{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RLVGJTAVK56NU3TCONGM765R4W","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8e9ffe110d4162ee787266c1219cc8b6e0ef561d704c00944f618038dc8fdb3e","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T10:59:06Z","title_canon_sha256":"23fa598550984b458db67207fd3f2ff0b8c7411f31c723fb715ebf6a32604947"},"schema_version":"1.0","source":{"id":"2407.03000","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03000","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03000v2","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03000","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_12","alias_value":"RLVGJTAVK56N","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_16","alias_value":"RLVGJTAVK56NU3TC","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_8","alias_value":"RLVGJTAV","created_at":"2026-07-05T09:18:27Z"}],"graph_snapshots":[{"event_id":"sha256:ba6086e1ed1ef20a9740cf5c063e9517fc29f94f3ea20964a7a7c8200b9a9ab3","target":"graph","created_at":"2026-07-05T09:18:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.03000/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jing Li, Yixiao Ren, Yu Yin, Zhe Hu","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T10:59:06Z","title":"VIVA: A Benchmark for Vision-Grounded Decision-Making with Human Values"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03000","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0954929c756c47d48a0cf4d3d33128f94b0e112597125dbdb9e84046ccd046be","target":"record","created_at":"2026-07-05T09:18:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8e9ffe110d4162ee787266c1219cc8b6e0ef561d704c00944f618038dc8fdb3e","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T10:59:06Z","title_canon_sha256":"23fa598550984b458db67207fd3f2ff0b8c7411f31c723fb715ebf6a32604947"},"schema_version":"1.0","source":{"id":"2407.03000","kind":"arxiv","version":2}},"canonical_sha256":"8aea64cc15577cda6e62734ccffbb1e5a69a02e76301988acc23dcfc83c9ccf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8aea64cc15577cda6e62734ccffbb1e5a69a02e76301988acc23dcfc83c9ccf6","first_computed_at":"2026-07-05T09:18:27.840602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:27.840602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EjUWjE00BajmIhGSNNFPrYCPYUZSNkphCASqfHo1exMnAkJxe//qytk3SvQS5uASJUyU9SPLFx2PpKx4dcHYBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:27.841110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03000","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0954929c756c47d48a0cf4d3d33128f94b0e112597125dbdb9e84046ccd046be","sha256:ba6086e1ed1ef20a9740cf5c063e9517fc29f94f3ea20964a7a7c8200b9a9ab3"],"state_sha256":"a87fef7c25e3fabae7ea430962162f9f41ddfaed62991c27895d88f606dbca8e"}