{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LOXXGQVLPHJWRRDAEFR5UME5RB","short_pith_number":"pith:LOXXGQVL","schema_version":"1.0","canonical_sha256":"5baf7342ab79d368c4602163da309d886453c4a920ff79517b6713026434f06c","source":{"kind":"arxiv","id":"2503.24388","version":1},"attestation_state":"computed","paper":{"title":"RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Gaoang Wang, Haian Huang, Jianfei Gao, Kai Chen, Kuikun Liu, Wenwei Zhang, Zhonghan Zhao","submitted_at":"2025-03-31T17:59:52Z","abstract_excerpt":"Reasoning before action and imagining potential outcomes (i.e., world models) are essential for embodied agents operating in complex open-world environments. Yet, prior work either incorporates only one of these abilities in an end-to-end agent or integrates multiple specialized models into an agent system, limiting the learning efficiency and generalization of the policy. Thus, this paper makes the first attempt to synergize Reasoning and Imagination in an end-to-end Generalist policy, termed RIG. To train RIG in an end-to-end manner, we construct a data pipeline that progressively integrates"},"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":"2503.24388","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-31T17:59:52Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"8d6a679ca85c7b03472bf92ab1291a8d7f8e24e1a8b18149ddeb334582868825","abstract_canon_sha256":"8386016de5d69a1130508892230f265d84f5c3c041480b34de96359ecf76d51c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:17.827484Z","signature_b64":"YyraMEIzbmawcBo8zdJNARb07iIvLnn7xAwNTz1ximoRGmq4IkJCxcLZMF1OYyeZIcLVqcyxw77qR0gThJ9/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5baf7342ab79d368c4602163da309d886453c4a920ff79517b6713026434f06c","last_reissued_at":"2026-07-05T10:42:17.827040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:17.827040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Gaoang Wang, Haian Huang, Jianfei Gao, Kai Chen, Kuikun Liu, Wenwei Zhang, Zhonghan Zhao","submitted_at":"2025-03-31T17:59:52Z","abstract_excerpt":"Reasoning before action and imagining potential outcomes (i.e., world models) are essential for embodied agents operating in complex open-world environments. Yet, prior work either incorporates only one of these abilities in an end-to-end agent or integrates multiple specialized models into an agent system, limiting the learning efficiency and generalization of the policy. Thus, this paper makes the first attempt to synergize Reasoning and Imagination in an end-to-end Generalist policy, termed RIG. To train RIG in an end-to-end manner, we construct a data pipeline that progressively integrates"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.24388","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/2503.24388/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":"2503.24388","created_at":"2026-07-05T10:42:17.827097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.24388v1","created_at":"2026-07-05T10:42:17.827097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.24388","created_at":"2026-07-05T10:42:17.827097+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOXXGQVLPHJW","created_at":"2026-07-05T10:42:17.827097+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOXXGQVLPHJWRRDA","created_at":"2026-07-05T10:42:17.827097+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOXXGQVL","created_at":"2026-07-05T10:42:17.827097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02951","citing_title":"Adaptive Graph Pruning for Multi-Agent Communication","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LOXXGQVLPHJWRRDAEFR5UME5RB","json":"https://pith.science/pith/LOXXGQVLPHJWRRDAEFR5UME5RB.json","graph_json":"https://pith.science/api/pith-number/LOXXGQVLPHJWRRDAEFR5UME5RB/graph.json","events_json":"https://pith.science/api/pith-number/LOXXGQVLPHJWRRDAEFR5UME5RB/events.json","paper":"https://pith.science/paper/LOXXGQVL"},"agent_actions":{"view_html":"https://pith.science/pith/LOXXGQVLPHJWRRDAEFR5UME5RB","download_json":"https://pith.science/pith/LOXXGQVLPHJWRRDAEFR5UME5RB.json","view_paper":"https://pith.science/paper/LOXXGQVL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.24388&json=true","fetch_graph":"https://pith.science/api/pith-number/LOXXGQVLPHJWRRDAEFR5UME5RB/graph.json","fetch_events":"https://pith.science/api/pith-number/LOXXGQVLPHJWRRDAEFR5UME5RB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOXXGQVLPHJWRRDAEFR5UME5RB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOXXGQVLPHJWRRDAEFR5UME5RB/action/storage_attestation","attest_author":"https://pith.science/pith/LOXXGQVLPHJWRRDAEFR5UME5RB/action/author_attestation","sign_citation":"https://pith.science/pith/LOXXGQVLPHJWRRDAEFR5UME5RB/action/citation_signature","submit_replication":"https://pith.science/pith/LOXXGQVLPHJWRRDAEFR5UME5RB/action/replication_record"}},"created_at":"2026-07-05T10:42:17.827097+00:00","updated_at":"2026-07-05T10:42:17.827097+00:00"}