{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ORPXMFAWUE5XPLZWIYCBSRSBRG","short_pith_number":"pith:ORPXMFAW","schema_version":"1.0","canonical_sha256":"745f761416a13b77af36460419464189b6ce3d7bc276359c09e8eeffc771c329","source":{"kind":"arxiv","id":"2408.04423","version":1},"attestation_state":"computed","paper":{"title":"UNMuTe: Unifying Navigation and Multimodal Dialogue-like Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Lorenzo Baraldi, Niyati Rawal, Rita Cucchiara, Roberto Bigazzi","submitted_at":"2024-08-08T12:47:52Z","abstract_excerpt":"Smart autonomous agents are becoming increasingly important in various real-life applications, including robotics and autonomous vehicles. One crucial skill that these agents must possess is the ability to interact with their surrounding entities, such as other agents or humans. In this work, we aim at building an intelligent agent that can efficiently navigate in an environment while being able to interact with an oracle (or human) in natural language and ask for directions when it is unsure about its navigation performance. The interaction is started by the agent that produces a question, wh"},"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":"2408.04423","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-08-08T12:47:52Z","cross_cats_sorted":[],"title_canon_sha256":"888fc2573a6f8949a7933d1e121df82c11fadd1bea032d4047c8172af4b3e797","abstract_canon_sha256":"1589b05aa0157572aea121e870ee05082763d7c69349f86e5cc6f60df8f43a93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:33.093657Z","signature_b64":"CTmoPYl4f3a91RCBWzHfeneXrY33JMVRLD00xwMTLxv4cHzj4uC0fwEgSEPT45ll92pPzyzymYXR6fL0l1DzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"745f761416a13b77af36460419464189b6ce3d7bc276359c09e8eeffc771c329","last_reissued_at":"2026-07-05T08:53:33.093142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:33.093142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UNMuTe: Unifying Navigation and Multimodal Dialogue-like Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Lorenzo Baraldi, Niyati Rawal, Rita Cucchiara, Roberto Bigazzi","submitted_at":"2024-08-08T12:47:52Z","abstract_excerpt":"Smart autonomous agents are becoming increasingly important in various real-life applications, including robotics and autonomous vehicles. One crucial skill that these agents must possess is the ability to interact with their surrounding entities, such as other agents or humans. In this work, we aim at building an intelligent agent that can efficiently navigate in an environment while being able to interact with an oracle (or human) in natural language and ask for directions when it is unsure about its navigation performance. The interaction is started by the agent that produces a question, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04423","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/2408.04423/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":"2408.04423","created_at":"2026-07-05T08:53:33.093200+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04423v1","created_at":"2026-07-05T08:53:33.093200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04423","created_at":"2026-07-05T08:53:33.093200+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORPXMFAWUE5X","created_at":"2026-07-05T08:53:33.093200+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORPXMFAWUE5XPLZW","created_at":"2026-07-05T08:53:33.093200+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORPXMFAW","created_at":"2026-07-05T08:53:33.093200+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01250","citing_title":"Collaborative Instance Object Navigation: Leveraging Uncertainty-Awareness to Minimize Human-Agent Dialogues","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ORPXMFAWUE5XPLZWIYCBSRSBRG","json":"https://pith.science/pith/ORPXMFAWUE5XPLZWIYCBSRSBRG.json","graph_json":"https://pith.science/api/pith-number/ORPXMFAWUE5XPLZWIYCBSRSBRG/graph.json","events_json":"https://pith.science/api/pith-number/ORPXMFAWUE5XPLZWIYCBSRSBRG/events.json","paper":"https://pith.science/paper/ORPXMFAW"},"agent_actions":{"view_html":"https://pith.science/pith/ORPXMFAWUE5XPLZWIYCBSRSBRG","download_json":"https://pith.science/pith/ORPXMFAWUE5XPLZWIYCBSRSBRG.json","view_paper":"https://pith.science/paper/ORPXMFAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04423&json=true","fetch_graph":"https://pith.science/api/pith-number/ORPXMFAWUE5XPLZWIYCBSRSBRG/graph.json","fetch_events":"https://pith.science/api/pith-number/ORPXMFAWUE5XPLZWIYCBSRSBRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORPXMFAWUE5XPLZWIYCBSRSBRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORPXMFAWUE5XPLZWIYCBSRSBRG/action/storage_attestation","attest_author":"https://pith.science/pith/ORPXMFAWUE5XPLZWIYCBSRSBRG/action/author_attestation","sign_citation":"https://pith.science/pith/ORPXMFAWUE5XPLZWIYCBSRSBRG/action/citation_signature","submit_replication":"https://pith.science/pith/ORPXMFAWUE5XPLZWIYCBSRSBRG/action/replication_record"}},"created_at":"2026-07-05T08:53:33.093200+00:00","updated_at":"2026-07-05T08:53:33.093200+00:00"}