{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AJ7RNTK2KKJQZHXTCI5XO32EPP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5aff6ae13d5ac7a8d0e98c95d8148bda3f592c45ecf11ada5854f148840df97f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-11-03T11:31:55Z","title_canon_sha256":"d318dbc605d5c9091058c6f05a71b402e836e1a0f70f9f12cabf88469cfe0e64"},"schema_version":"1.0","source":{"id":"2511.01472","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.01472","created_at":"2026-06-30T01:17:28Z"},{"alias_kind":"arxiv_version","alias_value":"2511.01472v2","created_at":"2026-06-30T01:17:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.01472","created_at":"2026-06-30T01:17:28Z"},{"alias_kind":"pith_short_12","alias_value":"AJ7RNTK2KKJQ","created_at":"2026-06-30T01:17:28Z"},{"alias_kind":"pith_short_16","alias_value":"AJ7RNTK2KKJQZHXT","created_at":"2026-06-30T01:17:28Z"},{"alias_kind":"pith_short_8","alias_value":"AJ7RNTK2","created_at":"2026-06-30T01:17:28Z"}],"graph_snapshots":[{"event_id":"sha256:109764252ad720e43c72792e90e7ad72482efc787f0578bb51909e9546a21968","target":"graph","created_at":"2026-06-30T01:17:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2511.01472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Avirup Das, Rishabh Dev Yadav, Saksham Gupta, Sarthak Mishra, Spandan Roy, Wei Pan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-11-03T11:31:55Z","title":"AERMANI-VLM: Structured Prompting and Reasoning for Aerial Manipulation with Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.01472","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:218bb526e12206916afc4614e24fd7d146174d4011cadd73641d1cc8476fc2f3","target":"record","created_at":"2026-06-30T01:17:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5aff6ae13d5ac7a8d0e98c95d8148bda3f592c45ecf11ada5854f148840df97f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-11-03T11:31:55Z","title_canon_sha256":"d318dbc605d5c9091058c6f05a71b402e836e1a0f70f9f12cabf88469cfe0e64"},"schema_version":"1.0","source":{"id":"2511.01472","kind":"arxiv","version":2}},"canonical_sha256":"027f16cd5a52930c9ef3123b776f447bc741fca056a32d315b7b5e1b8da1e1a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"027f16cd5a52930c9ef3123b776f447bc741fca056a32d315b7b5e1b8da1e1a6","first_computed_at":"2026-06-30T01:17:28.426843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:17:28.426843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nDf0uRn6B1c7TWDDYAZw5+o6mGJNLI2EKF7glpplexRqgSCmwynJ9VSK/un1BQ/omw1vnC8dr2h/XCdT5U67CQ==","signature_status":"signed_v1","signed_at":"2026-06-30T01:17:28.427896Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.01472","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:218bb526e12206916afc4614e24fd7d146174d4011cadd73641d1cc8476fc2f3","sha256:109764252ad720e43c72792e90e7ad72482efc787f0578bb51909e9546a21968"],"state_sha256":"1a2294e35221bb3ea96a9b5d06928040fe85743e7724678da34f2f144a76dcf5"}