{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HSYI7HOKIOCB4FGRRLTFNWJ3TH","short_pith_number":"pith:HSYI7HOK","schema_version":"1.0","canonical_sha256":"3cb08f9dca43841e14d18ae656d93b99dd45dc5206af0b4551a012be275f5b1d","source":{"kind":"arxiv","id":"2507.12496","version":1},"attestation_state":"computed","paper":{"title":"FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"De-Chuan Zhan, Le Gan, Rui Yu, ShengHua Wan, Yucen Wang","submitted_at":"2025-07-15T21:49:49Z","abstract_excerpt":"Foundation Models (FMs) and World Models (WMs) offer complementary strengths in task generalization at different levels. In this work, we propose FOUNDER, a framework that integrates the generalizable knowledge embedded in FMs with the dynamic modeling capabilities of WMs to enable open-ended task solving in embodied environments in a reward-free manner. We learn a mapping function that grounds FM representations in the WM state space, effectively inferring the agent's physical states in the world simulator from external observations. This mapping enables the learning of a goal-conditioned pol"},"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":"2507.12496","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-07-15T21:49:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3cd520e144bcacff3b217c7de0d13408151dbaa63cb8f2c1a619a3785a50e25f","abstract_canon_sha256":"04c9d6cbf6e035b353be7f4cf4cb909cdb2729a0d70e2944258ad78fb468ff99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:33.020849Z","signature_b64":"+3/Su/4ajNI2544ZqOaqxLpxdb+N5+dWbSt/y/aLY+6MclFbx+v7aWz0lSizRx+BmRifcIPHELK+GCzpF6XZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cb08f9dca43841e14d18ae656d93b99dd45dc5206af0b4551a012be275f5b1d","last_reissued_at":"2026-07-05T11:38:33.020257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:33.020257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"De-Chuan Zhan, Le Gan, Rui Yu, ShengHua Wan, Yucen Wang","submitted_at":"2025-07-15T21:49:49Z","abstract_excerpt":"Foundation Models (FMs) and World Models (WMs) offer complementary strengths in task generalization at different levels. In this work, we propose FOUNDER, a framework that integrates the generalizable knowledge embedded in FMs with the dynamic modeling capabilities of WMs to enable open-ended task solving in embodied environments in a reward-free manner. We learn a mapping function that grounds FM representations in the WM state space, effectively inferring the agent's physical states in the world simulator from external observations. This mapping enables the learning of a goal-conditioned pol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12496","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/2507.12496/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":"2507.12496","created_at":"2026-07-05T11:38:33.020325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12496v1","created_at":"2026-07-05T11:38:33.020325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12496","created_at":"2026-07-05T11:38:33.020325+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSYI7HOKIOCB","created_at":"2026-07-05T11:38:33.020325+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSYI7HOKIOCB4FGR","created_at":"2026-07-05T11:38:33.020325+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSYI7HOK","created_at":"2026-07-05T11:38:33.020325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12334","citing_title":"Reinforcing VLAs in Task-Agnostic World Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12334","citing_title":"Reinforcing VLAs in Task-Agnostic World Models","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HSYI7HOKIOCB4FGRRLTFNWJ3TH","json":"https://pith.science/pith/HSYI7HOKIOCB4FGRRLTFNWJ3TH.json","graph_json":"https://pith.science/api/pith-number/HSYI7HOKIOCB4FGRRLTFNWJ3TH/graph.json","events_json":"https://pith.science/api/pith-number/HSYI7HOKIOCB4FGRRLTFNWJ3TH/events.json","paper":"https://pith.science/paper/HSYI7HOK"},"agent_actions":{"view_html":"https://pith.science/pith/HSYI7HOKIOCB4FGRRLTFNWJ3TH","download_json":"https://pith.science/pith/HSYI7HOKIOCB4FGRRLTFNWJ3TH.json","view_paper":"https://pith.science/paper/HSYI7HOK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12496&json=true","fetch_graph":"https://pith.science/api/pith-number/HSYI7HOKIOCB4FGRRLTFNWJ3TH/graph.json","fetch_events":"https://pith.science/api/pith-number/HSYI7HOKIOCB4FGRRLTFNWJ3TH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSYI7HOKIOCB4FGRRLTFNWJ3TH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSYI7HOKIOCB4FGRRLTFNWJ3TH/action/storage_attestation","attest_author":"https://pith.science/pith/HSYI7HOKIOCB4FGRRLTFNWJ3TH/action/author_attestation","sign_citation":"https://pith.science/pith/HSYI7HOKIOCB4FGRRLTFNWJ3TH/action/citation_signature","submit_replication":"https://pith.science/pith/HSYI7HOKIOCB4FGRRLTFNWJ3TH/action/replication_record"}},"created_at":"2026-07-05T11:38:33.020325+00:00","updated_at":"2026-07-05T11:38:33.020325+00:00"}