{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:57AMKQGEB5YEYJMQBDNMBLXGBA","short_pith_number":"pith:57AMKQGE","schema_version":"1.0","canonical_sha256":"efc0c540c40f704c259008dac0aee6082a1ab54851aced117e14dbca39558588","source":{"kind":"arxiv","id":"2405.18831","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Zero-Shot GPT-4V Performance on 3D Visual Question Answering Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dimitrios Stamoulis, Georgios Pavlakos, Simranjit Singh","submitted_at":"2024-05-29T07:20:28Z","abstract_excerpt":"As interest in \"reformulating\" the 3D Visual Question Answering (VQA) problem in the context of foundation models grows, it is imperative to assess how these new paradigms influence existing closed-vocabulary datasets. In this case study, we evaluate the zero-shot performance of foundational models (GPT-4 Vision and GPT-4) on well-established 3D VQA benchmarks, namely 3D-VQA and ScanQA. We provide an investigation to contextualize the performance of GPT-based agents relative to traditional modeling approaches. We find that GPT-based agents without any fine-tuning perform on par with the closed"},"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":"2405.18831","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T07:20:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0dca7f59a3f2833075e46250f5ea28f1dd91ee941664ca914a4be68d69f7a85f","abstract_canon_sha256":"dc9514a8579fe868739bbf832b640bd9ef4513b43d729dbda4f6aeeb32071cb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:30.727257Z","signature_b64":"OCt1rlqb0A9Li0e6o+Ev+G00jBJEXh3spAk0cRlIfkao6hD1E5gjSKCqGXDMNuDNEcleYNYJdjNf4k68WlxDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efc0c540c40f704c259008dac0aee6082a1ab54851aced117e14dbca39558588","last_reissued_at":"2026-07-05T08:24:30.726733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:30.726733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Zero-Shot GPT-4V Performance on 3D Visual Question Answering Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dimitrios Stamoulis, Georgios Pavlakos, Simranjit Singh","submitted_at":"2024-05-29T07:20:28Z","abstract_excerpt":"As interest in \"reformulating\" the 3D Visual Question Answering (VQA) problem in the context of foundation models grows, it is imperative to assess how these new paradigms influence existing closed-vocabulary datasets. In this case study, we evaluate the zero-shot performance of foundational models (GPT-4 Vision and GPT-4) on well-established 3D VQA benchmarks, namely 3D-VQA and ScanQA. We provide an investigation to contextualize the performance of GPT-based agents relative to traditional modeling approaches. We find that GPT-based agents without any fine-tuning perform on par with the closed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18831","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/2405.18831/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":"2405.18831","created_at":"2026-07-05T08:24:30.726797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18831v1","created_at":"2026-07-05T08:24:30.726797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18831","created_at":"2026-07-05T08:24:30.726797+00:00"},{"alias_kind":"pith_short_12","alias_value":"57AMKQGEB5YE","created_at":"2026-07-05T08:24:30.726797+00:00"},{"alias_kind":"pith_short_16","alias_value":"57AMKQGEB5YEYJMQ","created_at":"2026-07-05T08:24:30.726797+00:00"},{"alias_kind":"pith_short_8","alias_value":"57AMKQGE","created_at":"2026-07-05T08:24:30.726797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00342","citing_title":"Embodied Intelligence for 3D Understanding: A Survey on 3D Scene Question Answering","ref_index":84,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/57AMKQGEB5YEYJMQBDNMBLXGBA","json":"https://pith.science/pith/57AMKQGEB5YEYJMQBDNMBLXGBA.json","graph_json":"https://pith.science/api/pith-number/57AMKQGEB5YEYJMQBDNMBLXGBA/graph.json","events_json":"https://pith.science/api/pith-number/57AMKQGEB5YEYJMQBDNMBLXGBA/events.json","paper":"https://pith.science/paper/57AMKQGE"},"agent_actions":{"view_html":"https://pith.science/pith/57AMKQGEB5YEYJMQBDNMBLXGBA","download_json":"https://pith.science/pith/57AMKQGEB5YEYJMQBDNMBLXGBA.json","view_paper":"https://pith.science/paper/57AMKQGE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18831&json=true","fetch_graph":"https://pith.science/api/pith-number/57AMKQGEB5YEYJMQBDNMBLXGBA/graph.json","fetch_events":"https://pith.science/api/pith-number/57AMKQGEB5YEYJMQBDNMBLXGBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57AMKQGEB5YEYJMQBDNMBLXGBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57AMKQGEB5YEYJMQBDNMBLXGBA/action/storage_attestation","attest_author":"https://pith.science/pith/57AMKQGEB5YEYJMQBDNMBLXGBA/action/author_attestation","sign_citation":"https://pith.science/pith/57AMKQGEB5YEYJMQBDNMBLXGBA/action/citation_signature","submit_replication":"https://pith.science/pith/57AMKQGEB5YEYJMQBDNMBLXGBA/action/replication_record"}},"created_at":"2026-07-05T08:24:30.726797+00:00","updated_at":"2026-07-05T08:24:30.726797+00:00"}