{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RLVGJTAVK56NU3TCONGM765R4W","short_pith_number":"pith:RLVGJTAV","schema_version":"1.0","canonical_sha256":"8aea64cc15577cda6e62734ccffbb1e5a69a02e76301988acc23dcfc83c9ccf6","source":{"kind":"arxiv","id":"2407.03000","version":2},"attestation_state":"computed","paper":{"title":"VIVA: A Benchmark for Vision-Grounded Decision-Making with Human Values","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Jing Li, Yixiao Ren, Yu Yin, Zhe Hu","submitted_at":"2024-07-03T10:59:06Z","abstract_excerpt":"Large vision language models (VLMs) have demonstrated significant potential for integration into daily life, making it crucial for them to incorporate human values when making decisions in real-world situations. This paper introduces VIVA, a benchmark for VIsion-grounded decision-making driven by human VAlues. While most large VLMs focus on physical-level skills, our work is the first to examine their multimodal capabilities in leveraging human values to make decisions under a vision-depicted situation. VIVA contains 1,240 images depicting diverse real-world situations and the manually annotat"},"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":"2407.03000","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T10:59:06Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"23fa598550984b458db67207fd3f2ff0b8c7411f31c723fb715ebf6a32604947","abstract_canon_sha256":"8e9ffe110d4162ee787266c1219cc8b6e0ef561d704c00944f618038dc8fdb3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:27.841110Z","signature_b64":"EjUWjE00BajmIhGSNNFPrYCPYUZSNkphCASqfHo1exMnAkJxe//qytk3SvQS5uASJUyU9SPLFx2PpKx4dcHYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aea64cc15577cda6e62734ccffbb1e5a69a02e76301988acc23dcfc83c9ccf6","last_reissued_at":"2026-07-05T09:18:27.840602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:27.840602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VIVA: A Benchmark for Vision-Grounded Decision-Making with Human Values","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Jing Li, Yixiao Ren, Yu Yin, Zhe Hu","submitted_at":"2024-07-03T10:59:06Z","abstract_excerpt":"Large vision language models (VLMs) have demonstrated significant potential for integration into daily life, making it crucial for them to incorporate human values when making decisions in real-world situations. This paper introduces VIVA, a benchmark for VIsion-grounded decision-making driven by human VAlues. While most large VLMs focus on physical-level skills, our work is the first to examine their multimodal capabilities in leveraging human values to make decisions under a vision-depicted situation. VIVA contains 1,240 images depicting diverse real-world situations and the manually annotat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03000","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/2407.03000/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":"2407.03000","created_at":"2026-07-05T09:18:27.840663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03000v2","created_at":"2026-07-05T09:18:27.840663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03000","created_at":"2026-07-05T09:18:27.840663+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLVGJTAVK56N","created_at":"2026-07-05T09:18:27.840663+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLVGJTAVK56NU3TC","created_at":"2026-07-05T09:18:27.840663+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLVGJTAV","created_at":"2026-07-05T09:18:27.840663+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08757","citing_title":"SocialNav-SUB: Benchmarking VLMs for Scene Understanding in Social Robot Navigation","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RLVGJTAVK56NU3TCONGM765R4W","json":"https://pith.science/pith/RLVGJTAVK56NU3TCONGM765R4W.json","graph_json":"https://pith.science/api/pith-number/RLVGJTAVK56NU3TCONGM765R4W/graph.json","events_json":"https://pith.science/api/pith-number/RLVGJTAVK56NU3TCONGM765R4W/events.json","paper":"https://pith.science/paper/RLVGJTAV"},"agent_actions":{"view_html":"https://pith.science/pith/RLVGJTAVK56NU3TCONGM765R4W","download_json":"https://pith.science/pith/RLVGJTAVK56NU3TCONGM765R4W.json","view_paper":"https://pith.science/paper/RLVGJTAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03000&json=true","fetch_graph":"https://pith.science/api/pith-number/RLVGJTAVK56NU3TCONGM765R4W/graph.json","fetch_events":"https://pith.science/api/pith-number/RLVGJTAVK56NU3TCONGM765R4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLVGJTAVK56NU3TCONGM765R4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLVGJTAVK56NU3TCONGM765R4W/action/storage_attestation","attest_author":"https://pith.science/pith/RLVGJTAVK56NU3TCONGM765R4W/action/author_attestation","sign_citation":"https://pith.science/pith/RLVGJTAVK56NU3TCONGM765R4W/action/citation_signature","submit_replication":"https://pith.science/pith/RLVGJTAVK56NU3TCONGM765R4W/action/replication_record"}},"created_at":"2026-07-05T09:18:27.840663+00:00","updated_at":"2026-07-05T09:18:27.840663+00:00"}