{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2QHTNN2HMBHRLESHGKZ557BFZZ","short_pith_number":"pith:2QHTNN2H","schema_version":"1.0","canonical_sha256":"d40f36b747604f15924732b3defc25ce43d29986b80c43251d4176e44f5fcb00","source":{"kind":"arxiv","id":"2407.00518","version":1},"attestation_state":"computed","paper":{"title":"When Robots Get Chatty: Grounding Multimodal Human-Robot Conversation and Collaboration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hassan Ali, Philipp Allgeuer, Stefan Wermter","submitted_at":"2024-06-29T19:43:34Z","abstract_excerpt":"We investigate the use of Large Language Models (LLMs) to equip neural robotic agents with human-like social and cognitive competencies, for the purpose of open-ended human-robot conversation and collaboration. We introduce a modular and extensible methodology for grounding an LLM with the sensory perceptions and capabilities of a physical robot, and integrate multiple deep learning models throughout the architecture in a form of system integration. The integrated models encompass various functions such as speech recognition, speech generation, open-vocabulary object detection, human pose esti"},"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":"2407.00518","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-29T19:43:34Z","cross_cats_sorted":[],"title_canon_sha256":"a53d4893ec142b1dda9e80453637b7935bffcb41102cacf01301d4ecc0270c2b","abstract_canon_sha256":"6bf4508220caf70eb6616361485a5f98644907d01aee6095aff6a07418bac32b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:47.453891Z","signature_b64":"uXkmglCsTZVgN0HzmipgLZGB910+h1ccbdZOppkCmo4vM7yb0e0jIVgq5Y1UGYIWPoFcTgbqXFSLTxKESJfRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d40f36b747604f15924732b3defc25ce43d29986b80c43251d4176e44f5fcb00","last_reissued_at":"2026-07-05T09:12:47.453427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:47.453427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Robots Get Chatty: Grounding Multimodal Human-Robot Conversation and Collaboration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hassan Ali, Philipp Allgeuer, Stefan Wermter","submitted_at":"2024-06-29T19:43:34Z","abstract_excerpt":"We investigate the use of Large Language Models (LLMs) to equip neural robotic agents with human-like social and cognitive competencies, for the purpose of open-ended human-robot conversation and collaboration. We introduce a modular and extensible methodology for grounding an LLM with the sensory perceptions and capabilities of a physical robot, and integrate multiple deep learning models throughout the architecture in a form of system integration. The integrated models encompass various functions such as speech recognition, speech generation, open-vocabulary object detection, human pose esti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00518","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/2407.00518/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":"2407.00518","created_at":"2026-07-05T09:12:47.453477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00518v1","created_at":"2026-07-05T09:12:47.453477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00518","created_at":"2026-07-05T09:12:47.453477+00:00"},{"alias_kind":"pith_short_12","alias_value":"2QHTNN2HMBHR","created_at":"2026-07-05T09:12:47.453477+00:00"},{"alias_kind":"pith_short_16","alias_value":"2QHTNN2HMBHRLESH","created_at":"2026-07-05T09:12:47.453477+00:00"},{"alias_kind":"pith_short_8","alias_value":"2QHTNN2H","created_at":"2026-07-05T09:12:47.453477+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2QHTNN2HMBHRLESHGKZ557BFZZ","json":"https://pith.science/pith/2QHTNN2HMBHRLESHGKZ557BFZZ.json","graph_json":"https://pith.science/api/pith-number/2QHTNN2HMBHRLESHGKZ557BFZZ/graph.json","events_json":"https://pith.science/api/pith-number/2QHTNN2HMBHRLESHGKZ557BFZZ/events.json","paper":"https://pith.science/paper/2QHTNN2H"},"agent_actions":{"view_html":"https://pith.science/pith/2QHTNN2HMBHRLESHGKZ557BFZZ","download_json":"https://pith.science/pith/2QHTNN2HMBHRLESHGKZ557BFZZ.json","view_paper":"https://pith.science/paper/2QHTNN2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00518&json=true","fetch_graph":"https://pith.science/api/pith-number/2QHTNN2HMBHRLESHGKZ557BFZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2QHTNN2HMBHRLESHGKZ557BFZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2QHTNN2HMBHRLESHGKZ557BFZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2QHTNN2HMBHRLESHGKZ557BFZZ/action/storage_attestation","attest_author":"https://pith.science/pith/2QHTNN2HMBHRLESHGKZ557BFZZ/action/author_attestation","sign_citation":"https://pith.science/pith/2QHTNN2HMBHRLESHGKZ557BFZZ/action/citation_signature","submit_replication":"https://pith.science/pith/2QHTNN2HMBHRLESHGKZ557BFZZ/action/replication_record"}},"created_at":"2026-07-05T09:12:47.453477+00:00","updated_at":"2026-07-05T09:12:47.453477+00:00"}