{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XVQGNEMTOVIVPZ453FT5R24SLI","short_pith_number":"pith:XVQGNEMT","schema_version":"1.0","canonical_sha256":"bd60669193755157e79dd967d8eb925a21c5eb604e833a64ac4f4ce095b876df","source":{"kind":"arxiv","id":"2605.14928","version":1},"attestation_state":"computed","paper":{"title":"Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ci-Jun Gao, Derek F. Wong, Feng Wan, Guanhua Chen, Lidia S. Chao, Shenghe Sun, Shudong Liu, Yutong Yao","submitted_at":"2026-05-14T15:03:36Z","abstract_excerpt":"Recent advances in vision-language models (VLMs) have achieved impressive results on standard image-text tasks, yet their potential for visual procedure question answering (VP-QA) remains largely unexplored. VP-QA presents unique challenges where users query next-step actions by uploading images for intermediate states of complex procedures. To systematically evaluate VLMs on this practical task, we propose ProcedureVQA, a novel multimodal benchmark specifically designed for visual procedural reasoning. Through comprehensive analysis, we identify two critical limitations in current VLMs: inade"},"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":"2605.14928","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T15:03:36Z","cross_cats_sorted":[],"title_canon_sha256":"f6910fb601ab6b666235cfc8c46374266fe31524696d9ef7f5193f9848f35074","abstract_canon_sha256":"1d8af4c1218b2abd0f3b886e7dda38558e744d38c29a14ce807eddf1e98a376f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:55.594829Z","signature_b64":"hPFmKAMVlnLQGLNLSZ5QRwymMK/3yfAUcRlN3UDxTHxcXLQNe+KVQl6AJRXOcclF7t4yLmRuA2PzNPWpTFlECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd60669193755157e79dd967d8eb925a21c5eb604e833a64ac4f4ce095b876df","last_reissued_at":"2026-05-17T23:38:55.594056Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:55.594056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ci-Jun Gao, Derek F. Wong, Feng Wan, Guanhua Chen, Lidia S. Chao, Shenghe Sun, Shudong Liu, Yutong Yao","submitted_at":"2026-05-14T15:03:36Z","abstract_excerpt":"Recent advances in vision-language models (VLMs) have achieved impressive results on standard image-text tasks, yet their potential for visual procedure question answering (VP-QA) remains largely unexplored. VP-QA presents unique challenges where users query next-step actions by uploading images for intermediate states of complex procedures. To systematically evaluate VLMs on this practical task, we propose ProcedureVQA, a novel multimodal benchmark specifically designed for visual procedural reasoning. Through comprehensive analysis, we identify two critical limitations in current VLMs: inade"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14928","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":""},"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":"2605.14928","created_at":"2026-05-17T23:38:55.594188+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14928v1","created_at":"2026-05-17T23:38:55.594188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14928","created_at":"2026-05-17T23:38:55.594188+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVQGNEMTOVIV","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVQGNEMTOVIVPZ45","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVQGNEMT","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVQGNEMTOVIVPZ453FT5R24SLI","json":"https://pith.science/pith/XVQGNEMTOVIVPZ453FT5R24SLI.json","graph_json":"https://pith.science/api/pith-number/XVQGNEMTOVIVPZ453FT5R24SLI/graph.json","events_json":"https://pith.science/api/pith-number/XVQGNEMTOVIVPZ453FT5R24SLI/events.json","paper":"https://pith.science/paper/XVQGNEMT"},"agent_actions":{"view_html":"https://pith.science/pith/XVQGNEMTOVIVPZ453FT5R24SLI","download_json":"https://pith.science/pith/XVQGNEMTOVIVPZ453FT5R24SLI.json","view_paper":"https://pith.science/paper/XVQGNEMT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14928&json=true","fetch_graph":"https://pith.science/api/pith-number/XVQGNEMTOVIVPZ453FT5R24SLI/graph.json","fetch_events":"https://pith.science/api/pith-number/XVQGNEMTOVIVPZ453FT5R24SLI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVQGNEMTOVIVPZ453FT5R24SLI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVQGNEMTOVIVPZ453FT5R24SLI/action/storage_attestation","attest_author":"https://pith.science/pith/XVQGNEMTOVIVPZ453FT5R24SLI/action/author_attestation","sign_citation":"https://pith.science/pith/XVQGNEMTOVIVPZ453FT5R24SLI/action/citation_signature","submit_replication":"https://pith.science/pith/XVQGNEMTOVIVPZ453FT5R24SLI/action/replication_record"}},"created_at":"2026-05-17T23:38:55.594188+00:00","updated_at":"2026-05-17T23:38:55.594188+00:00"}