{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JTGL7GUWIRMSCY2PPPDOEA7WJL","short_pith_number":"pith:JTGL7GUW","schema_version":"1.0","canonical_sha256":"4cccbf9a96445921634f7bc6e203f64ad1312b6e0e7b6c879765b8aedc1743bd","source":{"kind":"arxiv","id":"2501.09024","version":1},"attestation_state":"computed","paper":{"title":"Social-LLaVA: Enhancing Robot Navigation through Human-Language Reasoning in Social Spaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.RO"],"primary_cat":"cs.CV","authors_text":"Amir Hossain Raj, Amirreza Payandeh, Daeun Song, Dinesh Manocha, Jing Liang, Mohammad Nazeri, Praneel Mukherjee, Xuesu Xiao, Yangzhe Kong","submitted_at":"2024-12-30T23:59:30Z","abstract_excerpt":"Most existing social robot navigation techniques either leverage hand-crafted rules or human demonstrations to connect robot perception to socially compliant actions. However, there remains a significant gap in effectively translating perception into socially compliant actions, much like how human reasoning naturally occurs in dynamic environments. Considering the recent success of Vision-Language Models (VLMs), we propose using language to bridge the gap in human-like reasoning between perception and socially aware robot actions. We create a vision-language dataset, Social robot Navigation vi"},"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":"2501.09024","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-30T23:59:30Z","cross_cats_sorted":["cs.HC","cs.RO"],"title_canon_sha256":"cf8a7da184061f866504374085d6fbe20b31c7ce2b1bc5bd4951a0a0db150056","abstract_canon_sha256":"dde3a1d562f3c94c935350bdfb9b96e222c369e708db89b769a9f1fae845a69b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:40.372058Z","signature_b64":"nL3PbBbpFBS9TuNOvztuNmvVf0OW4nX3fQh9KjFkyXrXaeQ3ddMvzEYPcifMOOh/pC8SbibWr474j7T6+AkuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cccbf9a96445921634f7bc6e203f64ad1312b6e0e7b6c879765b8aedc1743bd","last_reissued_at":"2026-07-05T10:01:40.371577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:40.371577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Social-LLaVA: Enhancing Robot Navigation through Human-Language Reasoning in Social Spaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.RO"],"primary_cat":"cs.CV","authors_text":"Amir Hossain Raj, Amirreza Payandeh, Daeun Song, Dinesh Manocha, Jing Liang, Mohammad Nazeri, Praneel Mukherjee, Xuesu Xiao, Yangzhe Kong","submitted_at":"2024-12-30T23:59:30Z","abstract_excerpt":"Most existing social robot navigation techniques either leverage hand-crafted rules or human demonstrations to connect robot perception to socially compliant actions. However, there remains a significant gap in effectively translating perception into socially compliant actions, much like how human reasoning naturally occurs in dynamic environments. Considering the recent success of Vision-Language Models (VLMs), we propose using language to bridge the gap in human-like reasoning between perception and socially aware robot actions. We create a vision-language dataset, Social robot Navigation vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09024","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/2501.09024/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":"2501.09024","created_at":"2026-07-05T10:01:40.371639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09024v1","created_at":"2026-07-05T10:01:40.371639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09024","created_at":"2026-07-05T10:01:40.371639+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTGL7GUWIRMS","created_at":"2026-07-05T10:01:40.371639+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTGL7GUWIRMSCY2P","created_at":"2026-07-05T10:01:40.371639+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTGL7GUW","created_at":"2026-07-05T10:01:40.371639+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26047","citing_title":"Learning Robot Visual Navigation in Crowds via Intention-Aware Scene Representations","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10495","citing_title":"Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2503.07557","citing_title":"AutoSpatial: Visual-Language Reasoning for Social Robot Navigation through Efficient Spatial Reasoning Learning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2504.05477","citing_title":"Trust Through Transparency: Explainable Social Navigation for Autonomous Mobile Robots via Vision-Language Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13321","citing_title":"HCSG: Human-Centric Semantic-Geometric Reasoning for Vision-Language Navigation","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JTGL7GUWIRMSCY2PPPDOEA7WJL","json":"https://pith.science/pith/JTGL7GUWIRMSCY2PPPDOEA7WJL.json","graph_json":"https://pith.science/api/pith-number/JTGL7GUWIRMSCY2PPPDOEA7WJL/graph.json","events_json":"https://pith.science/api/pith-number/JTGL7GUWIRMSCY2PPPDOEA7WJL/events.json","paper":"https://pith.science/paper/JTGL7GUW"},"agent_actions":{"view_html":"https://pith.science/pith/JTGL7GUWIRMSCY2PPPDOEA7WJL","download_json":"https://pith.science/pith/JTGL7GUWIRMSCY2PPPDOEA7WJL.json","view_paper":"https://pith.science/paper/JTGL7GUW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09024&json=true","fetch_graph":"https://pith.science/api/pith-number/JTGL7GUWIRMSCY2PPPDOEA7WJL/graph.json","fetch_events":"https://pith.science/api/pith-number/JTGL7GUWIRMSCY2PPPDOEA7WJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTGL7GUWIRMSCY2PPPDOEA7WJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTGL7GUWIRMSCY2PPPDOEA7WJL/action/storage_attestation","attest_author":"https://pith.science/pith/JTGL7GUWIRMSCY2PPPDOEA7WJL/action/author_attestation","sign_citation":"https://pith.science/pith/JTGL7GUWIRMSCY2PPPDOEA7WJL/action/citation_signature","submit_replication":"https://pith.science/pith/JTGL7GUWIRMSCY2PPPDOEA7WJL/action/replication_record"}},"created_at":"2026-07-05T10:01:40.371639+00:00","updated_at":"2026-07-05T10:01:40.371639+00:00"}