{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:IGLTH2OTLOSBY6UZ52T5RMPIB4","short_pith_number":"pith:IGLTH2OT","canonical_record":{"source":{"id":"2211.08016","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-15T10:00:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"71ccff25d7591b156691e73b8a7f4e719f4f1cb1e80e1b35921b53069651fcd9","abstract_canon_sha256":"1e3b7411a664033e0866471504e87f5b89015e6f5b6bcede56da0331c1e0abba"},"schema_version":"1.0"},"canonical_sha256":"419733e9d35ba41c7a99eea7d8b1e80f289e021665e2bb0bac760d9311ae82d2","source":{"kind":"arxiv","id":"2211.08016","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.08016","created_at":"2026-07-05T05:16:08Z"},{"alias_kind":"arxiv_version","alias_value":"2211.08016v1","created_at":"2026-07-05T05:16:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08016","created_at":"2026-07-05T05:16:08Z"},{"alias_kind":"pith_short_12","alias_value":"IGLTH2OTLOSB","created_at":"2026-07-05T05:16:08Z"},{"alias_kind":"pith_short_16","alias_value":"IGLTH2OTLOSBY6UZ","created_at":"2026-07-05T05:16:08Z"},{"alias_kind":"pith_short_8","alias_value":"IGLTH2OT","created_at":"2026-07-05T05:16:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:IGLTH2OTLOSBY6UZ52T5RMPIB4","target":"record","payload":{"canonical_record":{"source":{"id":"2211.08016","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-15T10:00:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"71ccff25d7591b156691e73b8a7f4e719f4f1cb1e80e1b35921b53069651fcd9","abstract_canon_sha256":"1e3b7411a664033e0866471504e87f5b89015e6f5b6bcede56da0331c1e0abba"},"schema_version":"1.0"},"canonical_sha256":"419733e9d35ba41c7a99eea7d8b1e80f289e021665e2bb0bac760d9311ae82d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:16:08.927191Z","signature_b64":"YfddaPg+dU3CWNpEG9+WKrW6bWJAYVnDrdbk85JFHu39AsY06X/UXMKXSlWbs/tvcsnKEbND0ZfHpJetH2cACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"419733e9d35ba41c7a99eea7d8b1e80f289e021665e2bb0bac760d9311ae82d2","last_reissued_at":"2026-07-05T05:16:08.926740Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:16:08.926740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.08016","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":"2026-07-05T05:16:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BTXl+N0mA/iSPlQDwpH/hW5iZMC5ieH3jpHvBZHSJmKeejPzPwjHMTHLnMCz1n70lV0gLVTTN8HG47+lOK9xAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:02:29.063978Z"},"content_sha256":"41cce68e046696c092fba4a02c0c0ed525ff8c53d9397bae636b6be6a33874ae","schema_version":"1.0","event_id":"sha256:41cce68e046696c092fba4a02c0c0ed525ff8c53d9397bae636b6be6a33874ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:IGLTH2OTLOSBY6UZ52T5RMPIB4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contextual Transformer for Offline Meta Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haifeng Zhang, Jun Wang, Runji Lin, Xian Hong Wu Fung, Xidong Feng, Yali Du, Yaodong Yang, Ye Li, Zhaowei Zhang","submitted_at":"2022-11-15T10:00:14Z","abstract_excerpt":"The pretrain-finetuning paradigm in large-scale sequence models has made significant progress in natural language processing and computer vision tasks. However, such a paradigm is still hindered by several challenges in Reinforcement Learning (RL), including the lack of self-supervised pretraining algorithms based on offline data and efficient fine-tuning/prompt-tuning over unseen downstream tasks. In this work, we explore how prompts can improve sequence modeling-based offline reinforcement learning (offline-RL) algorithms. Firstly, we propose prompt tuning for offline RL, where a context vec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08016","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/2211.08016/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":"2026-07-05T05:16:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dpx3l/nmygijVqQRJsV88KsSKje2yiDicGWRuWycMwB0CShdHOTKX0YfvDF0dVRykAyH2JH8uG/U2vBvG3rHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:02:29.064367Z"},"content_sha256":"71f2860d36bad4ccb01a1cd8c088c0557f4ee357a5fd9c6bfe87d60e851a346c","schema_version":"1.0","event_id":"sha256:71f2860d36bad4ccb01a1cd8c088c0557f4ee357a5fd9c6bfe87d60e851a346c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IGLTH2OTLOSBY6UZ52T5RMPIB4/bundle.json","state_url":"https://pith.science/pith/IGLTH2OTLOSBY6UZ52T5RMPIB4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IGLTH2OTLOSBY6UZ52T5RMPIB4/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":"2026-07-05T11:02:29Z","links":{"resolver":"https://pith.science/pith/IGLTH2OTLOSBY6UZ52T5RMPIB4","bundle":"https://pith.science/pith/IGLTH2OTLOSBY6UZ52T5RMPIB4/bundle.json","state":"https://pith.science/pith/IGLTH2OTLOSBY6UZ52T5RMPIB4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IGLTH2OTLOSBY6UZ52T5RMPIB4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IGLTH2OTLOSBY6UZ52T5RMPIB4","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":"1e3b7411a664033e0866471504e87f5b89015e6f5b6bcede56da0331c1e0abba","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-15T10:00:14Z","title_canon_sha256":"71ccff25d7591b156691e73b8a7f4e719f4f1cb1e80e1b35921b53069651fcd9"},"schema_version":"1.0","source":{"id":"2211.08016","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.08016","created_at":"2026-07-05T05:16:08Z"},{"alias_kind":"arxiv_version","alias_value":"2211.08016v1","created_at":"2026-07-05T05:16:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08016","created_at":"2026-07-05T05:16:08Z"},{"alias_kind":"pith_short_12","alias_value":"IGLTH2OTLOSB","created_at":"2026-07-05T05:16:08Z"},{"alias_kind":"pith_short_16","alias_value":"IGLTH2OTLOSBY6UZ","created_at":"2026-07-05T05:16:08Z"},{"alias_kind":"pith_short_8","alias_value":"IGLTH2OT","created_at":"2026-07-05T05:16:08Z"}],"graph_snapshots":[{"event_id":"sha256:71f2860d36bad4ccb01a1cd8c088c0557f4ee357a5fd9c6bfe87d60e851a346c","target":"graph","created_at":"2026-07-05T05:16:08Z","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/2211.08016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The pretrain-finetuning paradigm in large-scale sequence models has made significant progress in natural language processing and computer vision tasks. However, such a paradigm is still hindered by several challenges in Reinforcement Learning (RL), including the lack of self-supervised pretraining algorithms based on offline data and efficient fine-tuning/prompt-tuning over unseen downstream tasks. In this work, we explore how prompts can improve sequence modeling-based offline reinforcement learning (offline-RL) algorithms. Firstly, we propose prompt tuning for offline RL, where a context vec","authors_text":"Haifeng Zhang, Jun Wang, Runji Lin, Xian Hong Wu Fung, Xidong Feng, Yali Du, Yaodong Yang, Ye Li, Zhaowei Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-15T10:00:14Z","title":"Contextual Transformer for Offline Meta Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08016","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":"sha256:41cce68e046696c092fba4a02c0c0ed525ff8c53d9397bae636b6be6a33874ae","target":"record","created_at":"2026-07-05T05:16:08Z","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":"1e3b7411a664033e0866471504e87f5b89015e6f5b6bcede56da0331c1e0abba","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-15T10:00:14Z","title_canon_sha256":"71ccff25d7591b156691e73b8a7f4e719f4f1cb1e80e1b35921b53069651fcd9"},"schema_version":"1.0","source":{"id":"2211.08016","kind":"arxiv","version":1}},"canonical_sha256":"419733e9d35ba41c7a99eea7d8b1e80f289e021665e2bb0bac760d9311ae82d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"419733e9d35ba41c7a99eea7d8b1e80f289e021665e2bb0bac760d9311ae82d2","first_computed_at":"2026-07-05T05:16:08.926740Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:16:08.926740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YfddaPg+dU3CWNpEG9+WKrW6bWJAYVnDrdbk85JFHu39AsY06X/UXMKXSlWbs/tvcsnKEbND0ZfHpJetH2cACQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:16:08.927191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.08016","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41cce68e046696c092fba4a02c0c0ed525ff8c53d9397bae636b6be6a33874ae","sha256:71f2860d36bad4ccb01a1cd8c088c0557f4ee357a5fd9c6bfe87d60e851a346c"],"state_sha256":"704de7ffa34b1db603cf4631ad7b233ac26d421c2ccaa3ad4fd891a990fe675e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dw9yxjRzSDHVh05lLnJpdI7m2z36M0c0yh1mip1+JKHXtG/nOSL8noITsTOYuUbJhO/o7nNO7Qi2/loh/vivAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T11:02:29.066452Z","bundle_sha256":"9824a57a6a3d0003bdb40327fd43500f67529d1ba2c6c030fb46a61c59cc464f"}}