{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GDSQ2VPGEOCNC635W3KME3QWUP","short_pith_number":"pith:GDSQ2VPG","canonical_record":{"source":{"id":"2103.06386","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-10T23:31:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ebdbf213dcd21486914506e492f8cd166f650b61f45b16649e83ac2f49612b01","abstract_canon_sha256":"e01bd97fd686350223139365dbc8ff8297eb0ff1d440ca689da9821a9ef8b596"},"schema_version":"1.0"},"canonical_sha256":"30e50d55e62384d17b7db6d4c26e16a3c7a80b663d02bc223f52fd3fea990922","source":{"kind":"arxiv","id":"2103.06386","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.06386","created_at":"2026-07-05T02:22:08Z"},{"alias_kind":"arxiv_version","alias_value":"2103.06386v1","created_at":"2026-07-05T02:22:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06386","created_at":"2026-07-05T02:22:08Z"},{"alias_kind":"pith_short_12","alias_value":"GDSQ2VPGEOCN","created_at":"2026-07-05T02:22:08Z"},{"alias_kind":"pith_short_16","alias_value":"GDSQ2VPGEOCNC635","created_at":"2026-07-05T02:22:08Z"},{"alias_kind":"pith_short_8","alias_value":"GDSQ2VPG","created_at":"2026-07-05T02:22:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GDSQ2VPGEOCNC635W3KME3QWUP","target":"record","payload":{"canonical_record":{"source":{"id":"2103.06386","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-10T23:31:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ebdbf213dcd21486914506e492f8cd166f650b61f45b16649e83ac2f49612b01","abstract_canon_sha256":"e01bd97fd686350223139365dbc8ff8297eb0ff1d440ca689da9821a9ef8b596"},"schema_version":"1.0"},"canonical_sha256":"30e50d55e62384d17b7db6d4c26e16a3c7a80b663d02bc223f52fd3fea990922","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:08.605449Z","signature_b64":"oH0mZhf4HTUbJB45+lpVPGWL9JIwFTOcMmWfK1ZH5czU6GnkalcuOY3JVm1Q48fWgRcvTrf8mG8DRSYCUbrZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30e50d55e62384d17b7db6d4c26e16a3c7a80b663d02bc223f52fd3fea990922","last_reissued_at":"2026-07-05T02:22:08.604979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:08.604979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.06386","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":"2026-07-05T02:22:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/KvvUcBVp1NZ0aO/rb12rJO+fMq0L3rEHxBlnTb4gb05h8jz1MMRj7b/HbroLSWkhIWwIaxDQirSeblScrTYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:12:06.667092Z"},"content_sha256":"9a16e904219247e049e84863fb1e22d700b0406411b73fad80bdb063fbc4310b","schema_version":"1.0","event_id":"sha256:9a16e904219247e049e84863fb1e22d700b0406411b73fad80bdb063fbc4310b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GDSQ2VPGEOCNC635W3KME3QWUP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Context-Based Meta-Reinforcement Learning with Self-Supervised Trajectory Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bernie Wang, Bichen Wu, Kurt Keutzer, Simon Xu, Yang Gao","submitted_at":"2021-03-10T23:31:19Z","abstract_excerpt":"Meta-reinforcement learning typically requires orders of magnitude more samples than single task reinforcement learning methods. This is because meta-training needs to deal with more diverse distributions and train extra components such as context encoders. To address this, we propose a novel self-supervised learning task, which we named Trajectory Contrastive Learning (TCL), to improve meta-training. TCL adopts contrastive learning and trains a context encoder to predict whether two transition windows are sampled from the same trajectory. TCL leverages the natural hierarchical structure of co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06386","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/2103.06386/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":"2026-07-05T02:22:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ns6HYZAZZXJ7SzrMpzW4TJPEcxgDAZFXpA15nm5cSjWMkgPlMCPsyubdaiEVlsMJ2pwc5WbuIKCqHTM0WDqDDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:12:06.667604Z"},"content_sha256":"dac97fb5a5573adf074dc428ca932d5e6831c2ff5032bde8c9b7966f2ab2681a","schema_version":"1.0","event_id":"sha256:dac97fb5a5573adf074dc428ca932d5e6831c2ff5032bde8c9b7966f2ab2681a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GDSQ2VPGEOCNC635W3KME3QWUP/bundle.json","state_url":"https://pith.science/pith/GDSQ2VPGEOCNC635W3KME3QWUP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GDSQ2VPGEOCNC635W3KME3QWUP/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":"2026-08-10T19:12:06Z","links":{"resolver":"https://pith.science/pith/GDSQ2VPGEOCNC635W3KME3QWUP","bundle":"https://pith.science/pith/GDSQ2VPGEOCNC635W3KME3QWUP/bundle.json","state":"https://pith.science/pith/GDSQ2VPGEOCNC635W3KME3QWUP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GDSQ2VPGEOCNC635W3KME3QWUP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GDSQ2VPGEOCNC635W3KME3QWUP","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":"e01bd97fd686350223139365dbc8ff8297eb0ff1d440ca689da9821a9ef8b596","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-10T23:31:19Z","title_canon_sha256":"ebdbf213dcd21486914506e492f8cd166f650b61f45b16649e83ac2f49612b01"},"schema_version":"1.0","source":{"id":"2103.06386","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.06386","created_at":"2026-07-05T02:22:08Z"},{"alias_kind":"arxiv_version","alias_value":"2103.06386v1","created_at":"2026-07-05T02:22:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06386","created_at":"2026-07-05T02:22:08Z"},{"alias_kind":"pith_short_12","alias_value":"GDSQ2VPGEOCN","created_at":"2026-07-05T02:22:08Z"},{"alias_kind":"pith_short_16","alias_value":"GDSQ2VPGEOCNC635","created_at":"2026-07-05T02:22:08Z"},{"alias_kind":"pith_short_8","alias_value":"GDSQ2VPG","created_at":"2026-07-05T02:22:08Z"}],"graph_snapshots":[{"event_id":"sha256:dac97fb5a5573adf074dc428ca932d5e6831c2ff5032bde8c9b7966f2ab2681a","target":"graph","created_at":"2026-07-05T02:22:08Z","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/2103.06386/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Meta-reinforcement learning typically requires orders of magnitude more samples than single task reinforcement learning methods. This is because meta-training needs to deal with more diverse distributions and train extra components such as context encoders. To address this, we propose a novel self-supervised learning task, which we named Trajectory Contrastive Learning (TCL), to improve meta-training. TCL adopts contrastive learning and trains a context encoder to predict whether two transition windows are sampled from the same trajectory. TCL leverages the natural hierarchical structure of co","authors_text":"Bernie Wang, Bichen Wu, Kurt Keutzer, Simon Xu, Yang Gao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-10T23:31:19Z","title":"Improving Context-Based Meta-Reinforcement Learning with Self-Supervised Trajectory Contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06386","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":"sha256:9a16e904219247e049e84863fb1e22d700b0406411b73fad80bdb063fbc4310b","target":"record","created_at":"2026-07-05T02:22:08Z","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":"e01bd97fd686350223139365dbc8ff8297eb0ff1d440ca689da9821a9ef8b596","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-10T23:31:19Z","title_canon_sha256":"ebdbf213dcd21486914506e492f8cd166f650b61f45b16649e83ac2f49612b01"},"schema_version":"1.0","source":{"id":"2103.06386","kind":"arxiv","version":1}},"canonical_sha256":"30e50d55e62384d17b7db6d4c26e16a3c7a80b663d02bc223f52fd3fea990922","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30e50d55e62384d17b7db6d4c26e16a3c7a80b663d02bc223f52fd3fea990922","first_computed_at":"2026-07-05T02:22:08.604979Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:22:08.604979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oH0mZhf4HTUbJB45+lpVPGWL9JIwFTOcMmWfK1ZH5czU6GnkalcuOY3JVm1Q48fWgRcvTrf8mG8DRSYCUbrZAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:22:08.605449Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.06386","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a16e904219247e049e84863fb1e22d700b0406411b73fad80bdb063fbc4310b","sha256:dac97fb5a5573adf074dc428ca932d5e6831c2ff5032bde8c9b7966f2ab2681a"],"state_sha256":"54ebd58e5a21b333ae5d40b17251914d33d9c8ce641bf60da933c1c0f2dadc07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bw6djpfuVTo/KFJ2wTHdKT6inWYsNHQCBNYwEmBU2f3V5bhr+EhOUYo4LWKLhSyTZWs5nEZXJaZVt48nbfaWDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T19:12:06.673068Z","bundle_sha256":"266c8f4bc56b40a762898a7db2eebee04b1f1b68698338a6396a8a5a2b90cafa"}}