{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X4ZFC2CRU7JRHPUJTDM5XYRMLH","short_pith_number":"pith:X4ZFC2CR","schema_version":"1.0","canonical_sha256":"bf32516851a7d313be8998d9dbe22c59e9efa87857c9569535692de0db7ad34c","source":{"kind":"arxiv","id":"2606.00780","version":1},"attestation_state":"computed","paper":{"title":"Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fuyuan Qian, Menglong Zhang, Quanying Liu, Song Wang","submitted_at":"2026-05-30T15:53:03Z","abstract_excerpt":"Offline meta-reinforcement learning leverages static datasets to enable agents to generalize to unseen environments by combining offline efficiency with meta-learning adaptability, yet it faces key challenges from context and policy distribution shifts. These issues hinder agents from adapting to online environments, and are further exacerbated under sparse-reward settings. As a result, agents often become trapped in an inherent pattern dilemma, failing to achieve robust generalization. In this work, we propose a novel framework that integrates information-theoretic task representation learnin"},"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":"2606.00780","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T15:53:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fd1162a4446564bd92a1dceec2aa8a59881c054a61ac6321bf861d8eba5980ed","abstract_canon_sha256":"ea7e4d91f8f25b232a425e8ac20b65433f10669dd8987305ce8d4d2c6ac463af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:05.539815Z","signature_b64":"Dr0YsV/t98iB/hbpwkkacd9rQ92fUXlmqgReAeRmhVZcMd4B+7G7edMdbICqS/1rj1Aynk0L4lvwDiHHci7HCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf32516851a7d313be8998d9dbe22c59e9efa87857c9569535692de0db7ad34c","last_reissued_at":"2026-06-02T01:04:05.539447Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:05.539447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fuyuan Qian, Menglong Zhang, Quanying Liu, Song Wang","submitted_at":"2026-05-30T15:53:03Z","abstract_excerpt":"Offline meta-reinforcement learning leverages static datasets to enable agents to generalize to unseen environments by combining offline efficiency with meta-learning adaptability, yet it faces key challenges from context and policy distribution shifts. These issues hinder agents from adapting to online environments, and are further exacerbated under sparse-reward settings. As a result, agents often become trapped in an inherent pattern dilemma, failing to achieve robust generalization. In this work, we propose a novel framework that integrates information-theoretic task representation learnin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00780","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/2606.00780/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":"2606.00780","created_at":"2026-06-02T01:04:05.539506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00780v1","created_at":"2026-06-02T01:04:05.539506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00780","created_at":"2026-06-02T01:04:05.539506+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4ZFC2CRU7JR","created_at":"2026-06-02T01:04:05.539506+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4ZFC2CRU7JRHPUJ","created_at":"2026-06-02T01:04:05.539506+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4ZFC2CR","created_at":"2026-06-02T01:04:05.539506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X4ZFC2CRU7JRHPUJTDM5XYRMLH","json":"https://pith.science/pith/X4ZFC2CRU7JRHPUJTDM5XYRMLH.json","graph_json":"https://pith.science/api/pith-number/X4ZFC2CRU7JRHPUJTDM5XYRMLH/graph.json","events_json":"https://pith.science/api/pith-number/X4ZFC2CRU7JRHPUJTDM5XYRMLH/events.json","paper":"https://pith.science/paper/X4ZFC2CR"},"agent_actions":{"view_html":"https://pith.science/pith/X4ZFC2CRU7JRHPUJTDM5XYRMLH","download_json":"https://pith.science/pith/X4ZFC2CRU7JRHPUJTDM5XYRMLH.json","view_paper":"https://pith.science/paper/X4ZFC2CR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00780&json=true","fetch_graph":"https://pith.science/api/pith-number/X4ZFC2CRU7JRHPUJTDM5XYRMLH/graph.json","fetch_events":"https://pith.science/api/pith-number/X4ZFC2CRU7JRHPUJTDM5XYRMLH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4ZFC2CRU7JRHPUJTDM5XYRMLH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4ZFC2CRU7JRHPUJTDM5XYRMLH/action/storage_attestation","attest_author":"https://pith.science/pith/X4ZFC2CRU7JRHPUJTDM5XYRMLH/action/author_attestation","sign_citation":"https://pith.science/pith/X4ZFC2CRU7JRHPUJTDM5XYRMLH/action/citation_signature","submit_replication":"https://pith.science/pith/X4ZFC2CRU7JRHPUJTDM5XYRMLH/action/replication_record"}},"created_at":"2026-06-02T01:04:05.539506+00:00","updated_at":"2026-06-02T01:04:05.539506+00:00"}