{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:IMYLM7G2BPNCWO25SPV2XH3HWW","short_pith_number":"pith:IMYLM7G2","canonical_record":{"source":{"id":"2102.10774","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-22T05:05:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b214fbeffa48104935a972c7575809a4587d04a87bf0d6ad3a27e08985291a9","abstract_canon_sha256":"1beb3df8bd4b9b27997673009e39cda021fe9da4d25afb7405605057da10237e"},"schema_version":"1.0"},"canonical_sha256":"4330b67cda0bda2b3b5d93ebab9f67b58852e24997cd17c1a319639f9a7e35f1","source":{"kind":"arxiv","id":"2102.10774","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.10774","created_at":"2026-07-05T03:22:45Z"},{"alias_kind":"arxiv_version","alias_value":"2102.10774v2","created_at":"2026-07-05T03:22:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10774","created_at":"2026-07-05T03:22:45Z"},{"alias_kind":"pith_short_12","alias_value":"IMYLM7G2BPNC","created_at":"2026-07-05T03:22:45Z"},{"alias_kind":"pith_short_16","alias_value":"IMYLM7G2BPNCWO25","created_at":"2026-07-05T03:22:45Z"},{"alias_kind":"pith_short_8","alias_value":"IMYLM7G2","created_at":"2026-07-05T03:22:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:IMYLM7G2BPNCWO25SPV2XH3HWW","target":"record","payload":{"canonical_record":{"source":{"id":"2102.10774","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-22T05:05:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b214fbeffa48104935a972c7575809a4587d04a87bf0d6ad3a27e08985291a9","abstract_canon_sha256":"1beb3df8bd4b9b27997673009e39cda021fe9da4d25afb7405605057da10237e"},"schema_version":"1.0"},"canonical_sha256":"4330b67cda0bda2b3b5d93ebab9f67b58852e24997cd17c1a319639f9a7e35f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:45.257991Z","signature_b64":"JMWZYV4YepY9g9n2XKGGXsx+PsnuMjrVoVxtXAFYnXmuZ6UJkdkXnw76PaV9E0x3FYYuTIXKlTdgp/kMPUCBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4330b67cda0bda2b3b5d93ebab9f67b58852e24997cd17c1a319639f9a7e35f1","last_reissued_at":"2026-07-05T03:22:45.257555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:45.257555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.10774","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:22:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R2EHGgZAyOzQIBn3yFwZ323VWQ0UIr1s2haeQyXTob8mAzcHVGrx1OSh89UlnJXl39JrpHffCD2nPgt29vHjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:58:31.921033Z"},"content_sha256":"d67218aeeecab2b8716dd75519a3dc124eb2491fb82665561b6950b79a7fcca1","schema_version":"1.0","event_id":"sha256:d67218aeeecab2b8716dd75519a3dc124eb2491fb82665561b6950b79a7fcca1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:IMYLM7G2BPNCWO25SPV2XH3HWW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dijun Luo, Junzhou Huang, Lanqing Li, Mingzhe Chen, Siteng Luo, Yuanhao Huang","submitted_at":"2021-02-22T05:05:16Z","abstract_excerpt":"Meta-learning for offline reinforcement learning (OMRL) is an understudied problem with tremendous potential impact by enabling RL algorithms in many real-world applications. A popular solution to the problem is to infer task identity as augmented state using a context-based encoder, for which efficient learning of robust task representations remains an open challenge. In this work, we provably improve upon one of the SOTA OMRL algorithms, FOCAL, by incorporating intra-task attention mechanism and inter-task contrastive learning objectives, to robustify task representation learning against spa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10774","kind":"arxiv","version":2},"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/2102.10774/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":"2026-07-05T03:22:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T1sVc7GIiPrTSvkzqmHUDEiFt0AFUChd6bDHTSZwgflP5/IWFWOsVrqsmhrdIrpPgVXTI14WMKvxB5iWe2IEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:58:31.921415Z"},"content_sha256":"647fbd17bbddb9addbb11d50d65998b2b26068e3e2a57d6d1526e388ffb3ebc0","schema_version":"1.0","event_id":"sha256:647fbd17bbddb9addbb11d50d65998b2b26068e3e2a57d6d1526e388ffb3ebc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IMYLM7G2BPNCWO25SPV2XH3HWW/bundle.json","state_url":"https://pith.science/pith/IMYLM7G2BPNCWO25SPV2XH3HWW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IMYLM7G2BPNCWO25SPV2XH3HWW/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":"2026-07-07T11:58:31Z","links":{"resolver":"https://pith.science/pith/IMYLM7G2BPNCWO25SPV2XH3HWW","bundle":"https://pith.science/pith/IMYLM7G2BPNCWO25SPV2XH3HWW/bundle.json","state":"https://pith.science/pith/IMYLM7G2BPNCWO25SPV2XH3HWW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IMYLM7G2BPNCWO25SPV2XH3HWW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IMYLM7G2BPNCWO25SPV2XH3HWW","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":"1beb3df8bd4b9b27997673009e39cda021fe9da4d25afb7405605057da10237e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-22T05:05:16Z","title_canon_sha256":"7b214fbeffa48104935a972c7575809a4587d04a87bf0d6ad3a27e08985291a9"},"schema_version":"1.0","source":{"id":"2102.10774","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.10774","created_at":"2026-07-05T03:22:45Z"},{"alias_kind":"arxiv_version","alias_value":"2102.10774v2","created_at":"2026-07-05T03:22:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10774","created_at":"2026-07-05T03:22:45Z"},{"alias_kind":"pith_short_12","alias_value":"IMYLM7G2BPNC","created_at":"2026-07-05T03:22:45Z"},{"alias_kind":"pith_short_16","alias_value":"IMYLM7G2BPNCWO25","created_at":"2026-07-05T03:22:45Z"},{"alias_kind":"pith_short_8","alias_value":"IMYLM7G2","created_at":"2026-07-05T03:22:45Z"}],"graph_snapshots":[{"event_id":"sha256:647fbd17bbddb9addbb11d50d65998b2b26068e3e2a57d6d1526e388ffb3ebc0","target":"graph","created_at":"2026-07-05T03:22:45Z","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/2102.10774/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Meta-learning for offline reinforcement learning (OMRL) is an understudied problem with tremendous potential impact by enabling RL algorithms in many real-world applications. A popular solution to the problem is to infer task identity as augmented state using a context-based encoder, for which efficient learning of robust task representations remains an open challenge. In this work, we provably improve upon one of the SOTA OMRL algorithms, FOCAL, by incorporating intra-task attention mechanism and inter-task contrastive learning objectives, to robustify task representation learning against spa","authors_text":"Dijun Luo, Junzhou Huang, Lanqing Li, Mingzhe Chen, Siteng Luo, Yuanhao Huang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-22T05:05:16Z","title":"Provably Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10774","kind":"arxiv","version":2},"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:d67218aeeecab2b8716dd75519a3dc124eb2491fb82665561b6950b79a7fcca1","target":"record","created_at":"2026-07-05T03:22:45Z","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":"1beb3df8bd4b9b27997673009e39cda021fe9da4d25afb7405605057da10237e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-22T05:05:16Z","title_canon_sha256":"7b214fbeffa48104935a972c7575809a4587d04a87bf0d6ad3a27e08985291a9"},"schema_version":"1.0","source":{"id":"2102.10774","kind":"arxiv","version":2}},"canonical_sha256":"4330b67cda0bda2b3b5d93ebab9f67b58852e24997cd17c1a319639f9a7e35f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4330b67cda0bda2b3b5d93ebab9f67b58852e24997cd17c1a319639f9a7e35f1","first_computed_at":"2026-07-05T03:22:45.257555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:45.257555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JMWZYV4YepY9g9n2XKGGXsx+PsnuMjrVoVxtXAFYnXmuZ6UJkdkXnw76PaV9E0x3FYYuTIXKlTdgp/kMPUCBCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:45.257991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.10774","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d67218aeeecab2b8716dd75519a3dc124eb2491fb82665561b6950b79a7fcca1","sha256:647fbd17bbddb9addbb11d50d65998b2b26068e3e2a57d6d1526e388ffb3ebc0"],"state_sha256":"a0c6b53f8ac392676e877d5ea077fe45dadc6473c6a59803cc95a95d352c22f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0sbp5FowrcWppnN8iNg+xlh7a9/0GkxjoshDm71lgE9e39oZAw6+5bBmzAPmDigMH17ST/xxXtI89F8G8l1NDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:58:31.923366Z","bundle_sha256":"a6fe6ee80070a8dff6fc6182eae1b35747be60aede1b356d1fe09b8f73207de0"}}