRMQA5RPM5M5S5XC5","target":"record","payload":{"canonical_record":{"source":{"id":"2302.00671","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-01T18:58:20Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"88fc4744af2e95f5f9058ad23208a375b2eb01ef8f2c7467b5623ef24d5a71b1","abstract_canon_sha256":"3ca3c82007a8571481681fcc7f77f1d0f9afdc2bf9cd7bb24cce3dfab6e029d7"},"schema_version":"1.0"},"canonical_sha256":"632e3e3e906422c803b17b3acecbb71741b2a1b1a86939290a8dbd40a7f14163","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:15.789301Z","signature_b64":"Edu9MHPiqUQ/dXLqL5Zv78hhcqQsMp7e0JArUkY7of+jQCD58eBpFVaBTjL+VzF9xCfe+Ai6MYIed5drBJspDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"632e3e3e906422c803b17b3acecbb71741b2a1b1a86939290a8dbd40a7f14163","last_reissued_at":"2026-07-05T10:55:15.788763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:15.788763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.00671","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:55:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PH+fBNkK/nkk5lUulEaqWqv8wZNoOpIz6S0wt8C99oLeaUCbI93KErq6TyTBo8QrbtOLepqONGu/vdeS2jZxBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:10:24.268469Z"},"content_sha256":"86143da064f63371de64ecbea86db7e905b0966c20acb93632f8316e97054f8a","schema_version":"1.0","event_id":"sha256:86143da064f63371de64ecbea86db7e905b0966c20acb93632f8316e97054f8a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MMXD4PUQMQRMQA5RPM5M5S5XC5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"QMP: Q-switch Mixture of Policies for Multi-Task Behavior Sharing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ayush Jain, Grace Zhang, Injune Hwang, Joseph J. Lim, Shao-Hua Sun","submitted_at":"2023-02-01T18:58:20Z","abstract_excerpt":"Multi-task reinforcement learning (MTRL) aims to learn several tasks simultaneously for better sample efficiency than learning them separately. Traditional methods achieve this by sharing parameters or relabeled data between tasks. In this work, we introduce a new framework for sharing behavioral policies across tasks, which can be used in addition to existing MTRL methods. The key idea is to improve each task's off-policy data collection by employing behaviors from other task policies. Selectively sharing helpful behaviors acquired in one task to collect training data for another task can lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00671","kind":"arxiv","version":3},"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/2302.00671/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":"2026-07-05T10:55:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gjrZ4UG/2FUN5uqmRC/jS5fVbV4cCNZTKOvqOZu8rneua2FS5obiIMOMyOmk6Ia1EicDCHfH6uhDb0FWUY+vAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:10:24.269066Z"},"content_sha256":"dfcd4a5fdd93c06428a43502c287af6f2e4a1fc7c48b0492aaeeaac29110d2e3","schema_version":"1.0","event_id":"sha256:dfcd4a5fdd93c06428a43502c287af6f2e4a1fc7c48b0492aaeeaac29110d2e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MMXD4PUQMQRMQA5RPM5M5S5XC5/bundle.json","state_url":"https://pith.science/pith/MMXD4PUQMQRMQA5RPM5M5S5XC5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MMXD4PUQMQRMQA5RPM5M5S5XC5/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":"2026-08-09T01:10:24Z","links":{"resolver":"https://pith.science/pith/MMXD4PUQMQRMQA5RPM5M5S5XC5","bundle":"https://pith.science/pith/MMXD4PUQMQRMQA5RPM5M5S5XC5/bundle.json","state":"https://pith.science/pith/MMXD4PUQMQRMQA5RPM5M5S5XC5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MMXD4PUQMQRMQA5RPM5M5S5XC5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MMXD4PUQMQRMQA5RPM5M5S5XC5","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":"3ca3c82007a8571481681fcc7f77f1d0f9afdc2bf9cd7bb24cce3dfab6e029d7","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-01T18:58:20Z","title_canon_sha256":"88fc4744af2e95f5f9058ad23208a375b2eb01ef8f2c7467b5623ef24d5a71b1"},"schema_version":"1.0","source":{"id":"2302.00671","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.00671","created_at":"2026-07-05T10:55:15Z"},{"alias_kind":"arxiv_version","alias_value":"2302.00671v3","created_at":"2026-07-05T10:55:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00671","created_at":"2026-07-05T10:55:15Z"},{"alias_kind":"pith_short_12","alias_value":"MMXD4PUQMQRM","created_at":"2026-07-05T10:55:15Z"},{"alias_kind":"pith_short_16","alias_value":"MMXD4PUQMQRMQA5R","created_at":"2026-07-05T10:55:15Z"},{"alias_kind":"pith_short_8","alias_value":"MMXD4PUQ","created_at":"2026-07-05T10:55:15Z"}],"graph_snapshots":[{"event_id":"sha256:dfcd4a5fdd93c06428a43502c287af6f2e4a1fc7c48b0492aaeeaac29110d2e3","target":"graph","created_at":"2026-07-05T10:55:15Z","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/2302.00671/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-task reinforcement learning (MTRL) aims to learn several tasks simultaneously for better sample efficiency than learning them separately. Traditional methods achieve this by sharing parameters or relabeled data between tasks. In this work, we introduce a new framework for sharing behavioral policies across tasks, which can be used in addition to existing MTRL methods. The key idea is to improve each task's off-policy data collection by employing behaviors from other task policies. Selectively sharing helpful behaviors acquired in one task to collect training data for another task can lea","authors_text":"Ayush Jain, Grace Zhang, Injune Hwang, Joseph J. Lim, Shao-Hua Sun","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-01T18:58:20Z","title":"QMP: Q-switch Mixture of Policies for Multi-Task Behavior Sharing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00671","kind":"arxiv","version":3},"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":"sha256:86143da064f63371de64ecbea86db7e905b0966c20acb93632f8316e97054f8a","target":"record","created_at":"2026-07-05T10:55:15Z","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":"3ca3c82007a8571481681fcc7f77f1d0f9afdc2bf9cd7bb24cce3dfab6e029d7","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-01T18:58:20Z","title_canon_sha256":"88fc4744af2e95f5f9058ad23208a375b2eb01ef8f2c7467b5623ef24d5a71b1"},"schema_version":"1.0","source":{"id":"2302.00671","kind":"arxiv","version":3}},"canonical_sha256":"632e3e3e906422c803b17b3acecbb71741b2a1b1a86939290a8dbd40a7f14163","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"632e3e3e906422c803b17b3acecbb71741b2a1b1a86939290a8dbd40a7f14163","first_computed_at":"2026-07-05T10:55:15.788763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:15.788763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Edu9MHPiqUQ/dXLqL5Zv78hhcqQsMp7e0JArUkY7of+jQCD58eBpFVaBTjL+VzF9xCfe+Ai6MYIed5drBJspDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:15.789301Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.00671","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86143da064f63371de64ecbea86db7e905b0966c20acb93632f8316e97054f8a","sha256:dfcd4a5fdd93c06428a43502c287af6f2e4a1fc7c48b0492aaeeaac29110d2e3"],"state_sha256":"e1d9b7319a669aa5fb10050df88202ddd0a70066de83d6ac3112d4124374eaa0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/PCUfAIXtVPDLjC5MYhqiVkap32V7KyFoVcHnPOAfSaJwzE0rQ12Jr0Q5muDqUFwt0HK8jBN8D35WHYoZQ8VDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T01:10:24.273923Z","bundle_sha256":"2abb07f21741867a5c6ac4594e8677953220ad2f21bc108015ad0678623704b2"}}