{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DOQPUIIX2UKTZ4RTCSLC6WMNFA","short_pith_number":"pith:DOQPUIIX","schema_version":"1.0","canonical_sha256":"1ba0fa2117d5153cf23314962f598d283d8c1b73fc916e2f2ce4d0cce5db213e","source":{"kind":"arxiv","id":"2506.00893","version":2},"attestation_state":"computed","paper":{"title":"Affordance Benchmark for MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chunyi Li, Guangtao Zhai, Haodong Duan, Junying Wang, Wenzhe Li, Yalun Wu, Yijin Guo, Yingji Liang, Zicheng Zhang","submitted_at":"2025-06-01T08:26:34Z","abstract_excerpt":"Affordance theory suggests that environments inherently provide action possibilities shaping perception and behavior. While Multimodal Large Language Models (MLLMs) achieve strong performance in vision-language tasks, their ability to perceive affordance, which is crucial for intuitive and safe interactions, remains underexplored. To address this, we introduce **A4Bench**, a novel benchmark designed to evaluate the affordance perception abilities of MLLMs across two dimensions: 1) Constitutive Affordance, assessing understanding of inherent object properties through 1,282 questionanswer pairs "},"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":"2506.00893","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T08:26:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"425d468dd60fc0c314f083afb443a3a81a98e4b8c7f3ee63cb16d4f6746ddb38","abstract_canon_sha256":"ed826a2de6653a8be02e9ee0df0c163b471e0f553fb3ad847c32a2b4a6d7e537"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:23.831058Z","signature_b64":"iC68hs4b31aiX+MdFR5sWXV4zbMTRtxIOmGk9BAaOHgFJqbRwzoYs+2B03JUmHCHCa2VUeOJYeBHsev/8mifDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ba0fa2117d5153cf23314962f598d283d8c1b73fc916e2f2ce4d0cce5db213e","last_reissued_at":"2026-07-05T11:47:23.830584Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:23.830584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Affordance Benchmark for MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chunyi Li, Guangtao Zhai, Haodong Duan, Junying Wang, Wenzhe Li, Yalun Wu, Yijin Guo, Yingji Liang, Zicheng Zhang","submitted_at":"2025-06-01T08:26:34Z","abstract_excerpt":"Affordance theory suggests that environments inherently provide action possibilities shaping perception and behavior. While Multimodal Large Language Models (MLLMs) achieve strong performance in vision-language tasks, their ability to perceive affordance, which is crucial for intuitive and safe interactions, remains underexplored. To address this, we introduce **A4Bench**, a novel benchmark designed to evaluate the affordance perception abilities of MLLMs across two dimensions: 1) Constitutive Affordance, assessing understanding of inherent object properties through 1,282 questionanswer pairs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00893","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/2506.00893/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":"2506.00893","created_at":"2026-07-05T11:47:23.830642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00893v2","created_at":"2026-07-05T11:47:23.830642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00893","created_at":"2026-07-05T11:47:23.830642+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOQPUIIX2UKT","created_at":"2026-07-05T11:47:23.830642+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOQPUIIX2UKTZ4RT","created_at":"2026-07-05T11:47:23.830642+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOQPUIIX","created_at":"2026-07-05T11:47:23.830642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07962","citing_title":"ChronoPhyBench: Do MLLMs Truly Understand the World or Merely Exploit Language Priors?","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DOQPUIIX2UKTZ4RTCSLC6WMNFA","json":"https://pith.science/pith/DOQPUIIX2UKTZ4RTCSLC6WMNFA.json","graph_json":"https://pith.science/api/pith-number/DOQPUIIX2UKTZ4RTCSLC6WMNFA/graph.json","events_json":"https://pith.science/api/pith-number/DOQPUIIX2UKTZ4RTCSLC6WMNFA/events.json","paper":"https://pith.science/paper/DOQPUIIX"},"agent_actions":{"view_html":"https://pith.science/pith/DOQPUIIX2UKTZ4RTCSLC6WMNFA","download_json":"https://pith.science/pith/DOQPUIIX2UKTZ4RTCSLC6WMNFA.json","view_paper":"https://pith.science/paper/DOQPUIIX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00893&json=true","fetch_graph":"https://pith.science/api/pith-number/DOQPUIIX2UKTZ4RTCSLC6WMNFA/graph.json","fetch_events":"https://pith.science/api/pith-number/DOQPUIIX2UKTZ4RTCSLC6WMNFA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOQPUIIX2UKTZ4RTCSLC6WMNFA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOQPUIIX2UKTZ4RTCSLC6WMNFA/action/storage_attestation","attest_author":"https://pith.science/pith/DOQPUIIX2UKTZ4RTCSLC6WMNFA/action/author_attestation","sign_citation":"https://pith.science/pith/DOQPUIIX2UKTZ4RTCSLC6WMNFA/action/citation_signature","submit_replication":"https://pith.science/pith/DOQPUIIX2UKTZ4RTCSLC6WMNFA/action/replication_record"}},"created_at":"2026-07-05T11:47:23.830642+00:00","updated_at":"2026-07-05T11:47:23.830642+00:00"}