{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AJ7RNTK2KKJQZHXTCI5XO32EPP","short_pith_number":"pith:AJ7RNTK2","schema_version":"1.0","canonical_sha256":"027f16cd5a52930c9ef3123b776f447bc741fca056a32d315b7b5e1b8da1e1a6","source":{"kind":"arxiv","id":"2511.01472","version":2},"attestation_state":"computed","paper":{"title":"AERMANI-VLM: Structured Prompting and Reasoning for Aerial Manipulation with Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Avirup Das, Rishabh Dev Yadav, Saksham Gupta, Sarthak Mishra, Spandan Roy, Wei Pan","submitted_at":"2025-11-03T11:31:55Z","abstract_excerpt":"The rapid progress of vision--language models (VLMs) has sparked growing interest in robotic control, where natural language can express the operation goals while visual feedback links perception to action. However, directly deploying VLM-driven policies on aerial manipulators remains unsafe and unreliable since the generated actions are often inconsistent, hallucination-prone, and dynamically infeasible for flight. In this work, we present AERMANI-VLM, the first framework to adapt pretrained VLMs for aerial manipulation by separating high-level reasoning from low-level control, without any ta"},"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":"2511.01472","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-11-03T11:31:55Z","cross_cats_sorted":[],"title_canon_sha256":"d318dbc605d5c9091058c6f05a71b402e836e1a0f70f9f12cabf88469cfe0e64","abstract_canon_sha256":"5aff6ae13d5ac7a8d0e98c95d8148bda3f592c45ecf11ada5854f148840df97f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:28.427896Z","signature_b64":"nDf0uRn6B1c7TWDDYAZw5+o6mGJNLI2EKF7glpplexRqgSCmwynJ9VSK/un1BQ/omw1vnC8dr2h/XCdT5U67CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"027f16cd5a52930c9ef3123b776f447bc741fca056a32d315b7b5e1b8da1e1a6","last_reissued_at":"2026-06-30T01:17:28.426843Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:28.426843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AERMANI-VLM: Structured Prompting and Reasoning for Aerial Manipulation with Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Avirup Das, Rishabh Dev Yadav, Saksham Gupta, Sarthak Mishra, Spandan Roy, Wei Pan","submitted_at":"2025-11-03T11:31:55Z","abstract_excerpt":"The rapid progress of vision--language models (VLMs) has sparked growing interest in robotic control, where natural language can express the operation goals while visual feedback links perception to action. However, directly deploying VLM-driven policies on aerial manipulators remains unsafe and unreliable since the generated actions are often inconsistent, hallucination-prone, and dynamically infeasible for flight. In this work, we present AERMANI-VLM, the first framework to adapt pretrained VLMs for aerial manipulation by separating high-level reasoning from low-level control, without any ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.01472","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/2511.01472/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":"2511.01472","created_at":"2026-06-30T01:17:28.426972+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.01472v2","created_at":"2026-06-30T01:17:28.426972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.01472","created_at":"2026-06-30T01:17:28.426972+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJ7RNTK2KKJQ","created_at":"2026-06-30T01:17:28.426972+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJ7RNTK2KKJQZHXT","created_at":"2026-06-30T01:17:28.426972+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJ7RNTK2","created_at":"2026-06-30T01:17:28.426972+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2601.15486","citing_title":"A Universal Large Language Model -- Drone Command and Control Interface","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02900","citing_title":"Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses","ref_index":263,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07705","citing_title":"Vision-Language Navigation for Aerial Robots: Towards the Era of Large Language Models","ref_index":84,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13654","citing_title":"Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap","ref_index":183,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AJ7RNTK2KKJQZHXTCI5XO32EPP","json":"https://pith.science/pith/AJ7RNTK2KKJQZHXTCI5XO32EPP.json","graph_json":"https://pith.science/api/pith-number/AJ7RNTK2KKJQZHXTCI5XO32EPP/graph.json","events_json":"https://pith.science/api/pith-number/AJ7RNTK2KKJQZHXTCI5XO32EPP/events.json","paper":"https://pith.science/paper/AJ7RNTK2"},"agent_actions":{"view_html":"https://pith.science/pith/AJ7RNTK2KKJQZHXTCI5XO32EPP","download_json":"https://pith.science/pith/AJ7RNTK2KKJQZHXTCI5XO32EPP.json","view_paper":"https://pith.science/paper/AJ7RNTK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.01472&json=true","fetch_graph":"https://pith.science/api/pith-number/AJ7RNTK2KKJQZHXTCI5XO32EPP/graph.json","fetch_events":"https://pith.science/api/pith-number/AJ7RNTK2KKJQZHXTCI5XO32EPP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJ7RNTK2KKJQZHXTCI5XO32EPP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJ7RNTK2KKJQZHXTCI5XO32EPP/action/storage_attestation","attest_author":"https://pith.science/pith/AJ7RNTK2KKJQZHXTCI5XO32EPP/action/author_attestation","sign_citation":"https://pith.science/pith/AJ7RNTK2KKJQZHXTCI5XO32EPP/action/citation_signature","submit_replication":"https://pith.science/pith/AJ7RNTK2KKJQZHXTCI5XO32EPP/action/replication_record"}},"created_at":"2026-06-30T01:17:28.426972+00:00","updated_at":"2026-06-30T01:17:28.426972+00:00"}