{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O5FW2YSEBVEV4K7TCB5JE6QKDP","short_pith_number":"pith:O5FW2YSE","schema_version":"1.0","canonical_sha256":"774b6d62440d495e2bf3107a927a0a1bc4aef43378cbb5dc93665bfa1d22879e","source":{"kind":"arxiv","id":"2512.22867","version":2},"attestation_state":"computed","paper":{"title":"MUSON: A Reasoning-oriented Multimodal Dataset for Socially Compliant Navigation in Urban Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Ling Xiao, Qianyi Li, Runji Cai, Tianze Yu, Tomohito Kawabata, Xinyu Zhang, Xuance Peng, Xuesu Xiao, Zhen Xiong, Zhuonan Liu, Zishuo Wang","submitted_at":"2025-12-28T10:41:39Z","abstract_excerpt":"Socially compliant navigation requires structured reasoning about dynamic pedestrians and physical constraints to ensure safe and interpretable decisions. Vision-language models (VLMs) provide a promising foundation for this task because they can integrate visual observations with language-based social knowledge. However, existing untuned VLMs still struggle to reliably understand fine-grained social norms, making task-specific fine-tuning essential. At the same time, no large-scale egocentric dataset is available this task. To address these challenges, we introduce MUSON, a multimodal dataset"},"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":"2512.22867","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-28T10:41:39Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"76476ad06e3c011a638f663f5f2d1acbfa66d11e21bf4f57838728e16d7bbd3c","abstract_canon_sha256":"76e97232c77c073e8f60042ccda35137c7c5e6475cd71627077fad832782cc46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:02.739900Z","signature_b64":"5rDhqSiaJxknjvoXVhGrzV9em5sck4+FHLMmZE3I/DaaAS8mPugskLwEqrtfy0kh3OtRktHoPuNZouIkmFiWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"774b6d62440d495e2bf3107a927a0a1bc4aef43378cbb5dc93665bfa1d22879e","last_reissued_at":"2026-07-07T01:16:02.738955Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:02.738955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MUSON: A Reasoning-oriented Multimodal Dataset for Socially Compliant Navigation in Urban Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Ling Xiao, Qianyi Li, Runji Cai, Tianze Yu, Tomohito Kawabata, Xinyu Zhang, Xuance Peng, Xuesu Xiao, Zhen Xiong, Zhuonan Liu, Zishuo Wang","submitted_at":"2025-12-28T10:41:39Z","abstract_excerpt":"Socially compliant navigation requires structured reasoning about dynamic pedestrians and physical constraints to ensure safe and interpretable decisions. Vision-language models (VLMs) provide a promising foundation for this task because they can integrate visual observations with language-based social knowledge. However, existing untuned VLMs still struggle to reliably understand fine-grained social norms, making task-specific fine-tuning essential. At the same time, no large-scale egocentric dataset is available this task. To address these challenges, we introduce MUSON, a multimodal dataset"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.22867","kind":"arxiv","version":2},"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/2512.22867/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":"2512.22867","created_at":"2026-07-07T01:16:02.739074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.22867v2","created_at":"2026-07-07T01:16:02.739074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.22867","created_at":"2026-07-07T01:16:02.739074+00:00"},{"alias_kind":"pith_short_12","alias_value":"O5FW2YSEBVEV","created_at":"2026-07-07T01:16:02.739074+00:00"},{"alias_kind":"pith_short_16","alias_value":"O5FW2YSEBVEV4K7T","created_at":"2026-07-07T01:16:02.739074+00:00"},{"alias_kind":"pith_short_8","alias_value":"O5FW2YSE","created_at":"2026-07-07T01:16:02.739074+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.28760","citing_title":"Vision-Language Models for Deployable Social Robot Navigation: Bridging Semantic Reasoning and Low-Level Control","ref_index":96,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O5FW2YSEBVEV4K7TCB5JE6QKDP","json":"https://pith.science/pith/O5FW2YSEBVEV4K7TCB5JE6QKDP.json","graph_json":"https://pith.science/api/pith-number/O5FW2YSEBVEV4K7TCB5JE6QKDP/graph.json","events_json":"https://pith.science/api/pith-number/O5FW2YSEBVEV4K7TCB5JE6QKDP/events.json","paper":"https://pith.science/paper/O5FW2YSE"},"agent_actions":{"view_html":"https://pith.science/pith/O5FW2YSEBVEV4K7TCB5JE6QKDP","download_json":"https://pith.science/pith/O5FW2YSEBVEV4K7TCB5JE6QKDP.json","view_paper":"https://pith.science/paper/O5FW2YSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.22867&json=true","fetch_graph":"https://pith.science/api/pith-number/O5FW2YSEBVEV4K7TCB5JE6QKDP/graph.json","fetch_events":"https://pith.science/api/pith-number/O5FW2YSEBVEV4K7TCB5JE6QKDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O5FW2YSEBVEV4K7TCB5JE6QKDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O5FW2YSEBVEV4K7TCB5JE6QKDP/action/storage_attestation","attest_author":"https://pith.science/pith/O5FW2YSEBVEV4K7TCB5JE6QKDP/action/author_attestation","sign_citation":"https://pith.science/pith/O5FW2YSEBVEV4K7TCB5JE6QKDP/action/citation_signature","submit_replication":"https://pith.science/pith/O5FW2YSEBVEV4K7TCB5JE6QKDP/action/replication_record"}},"created_at":"2026-07-07T01:16:02.739074+00:00","updated_at":"2026-07-07T01:16:02.739074+00:00"}