{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JJHKOYUNY5C5EQ5BAL2IWHWSEW","short_pith_number":"pith:JJHKOYUN","schema_version":"1.0","canonical_sha256":"4a4ea7628dc745d243a102f48b1ed225b5dcf4d4f9bb20154c9f911d2b59593b","source":{"kind":"arxiv","id":"2606.10495","version":1},"attestation_state":"computed","paper":{"title":"Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"(2) University of Southern California), Dianwei Chen (1), Dinesh Manocha (1) ((1) University of Maryland, Guangyao Shi (2), Qingzi Wang (1), Xianfeng Yang (1), Xiyang Wu (1)","submitted_at":"2026-06-09T07:18:01Z","abstract_excerpt":"Safe social navigation requires robots to distinguish people from ordinary obstacles and to react before danger becomes imminent. We show that pretrained Vision-Language-Action (VLA) models already encode pedestrian-object distinctions and future collision signals in their internal representations, but behavior cloning fails to translate these signals into socially appropriate actions. To address this mismatch, we propose SALSA, a two-stage annotation-free post-training framework: (1) social behavioral alignment bridges intermediate-layer social features to the action head and trains on counte"},"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":"2606.10495","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-09T07:18:01Z","cross_cats_sorted":[],"title_canon_sha256":"009fd2ced35ebe8228abfd228e1b42e7e04daa72ad398f96822a2d830e51d7ae","abstract_canon_sha256":"3cab10bacb29b6c0c580e2e0e183ff875544c76decb8c285c7b8997479808479"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:22.409226Z","signature_b64":"3TGmk+XVXm5rHlO1MPfldi1+PfF5vVUdeIVfHHNMWwKUyPJmykN9Hi+tjCIFCgMPwckPtWfcyv6t8TQpkc+xCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a4ea7628dc745d243a102f48b1ed225b5dcf4d4f9bb20154c9f911d2b59593b","last_reissued_at":"2026-06-10T01:10:22.408360Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:22.408360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"(2) University of Southern California), Dianwei Chen (1), Dinesh Manocha (1) ((1) University of Maryland, Guangyao Shi (2), Qingzi Wang (1), Xianfeng Yang (1), Xiyang Wu (1)","submitted_at":"2026-06-09T07:18:01Z","abstract_excerpt":"Safe social navigation requires robots to distinguish people from ordinary obstacles and to react before danger becomes imminent. We show that pretrained Vision-Language-Action (VLA) models already encode pedestrian-object distinctions and future collision signals in their internal representations, but behavior cloning fails to translate these signals into socially appropriate actions. To address this mismatch, we propose SALSA, a two-stage annotation-free post-training framework: (1) social behavioral alignment bridges intermediate-layer social features to the action head and trains on counte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10495","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/2606.10495/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":"2606.10495","created_at":"2026-06-10T01:10:22.408494+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10495v1","created_at":"2026-06-10T01:10:22.408494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10495","created_at":"2026-06-10T01:10:22.408494+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJHKOYUNY5C5","created_at":"2026-06-10T01:10:22.408494+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJHKOYUNY5C5EQ5B","created_at":"2026-06-10T01:10:22.408494+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJHKOYUN","created_at":"2026-06-10T01:10:22.408494+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/JJHKOYUNY5C5EQ5BAL2IWHWSEW","json":"https://pith.science/pith/JJHKOYUNY5C5EQ5BAL2IWHWSEW.json","graph_json":"https://pith.science/api/pith-number/JJHKOYUNY5C5EQ5BAL2IWHWSEW/graph.json","events_json":"https://pith.science/api/pith-number/JJHKOYUNY5C5EQ5BAL2IWHWSEW/events.json","paper":"https://pith.science/paper/JJHKOYUN"},"agent_actions":{"view_html":"https://pith.science/pith/JJHKOYUNY5C5EQ5BAL2IWHWSEW","download_json":"https://pith.science/pith/JJHKOYUNY5C5EQ5BAL2IWHWSEW.json","view_paper":"https://pith.science/paper/JJHKOYUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10495&json=true","fetch_graph":"https://pith.science/api/pith-number/JJHKOYUNY5C5EQ5BAL2IWHWSEW/graph.json","fetch_events":"https://pith.science/api/pith-number/JJHKOYUNY5C5EQ5BAL2IWHWSEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJHKOYUNY5C5EQ5BAL2IWHWSEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJHKOYUNY5C5EQ5BAL2IWHWSEW/action/storage_attestation","attest_author":"https://pith.science/pith/JJHKOYUNY5C5EQ5BAL2IWHWSEW/action/author_attestation","sign_citation":"https://pith.science/pith/JJHKOYUNY5C5EQ5BAL2IWHWSEW/action/citation_signature","submit_replication":"https://pith.science/pith/JJHKOYUNY5C5EQ5BAL2IWHWSEW/action/replication_record"}},"created_at":"2026-06-10T01:10:22.408494+00:00","updated_at":"2026-06-10T01:10:22.408494+00:00"}