{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KT56VFFZECXZW66PDEI7EB5VLM","short_pith_number":"pith:KT56VFFZ","schema_version":"1.0","canonical_sha256":"54fbea94b920af9b7bcf1911f207b55b1f43eb17ed780f5dad61c959a209a950","source":{"kind":"arxiv","id":"2404.00210","version":3},"attestation_state":"computed","paper":{"title":"VLM-Social-Nav: Socially Aware Robot Navigation through Scoring using Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Amir Hossain Raj, Amirreza Payandeh, Daeun Song, Dinesh Manocha, Jing Liang, Xuesu Xiao","submitted_at":"2024-03-30T01:17:40Z","abstract_excerpt":"We propose VLM-Social-Nav, a novel Vision-Language Model (VLM) based navigation approach to compute a robot's motion in human-centered environments. Our goal is to make real-time decisions on robot actions that are socially compliant with human expectations. We utilize a perception model to detect important social entities and prompt a VLM to generate guidance for socially compliant robot behavior. VLM-Social-Nav uses a VLM-based scoring module that computes a cost term that ensures socially appropriate and effective robot actions generated by the underlying planner. Our overall approach reduc"},"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":"2404.00210","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-03-30T01:17:40Z","cross_cats_sorted":[],"title_canon_sha256":"d9ebb4bc798b0aeb29ec1b91e56ee65e7a2acb750f8555ce5db92623021a0f7e","abstract_canon_sha256":"5ef28d395a0022e9ea8c9f348aaf72e5d2dfffce768115d160441f026d6ae5c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:16.752047Z","signature_b64":"D2ZRvc9cWK2HAFrCyRDXV9xMYOKMH4yHKitjc+tHIRa6VDBNCOtgYI3VHk/6HvgQocAwcvoKbnB3sSmQ28CKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54fbea94b920af9b7bcf1911f207b55b1f43eb17ed780f5dad61c959a209a950","last_reissued_at":"2026-07-05T09:40:16.751566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:16.751566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLM-Social-Nav: Socially Aware Robot Navigation through Scoring using Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Amir Hossain Raj, Amirreza Payandeh, Daeun Song, Dinesh Manocha, Jing Liang, Xuesu Xiao","submitted_at":"2024-03-30T01:17:40Z","abstract_excerpt":"We propose VLM-Social-Nav, a novel Vision-Language Model (VLM) based navigation approach to compute a robot's motion in human-centered environments. Our goal is to make real-time decisions on robot actions that are socially compliant with human expectations. We utilize a perception model to detect important social entities and prompt a VLM to generate guidance for socially compliant robot behavior. VLM-Social-Nav uses a VLM-based scoring module that computes a cost term that ensures socially appropriate and effective robot actions generated by the underlying planner. Our overall approach reduc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00210","kind":"arxiv","version":3},"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/2404.00210/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":"2404.00210","created_at":"2026-07-05T09:40:16.751626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00210v3","created_at":"2026-07-05T09:40:16.751626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00210","created_at":"2026-07-05T09:40:16.751626+00:00"},{"alias_kind":"pith_short_12","alias_value":"KT56VFFZECXZ","created_at":"2026-07-05T09:40:16.751626+00:00"},{"alias_kind":"pith_short_16","alias_value":"KT56VFFZECXZW66P","created_at":"2026-07-05T09:40:16.751626+00:00"},{"alias_kind":"pith_short_8","alias_value":"KT56VFFZ","created_at":"2026-07-05T09:40:16.751626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10495","citing_title":"Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02525","citing_title":"A Semantic Autonomy Framework for VLM-Integrated Indoor Mobile Robots: Hybrid Deterministic Reasoning and Cross-Robot Adaptive Memory","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KT56VFFZECXZW66PDEI7EB5VLM","json":"https://pith.science/pith/KT56VFFZECXZW66PDEI7EB5VLM.json","graph_json":"https://pith.science/api/pith-number/KT56VFFZECXZW66PDEI7EB5VLM/graph.json","events_json":"https://pith.science/api/pith-number/KT56VFFZECXZW66PDEI7EB5VLM/events.json","paper":"https://pith.science/paper/KT56VFFZ"},"agent_actions":{"view_html":"https://pith.science/pith/KT56VFFZECXZW66PDEI7EB5VLM","download_json":"https://pith.science/pith/KT56VFFZECXZW66PDEI7EB5VLM.json","view_paper":"https://pith.science/paper/KT56VFFZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00210&json=true","fetch_graph":"https://pith.science/api/pith-number/KT56VFFZECXZW66PDEI7EB5VLM/graph.json","fetch_events":"https://pith.science/api/pith-number/KT56VFFZECXZW66PDEI7EB5VLM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KT56VFFZECXZW66PDEI7EB5VLM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KT56VFFZECXZW66PDEI7EB5VLM/action/storage_attestation","attest_author":"https://pith.science/pith/KT56VFFZECXZW66PDEI7EB5VLM/action/author_attestation","sign_citation":"https://pith.science/pith/KT56VFFZECXZW66PDEI7EB5VLM/action/citation_signature","submit_replication":"https://pith.science/pith/KT56VFFZECXZW66PDEI7EB5VLM/action/replication_record"}},"created_at":"2026-07-05T09:40:16.751626+00:00","updated_at":"2026-07-05T09:40:16.751626+00:00"}