{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3J4BN2NDZSSDOCCU4QV3XOD4TR","short_pith_number":"pith:3J4BN2ND","schema_version":"1.0","canonical_sha256":"da7816e9a3cca4370854e42bbbb87c9c6c2c74992096cb56fde076e6ef4ecc06","source":{"kind":"arxiv","id":"2308.10435","version":1},"attestation_state":"computed","paper":{"title":"GPT-in-the-Loop: Adaptive Decision-Making for Multiagent Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.SE"],"primary_cat":"cs.MA","authors_text":"Donald Cowan, Nathalia Nascimento, Paulo Alencar","submitted_at":"2023-08-21T03:08:16Z","abstract_excerpt":"This paper introduces the \"GPT-in-the-loop\" approach, a novel method combining the advanced reasoning capabilities of Large Language Models (LLMs) like Generative Pre-trained Transformers (GPT) with multiagent (MAS) systems. Venturing beyond traditional adaptive approaches that generally require long training processes, our framework employs GPT-4 for enhanced problem-solving and explanation skills. Our experimental backdrop is the smart streetlight Internet of Things (IoT) application. Here, agents use sensors, actuators, and neural networks to create an energy-efficient lighting system. By i"},"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":"2308.10435","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2023-08-21T03:08:16Z","cross_cats_sorted":["cs.AI","cs.NE","cs.SE"],"title_canon_sha256":"5929de82ed55a26828cfbd63159b4303ebb4a19b2d343c95ca60ec7b9d14526b","abstract_canon_sha256":"f7fb9b4af1f6162efb52f6f2a002372f5f06c8e69062b5102d57f567fe272d30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:09.042441Z","signature_b64":"LmWhUeGpwZtO6bXntl//PlY6U0NKDKpaZ6pB8IYN0q5H5ZdF9wGrQcB2Or4MA97dJWeB3M9yFQUMHPjvdB9QAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da7816e9a3cca4370854e42bbbb87c9c6c2c74992096cb56fde076e6ef4ecc06","last_reissued_at":"2026-07-05T06:43:09.041954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:09.041954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPT-in-the-Loop: Adaptive Decision-Making for Multiagent Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.SE"],"primary_cat":"cs.MA","authors_text":"Donald Cowan, Nathalia Nascimento, Paulo Alencar","submitted_at":"2023-08-21T03:08:16Z","abstract_excerpt":"This paper introduces the \"GPT-in-the-loop\" approach, a novel method combining the advanced reasoning capabilities of Large Language Models (LLMs) like Generative Pre-trained Transformers (GPT) with multiagent (MAS) systems. Venturing beyond traditional adaptive approaches that generally require long training processes, our framework employs GPT-4 for enhanced problem-solving and explanation skills. Our experimental backdrop is the smart streetlight Internet of Things (IoT) application. Here, agents use sensors, actuators, and neural networks to create an energy-efficient lighting system. By i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10435","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/2308.10435/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":"2308.10435","created_at":"2026-07-05T06:43:09.042014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10435v1","created_at":"2026-07-05T06:43:09.042014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10435","created_at":"2026-07-05T06:43:09.042014+00:00"},{"alias_kind":"pith_short_12","alias_value":"3J4BN2NDZSSD","created_at":"2026-07-05T06:43:09.042014+00:00"},{"alias_kind":"pith_short_16","alias_value":"3J4BN2NDZSSDOCCU","created_at":"2026-07-05T06:43:09.042014+00:00"},{"alias_kind":"pith_short_8","alias_value":"3J4BN2ND","created_at":"2026-07-05T06:43:09.042014+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.02170","citing_title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07462","citing_title":"The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3J4BN2NDZSSDOCCU4QV3XOD4TR","json":"https://pith.science/pith/3J4BN2NDZSSDOCCU4QV3XOD4TR.json","graph_json":"https://pith.science/api/pith-number/3J4BN2NDZSSDOCCU4QV3XOD4TR/graph.json","events_json":"https://pith.science/api/pith-number/3J4BN2NDZSSDOCCU4QV3XOD4TR/events.json","paper":"https://pith.science/paper/3J4BN2ND"},"agent_actions":{"view_html":"https://pith.science/pith/3J4BN2NDZSSDOCCU4QV3XOD4TR","download_json":"https://pith.science/pith/3J4BN2NDZSSDOCCU4QV3XOD4TR.json","view_paper":"https://pith.science/paper/3J4BN2ND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10435&json=true","fetch_graph":"https://pith.science/api/pith-number/3J4BN2NDZSSDOCCU4QV3XOD4TR/graph.json","fetch_events":"https://pith.science/api/pith-number/3J4BN2NDZSSDOCCU4QV3XOD4TR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3J4BN2NDZSSDOCCU4QV3XOD4TR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3J4BN2NDZSSDOCCU4QV3XOD4TR/action/storage_attestation","attest_author":"https://pith.science/pith/3J4BN2NDZSSDOCCU4QV3XOD4TR/action/author_attestation","sign_citation":"https://pith.science/pith/3J4BN2NDZSSDOCCU4QV3XOD4TR/action/citation_signature","submit_replication":"https://pith.science/pith/3J4BN2NDZSSDOCCU4QV3XOD4TR/action/replication_record"}},"created_at":"2026-07-05T06:43:09.042014+00:00","updated_at":"2026-07-05T06:43:09.042014+00:00"}