{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XUB2PUBROQSFUCS6HPZF3UYL7O","short_pith_number":"pith:XUB2PUBR","schema_version":"1.0","canonical_sha256":"bd03a7d03174245a0a5e3bf25dd30bfb9401a54082ca78b5edc11db0c5310662","source":{"kind":"arxiv","id":"2505.08189","version":2},"attestation_state":"computed","paper":{"title":"DSADF: Thinking Fast and Slow for Decision Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benteng Chen, Dongfei Cui, Haoming Wang, Jun Yan, Shufei Zhang, Weida Wang, Zeke Xie, Zhihao Dou","submitted_at":"2025-05-13T02:58:04Z","abstract_excerpt":"Although Reinforcement Learning (RL) agents are effective in well-defined environments, they often struggle to generalize their learned policies to dynamic settings due to their reliance on trial-and-error interactions. Recent work has explored applying Large Language Models (LLMs) or Vision Language Models (VLMs) to boost the generalization of RL agents through policy optimization guidance or prior knowledge. However, these approaches often lack seamless coordination between the RL agent and the foundation model, leading to unreasonable decision-making in unfamiliar environments and efficienc"},"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":"2505.08189","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-13T02:58:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d905f9dfb9fdbff0addb3e4c21f81cab5edd9e8da0da1549530619aff8331453","abstract_canon_sha256":"97589ce1d719097ac29a88498a26454e2021c9026145d210a6ea87438e6926aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:28.873069Z","signature_b64":"YQdYh591Hq4JAVYcchLEtratJ4n9doNZvYEIAwgUS03sDf5pbaNsCBuoCZ4zFxzCpYqcOQmiJvNhKNCFub2NBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd03a7d03174245a0a5e3bf25dd30bfb9401a54082ca78b5edc11db0c5310662","last_reissued_at":"2026-07-05T11:58:28.872565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:28.872565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DSADF: Thinking Fast and Slow for Decision Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benteng Chen, Dongfei Cui, Haoming Wang, Jun Yan, Shufei Zhang, Weida Wang, Zeke Xie, Zhihao Dou","submitted_at":"2025-05-13T02:58:04Z","abstract_excerpt":"Although Reinforcement Learning (RL) agents are effective in well-defined environments, they often struggle to generalize their learned policies to dynamic settings due to their reliance on trial-and-error interactions. Recent work has explored applying Large Language Models (LLMs) or Vision Language Models (VLMs) to boost the generalization of RL agents through policy optimization guidance or prior knowledge. However, these approaches often lack seamless coordination between the RL agent and the foundation model, leading to unreasonable decision-making in unfamiliar environments and efficienc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08189","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/2505.08189/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":"2505.08189","created_at":"2026-07-05T11:58:28.872623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.08189v2","created_at":"2026-07-05T11:58:28.872623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08189","created_at":"2026-07-05T11:58:28.872623+00:00"},{"alias_kind":"pith_short_12","alias_value":"XUB2PUBROQSF","created_at":"2026-07-05T11:58:28.872623+00:00"},{"alias_kind":"pith_short_16","alias_value":"XUB2PUBROQSFUCS6","created_at":"2026-07-05T11:58:28.872623+00:00"},{"alias_kind":"pith_short_8","alias_value":"XUB2PUBR","created_at":"2026-07-05T11:58:28.872623+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/XUB2PUBROQSFUCS6HPZF3UYL7O","json":"https://pith.science/pith/XUB2PUBROQSFUCS6HPZF3UYL7O.json","graph_json":"https://pith.science/api/pith-number/XUB2PUBROQSFUCS6HPZF3UYL7O/graph.json","events_json":"https://pith.science/api/pith-number/XUB2PUBROQSFUCS6HPZF3UYL7O/events.json","paper":"https://pith.science/paper/XUB2PUBR"},"agent_actions":{"view_html":"https://pith.science/pith/XUB2PUBROQSFUCS6HPZF3UYL7O","download_json":"https://pith.science/pith/XUB2PUBROQSFUCS6HPZF3UYL7O.json","view_paper":"https://pith.science/paper/XUB2PUBR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.08189&json=true","fetch_graph":"https://pith.science/api/pith-number/XUB2PUBROQSFUCS6HPZF3UYL7O/graph.json","fetch_events":"https://pith.science/api/pith-number/XUB2PUBROQSFUCS6HPZF3UYL7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XUB2PUBROQSFUCS6HPZF3UYL7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XUB2PUBROQSFUCS6HPZF3UYL7O/action/storage_attestation","attest_author":"https://pith.science/pith/XUB2PUBROQSFUCS6HPZF3UYL7O/action/author_attestation","sign_citation":"https://pith.science/pith/XUB2PUBROQSFUCS6HPZF3UYL7O/action/citation_signature","submit_replication":"https://pith.science/pith/XUB2PUBROQSFUCS6HPZF3UYL7O/action/replication_record"}},"created_at":"2026-07-05T11:58:28.872623+00:00","updated_at":"2026-07-05T11:58:28.872623+00:00"}