{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H7BS6WCBGZ2G3727LKNBV7EJIW","short_pith_number":"pith:H7BS6WCB","schema_version":"1.0","canonical_sha256":"3fc32f584136746dff5f5a9a1afc8945b002eaaaccf1b5b9a19506427c075a96","source":{"kind":"arxiv","id":"2412.11672","version":1},"attestation_state":"computed","paper":{"title":"LLM-DaaS: LLM-driven Drone-as-a-Service Operations from Text User Requests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Ali Hamdi, Kamal Mohamed, Lillian Wassim","submitted_at":"2024-12-16T11:25:56Z","abstract_excerpt":"We propose LLM-DaaS, a novel Drone-as-a-Service (DaaS) framework that leverages Large Language Models (LLMs) to transform free-text user requests into structured, actionable DaaS operation tasks. Our approach addresses the key challenge of interpreting and structuring natural language input to automate drone service operations under uncertain conditions. The system is composed of three main components: free-text request processing, structured request generation, and dynamic DaaS selection and composition. First, we fine-tune different LLM models such as Phi-3.5, LLaMA-3.2 7b and Gemma 2b on a "},"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":"2412.11672","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-16T11:25:56Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"b28a171e15d6f2e427ef181c22a05ebbbbfd1ace4d8549602fb2ed455687f872","abstract_canon_sha256":"ab22c82a51d4ab49c00fc097e20b9292f23102e867fac764635732faedae7706"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:49.700624Z","signature_b64":"9HBp9yIWJ9tVSrihtxOv/M/qC8zU6LtKu6/k4Z0kb+zy1lSB96dYaiOqUWXIdiKO1kL2A/4upGpXiod3x7x8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fc32f584136746dff5f5a9a1afc8945b002eaaaccf1b5b9a19506427c075a96","last_reissued_at":"2026-07-05T09:49:49.700109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:49.700109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-DaaS: LLM-driven Drone-as-a-Service Operations from Text User Requests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Ali Hamdi, Kamal Mohamed, Lillian Wassim","submitted_at":"2024-12-16T11:25:56Z","abstract_excerpt":"We propose LLM-DaaS, a novel Drone-as-a-Service (DaaS) framework that leverages Large Language Models (LLMs) to transform free-text user requests into structured, actionable DaaS operation tasks. Our approach addresses the key challenge of interpreting and structuring natural language input to automate drone service operations under uncertain conditions. The system is composed of three main components: free-text request processing, structured request generation, and dynamic DaaS selection and composition. First, we fine-tune different LLM models such as Phi-3.5, LLaMA-3.2 7b and Gemma 2b on a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11672","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/2412.11672/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":"2412.11672","created_at":"2026-07-05T09:49:49.700171+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11672v1","created_at":"2026-07-05T09:49:49.700171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11672","created_at":"2026-07-05T09:49:49.700171+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7BS6WCBGZ2G","created_at":"2026-07-05T09:49:49.700171+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7BS6WCBGZ2G3727","created_at":"2026-07-05T09:49:49.700171+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7BS6WCB","created_at":"2026-07-05T09:49:49.700171+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.11222","citing_title":"An Agentic Flow for Finite State Machine Extraction using Prompt Chaining","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7BS6WCBGZ2G3727LKNBV7EJIW","json":"https://pith.science/pith/H7BS6WCBGZ2G3727LKNBV7EJIW.json","graph_json":"https://pith.science/api/pith-number/H7BS6WCBGZ2G3727LKNBV7EJIW/graph.json","events_json":"https://pith.science/api/pith-number/H7BS6WCBGZ2G3727LKNBV7EJIW/events.json","paper":"https://pith.science/paper/H7BS6WCB"},"agent_actions":{"view_html":"https://pith.science/pith/H7BS6WCBGZ2G3727LKNBV7EJIW","download_json":"https://pith.science/pith/H7BS6WCBGZ2G3727LKNBV7EJIW.json","view_paper":"https://pith.science/paper/H7BS6WCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11672&json=true","fetch_graph":"https://pith.science/api/pith-number/H7BS6WCBGZ2G3727LKNBV7EJIW/graph.json","fetch_events":"https://pith.science/api/pith-number/H7BS6WCBGZ2G3727LKNBV7EJIW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7BS6WCBGZ2G3727LKNBV7EJIW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7BS6WCBGZ2G3727LKNBV7EJIW/action/storage_attestation","attest_author":"https://pith.science/pith/H7BS6WCBGZ2G3727LKNBV7EJIW/action/author_attestation","sign_citation":"https://pith.science/pith/H7BS6WCBGZ2G3727LKNBV7EJIW/action/citation_signature","submit_replication":"https://pith.science/pith/H7BS6WCBGZ2G3727LKNBV7EJIW/action/replication_record"}},"created_at":"2026-07-05T09:49:49.700171+00:00","updated_at":"2026-07-05T09:49:49.700171+00:00"}