{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PTS7H7W652GKSDY2KYO4DFSETG","short_pith_number":"pith:PTS7H7W6","schema_version":"1.0","canonical_sha256":"7ce5f3fedeee8ca90f1a561dc1964499b565063b13859597ef2a17c008a832d4","source":{"kind":"arxiv","id":"2507.10087","version":1},"attestation_state":"computed","paper":{"title":"Foundation Model Driven Robotics: A Comprehensive Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ammar Waheed, Muhammad Tayyab Khan","submitted_at":"2025-07-14T09:13:07Z","abstract_excerpt":"The rapid emergence of foundation models, particularly Large Language Models (LLMs) and Vision-Language Models (VLMs), has introduced a transformative paradigm in robotics. These models offer powerful capabilities in semantic understanding, high-level reasoning, and cross-modal generalization, enabling significant advances in perception, planning, control, and human-robot interaction. This critical review provides a structured synthesis of recent developments, categorizing applications across simulation-driven design, open-world execution, sim-to-real transfer, and adaptable robotics. Unlike e"},"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":"2507.10087","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-14T09:13:07Z","cross_cats_sorted":[],"title_canon_sha256":"bae719f17851410e8071c43b9e7efc7174a736d2abc51671fb1728c33205c3ae","abstract_canon_sha256":"4e3bf9732ef8021b2b3abdaf001176014272f1d91af46b9e19e0624abcb35766"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:44.709060Z","signature_b64":"sufbRvzfBjNGX1bj5O85WYget89ad9AeTlyRZljieUMENuSua2As+ueYh/5+VRK8OOy0jlb8d7jM7swCsa9UCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ce5f3fedeee8ca90f1a561dc1964499b565063b13859597ef2a17c008a832d4","last_reissued_at":"2026-07-05T11:36:44.708464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:44.708464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Foundation Model Driven Robotics: A Comprehensive Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ammar Waheed, Muhammad Tayyab Khan","submitted_at":"2025-07-14T09:13:07Z","abstract_excerpt":"The rapid emergence of foundation models, particularly Large Language Models (LLMs) and Vision-Language Models (VLMs), has introduced a transformative paradigm in robotics. These models offer powerful capabilities in semantic understanding, high-level reasoning, and cross-modal generalization, enabling significant advances in perception, planning, control, and human-robot interaction. This critical review provides a structured synthesis of recent developments, categorizing applications across simulation-driven design, open-world execution, sim-to-real transfer, and adaptable robotics. Unlike e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10087","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/2507.10087/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":"2507.10087","created_at":"2026-07-05T11:36:44.708529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10087v1","created_at":"2026-07-05T11:36:44.708529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10087","created_at":"2026-07-05T11:36:44.708529+00:00"},{"alias_kind":"pith_short_12","alias_value":"PTS7H7W652GK","created_at":"2026-07-05T11:36:44.708529+00:00"},{"alias_kind":"pith_short_16","alias_value":"PTS7H7W652GKSDY2","created_at":"2026-07-05T11:36:44.708529+00:00"},{"alias_kind":"pith_short_8","alias_value":"PTS7H7W6","created_at":"2026-07-05T11:36:44.708529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24578","citing_title":"World Models as Group Actions","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04978","citing_title":"Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24002","citing_title":"IntentVLM: Open-Vocabulary Intention Recognition through Forward-Inverse Modeling with Video-Language Models","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13654","citing_title":"Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap","ref_index":92,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PTS7H7W652GKSDY2KYO4DFSETG","json":"https://pith.science/pith/PTS7H7W652GKSDY2KYO4DFSETG.json","graph_json":"https://pith.science/api/pith-number/PTS7H7W652GKSDY2KYO4DFSETG/graph.json","events_json":"https://pith.science/api/pith-number/PTS7H7W652GKSDY2KYO4DFSETG/events.json","paper":"https://pith.science/paper/PTS7H7W6"},"agent_actions":{"view_html":"https://pith.science/pith/PTS7H7W652GKSDY2KYO4DFSETG","download_json":"https://pith.science/pith/PTS7H7W652GKSDY2KYO4DFSETG.json","view_paper":"https://pith.science/paper/PTS7H7W6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10087&json=true","fetch_graph":"https://pith.science/api/pith-number/PTS7H7W652GKSDY2KYO4DFSETG/graph.json","fetch_events":"https://pith.science/api/pith-number/PTS7H7W652GKSDY2KYO4DFSETG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PTS7H7W652GKSDY2KYO4DFSETG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PTS7H7W652GKSDY2KYO4DFSETG/action/storage_attestation","attest_author":"https://pith.science/pith/PTS7H7W652GKSDY2KYO4DFSETG/action/author_attestation","sign_citation":"https://pith.science/pith/PTS7H7W652GKSDY2KYO4DFSETG/action/citation_signature","submit_replication":"https://pith.science/pith/PTS7H7W652GKSDY2KYO4DFSETG/action/replication_record"}},"created_at":"2026-07-05T11:36:44.708529+00:00","updated_at":"2026-07-05T11:36:44.708529+00:00"}