{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HMO6JIQFI5LE3XYV3PGE6V2OUQ","short_pith_number":"pith:HMO6JIQF","canonical_record":{"source":{"id":"2403.07261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-12T02:38:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"938f24daffaa2056cfcaa31cf95c4061bccdecd88bc855da19414a17a18d0c22","abstract_canon_sha256":"912ecb4ee9774dd903cb8cd15d1d1518811e1880fc63ba3571d1aa25f4de3f94"},"schema_version":"1.0"},"canonical_sha256":"3b1de4a20547564ddf15dbcc4f574ea41a881ffc8935ff17f8cd81becb1b5483","source":{"kind":"arxiv","id":"2403.07261","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.07261","created_at":"2026-07-05T07:55:01Z"},{"alias_kind":"arxiv_version","alias_value":"2403.07261v1","created_at":"2026-07-05T07:55:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07261","created_at":"2026-07-05T07:55:01Z"},{"alias_kind":"pith_short_12","alias_value":"HMO6JIQFI5LE","created_at":"2026-07-05T07:55:01Z"},{"alias_kind":"pith_short_16","alias_value":"HMO6JIQFI5LE3XYV","created_at":"2026-07-05T07:55:01Z"},{"alias_kind":"pith_short_8","alias_value":"HMO6JIQF","created_at":"2026-07-05T07:55:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HMO6JIQFI5LE3XYV3PGE6V2OUQ","target":"record","payload":{"canonical_record":{"source":{"id":"2403.07261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-12T02:38:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"938f24daffaa2056cfcaa31cf95c4061bccdecd88bc855da19414a17a18d0c22","abstract_canon_sha256":"912ecb4ee9774dd903cb8cd15d1d1518811e1880fc63ba3571d1aa25f4de3f94"},"schema_version":"1.0"},"canonical_sha256":"3b1de4a20547564ddf15dbcc4f574ea41a881ffc8935ff17f8cd81becb1b5483","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:01.238564Z","signature_b64":"b2imzXC5ryIdjmL24pxIJoHjupzoQLZrEj/eIogGtiZ2GD6HvW7t78mwwlQ22uFHqqlkJVmJGK1mgTSbUYUZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b1de4a20547564ddf15dbcc4f574ea41a881ffc8935ff17f8cd81becb1b5483","last_reissued_at":"2026-07-05T07:55:01.238135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:01.238135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.07261","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":"2026-07-05T07:55:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VN+Ez8u4VYZbZz7XFR3rdz2zNHjrWq7oR+NeJ6IaShOCxfn+nFT0ps2xUWzqn5LsXHjw0gu8mqK4kL3kigidCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:46:03.073156Z"},"content_sha256":"47afc7cc74b24b59155a6e335b3ba12a38ae09b34457a7677da80ee97a52f434","schema_version":"1.0","event_id":"sha256:47afc7cc74b24b59155a6e335b3ba12a38ae09b34457a7677da80ee97a52f434"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HMO6JIQFI5LE3XYV3PGE6V2OUQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chengxing Jia, Chen-Xiao Gao, Fuxiang Zhang, Lei Yuan, Xu-Hui Liu, Yang Yu, Yi-Chen Li, Zongzhang Zhang","submitted_at":"2024-03-12T02:38:36Z","abstract_excerpt":"Offline meta-reinforcement learning (OMRL) proficiently allows an agent to tackle novel tasks while solely relying on a static dataset. For precise and efficient task identification, existing OMRL research suggests learning separate task representations that be incorporated with policy input, thus forming a context-based meta-policy. A major approach to train task representations is to adopt contrastive learning using multi-task offline data. The dataset typically encompasses interactions from various policies (i.e., the behavior policies), thus providing a plethora of contextual information r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07261","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/2403.07261/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":"2026-07-05T07:55:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/1kIYawk2A3ltniM9epUHTnFfGV1mnPV9n0F1ZNOwKXSFWW9IfEonHSlmsc6AkCqF/V80qnXNmRBOd6Es4d/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:46:03.073914Z"},"content_sha256":"aacce935817dc5732d6175d1ebc20cf5361cce904ab8419c850c1bca94e2a8b6","schema_version":"1.0","event_id":"sha256:aacce935817dc5732d6175d1ebc20cf5361cce904ab8419c850c1bca94e2a8b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HMO6JIQFI5LE3XYV3PGE6V2OUQ/bundle.json","state_url":"https://pith.science/pith/HMO6JIQFI5LE3XYV3PGE6V2OUQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HMO6JIQFI5LE3XYV3PGE6V2OUQ/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":"2026-08-23T18:46:03Z","links":{"resolver":"https://pith.science/pith/HMO6JIQFI5LE3XYV3PGE6V2OUQ","bundle":"https://pith.science/pith/HMO6JIQFI5LE3XYV3PGE6V2OUQ/bundle.json","state":"https://pith.science/pith/HMO6JIQFI5LE3XYV3PGE6V2OUQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HMO6JIQFI5LE3XYV3PGE6V2OUQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HMO6JIQFI5LE3XYV3PGE6V2OUQ","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":"912ecb4ee9774dd903cb8cd15d1d1518811e1880fc63ba3571d1aa25f4de3f94","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-12T02:38:36Z","title_canon_sha256":"938f24daffaa2056cfcaa31cf95c4061bccdecd88bc855da19414a17a18d0c22"},"schema_version":"1.0","source":{"id":"2403.07261","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.07261","created_at":"2026-07-05T07:55:01Z"},{"alias_kind":"arxiv_version","alias_value":"2403.07261v1","created_at":"2026-07-05T07:55:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07261","created_at":"2026-07-05T07:55:01Z"},{"alias_kind":"pith_short_12","alias_value":"HMO6JIQFI5LE","created_at":"2026-07-05T07:55:01Z"},{"alias_kind":"pith_short_16","alias_value":"HMO6JIQFI5LE3XYV","created_at":"2026-07-05T07:55:01Z"},{"alias_kind":"pith_short_8","alias_value":"HMO6JIQF","created_at":"2026-07-05T07:55:01Z"}],"graph_snapshots":[{"event_id":"sha256:aacce935817dc5732d6175d1ebc20cf5361cce904ab8419c850c1bca94e2a8b6","target":"graph","created_at":"2026-07-05T07:55:01Z","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/2403.07261/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline meta-reinforcement learning (OMRL) proficiently allows an agent to tackle novel tasks while solely relying on a static dataset. For precise and efficient task identification, existing OMRL research suggests learning separate task representations that be incorporated with policy input, thus forming a context-based meta-policy. A major approach to train task representations is to adopt contrastive learning using multi-task offline data. The dataset typically encompasses interactions from various policies (i.e., the behavior policies), thus providing a plethora of contextual information r","authors_text":"Chengxing Jia, Chen-Xiao Gao, Fuxiang Zhang, Lei Yuan, Xu-Hui Liu, Yang Yu, Yi-Chen Li, Zongzhang Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-12T02:38:36Z","title":"Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07261","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":"sha256:47afc7cc74b24b59155a6e335b3ba12a38ae09b34457a7677da80ee97a52f434","target":"record","created_at":"2026-07-05T07:55:01Z","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":"912ecb4ee9774dd903cb8cd15d1d1518811e1880fc63ba3571d1aa25f4de3f94","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-12T02:38:36Z","title_canon_sha256":"938f24daffaa2056cfcaa31cf95c4061bccdecd88bc855da19414a17a18d0c22"},"schema_version":"1.0","source":{"id":"2403.07261","kind":"arxiv","version":1}},"canonical_sha256":"3b1de4a20547564ddf15dbcc4f574ea41a881ffc8935ff17f8cd81becb1b5483","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b1de4a20547564ddf15dbcc4f574ea41a881ffc8935ff17f8cd81becb1b5483","first_computed_at":"2026-07-05T07:55:01.238135Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:01.238135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b2imzXC5ryIdjmL24pxIJoHjupzoQLZrEj/eIogGtiZ2GD6HvW7t78mwwlQ22uFHqqlkJVmJGK1mgTSbUYUZAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:01.238564Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.07261","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47afc7cc74b24b59155a6e335b3ba12a38ae09b34457a7677da80ee97a52f434","sha256:aacce935817dc5732d6175d1ebc20cf5361cce904ab8419c850c1bca94e2a8b6"],"state_sha256":"644fe91e3d716a6c934031c40fae3cac89547736fd65512c0cc4119632b5d9c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yXHGX4iynGulWic+XufDzDVPv0xBjpi0feDCtWX5vjJvlhyrGORSAVBVRXonZ3zS9JZwpfOzcfYHbieTwwEKCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T18:46:03.079223Z","bundle_sha256":"a75612a6cd447c6d65e624a3a068b36ae73dcc61013240ec20840e1f5ae6b2e0"}}