{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IGLTH2OTLOSBY6UZ52T5RMPIB4","short_pith_number":"pith:IGLTH2OT","schema_version":"1.0","canonical_sha256":"419733e9d35ba41c7a99eea7d8b1e80f289e021665e2bb0bac760d9311ae82d2","source":{"kind":"arxiv","id":"2211.08016","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2211.08016","created_at":"2026-07-05T05:16:08.926795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.08016v1","created_at":"2026-07-05T05:16:08.926795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08016","created_at":"2026-07-05T05:16:08.926795+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGLTH2OTLOSB","created_at":"2026-07-05T05:16:08.926795+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGLTH2OTLOSBY6UZ","created_at":"2026-07-05T05:16:08.926795+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGLTH2OT","created_at":"2026-07-05T05:16:08.926795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13472","citing_title":"Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IGLTH2OTLOSBY6UZ52T5RMPIB4","json":"https://pith.science/pith/IGLTH2OTLOSBY6UZ52T5RMPIB4.json","graph_json":"https://pith.science/api/pith-number/IGLTH2OTLOSBY6UZ52T5RMPIB4/graph.json","events_json":"https://pith.science/api/pith-number/IGLTH2OTLOSBY6UZ52T5RMPIB4/events.json","paper":"https://pith.science/paper/IGLTH2OT"},"agent_actions":{"view_html":"https://pith.science/pith/IGLTH2OTLOSBY6UZ52T5RMPIB4","download_json":"https://pith.science/pith/IGLTH2OTLOSBY6UZ52T5RMPIB4.json","view_paper":"https://pith.science/paper/IGLTH2OT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.08016&json=true","fetch_graph":"https://pith.science/api/pith-number/IGLTH2OTLOSBY6UZ52T5RMPIB4/graph.json","fetch_events":"https://pith.science/api/pith-number/IGLTH2OTLOSBY6UZ52T5RMPIB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGLTH2OTLOSBY6UZ52T5RMPIB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGLTH2OTLOSBY6UZ52T5RMPIB4/action/storage_attestation","attest_author":"https://pith.science/pith/IGLTH2OTLOSBY6UZ52T5RMPIB4/action/author_attestation","sign_citation":"https://pith.science/pith/IGLTH2OTLOSBY6UZ52T5RMPIB4/action/citation_signature","submit_replication":"https://pith.science/pith/IGLTH2OTLOSBY6UZ52T5RMPIB4/action/replication_record"}},"created_at":"2026-07-05T05:16:08.926795+00:00","updated_at":"2026-07-05T05:16:08.926795+00:00"}