{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XVQGNEMTOVIVPZ453FT5R24SLI","short_pith_number":"pith:XVQGNEMT","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"},"canonical_sha256":"bd60669193755157e79dd967d8eb925a21c5eb604e833a64ac4f4ce095b876df","source":{"kind":"arxiv","id":"2605.14928","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14928","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14928v1","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14928","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"pith_short_12","alias_value":"XVQGNEMTOVIV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"XVQGNEMTOVIVPZ45","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"XVQGNEMT","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XVQGNEMTOVIVPZ453FT5R24SLI","target":"record","payload":{"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"},"canonical_sha256":"bd60669193755157e79dd967d8eb925a21c5eb604e833a64ac4f4ce095b876df","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"},"source_kind":"arxiv","source_id":"2605.14928","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XsobopSYSXWyktTDN2hIGTy73VyKJETkE4c9x0g5fndUef+FPS5z0LH7SmOcZL5Wpe0fQcoscsgmEFOcptg+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:25:10.005862Z"},"content_sha256":"5a7f1f7ec23a9b22d5c0f8b2bb4ba0f69ae370fd994b574ddda580a697afe9bf","schema_version":"1.0","event_id":"sha256:5a7f1f7ec23a9b22d5c0f8b2bb4ba0f69ae370fd994b574ddda580a697afe9bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XVQGNEMTOVIVPZ453FT5R24SLI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k+Wdxoknxl3rS4CSdBXOse3q4hFzX9jDykl1TB1J9fPoZ80j3BcaQuw+w1af6jsbvUP97I9CGQjb8Ta4t3xqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:25:10.006417Z"},"content_sha256":"5e7645b44f5133d2d24049158f49cd8e489d99b80d2ddffb72ca07f0b055a4a8","schema_version":"1.0","event_id":"sha256:5e7645b44f5133d2d24049158f49cd8e489d99b80d2ddffb72ca07f0b055a4a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XVQGNEMTOVIVPZ453FT5R24SLI/bundle.json","state_url":"https://pith.science/pith/XVQGNEMTOVIVPZ453FT5R24SLI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XVQGNEMTOVIVPZ453FT5R24SLI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T09:25:10Z","links":{"resolver":"https://pith.science/pith/XVQGNEMTOVIVPZ453FT5R24SLI","bundle":"https://pith.science/pith/XVQGNEMTOVIVPZ453FT5R24SLI/bundle.json","state":"https://pith.science/pith/XVQGNEMTOVIVPZ453FT5R24SLI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XVQGNEMTOVIVPZ453FT5R24SLI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XVQGNEMTOVIVPZ453FT5R24SLI","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":"1d8af4c1218b2abd0f3b886e7dda38558e744d38c29a14ce807eddf1e98a376f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T15:03:36Z","title_canon_sha256":"f6910fb601ab6b666235cfc8c46374266fe31524696d9ef7f5193f9848f35074"},"schema_version":"1.0","source":{"id":"2605.14928","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14928","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14928v1","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14928","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"pith_short_12","alias_value":"XVQGNEMTOVIV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"XVQGNEMTOVIVPZ45","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"XVQGNEMT","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:5e7645b44f5133d2d24049158f49cd8e489d99b80d2ddffb72ca07f0b055a4a8","target":"graph","created_at":"2026-05-17T23:38:55Z","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"},"paper":{"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","authors_text":"Ci-Jun Gao, Derek F. Wong, Feng Wan, Guanhua Chen, Lidia S. Chao, Shenghe Sun, Shudong Liu, Yutong Yao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T15:03:36Z","title":"Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14928","kind":"arxiv","version":1},"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":"sha256:5a7f1f7ec23a9b22d5c0f8b2bb4ba0f69ae370fd994b574ddda580a697afe9bf","target":"record","created_at":"2026-05-17T23:38:55Z","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":"1d8af4c1218b2abd0f3b886e7dda38558e744d38c29a14ce807eddf1e98a376f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T15:03:36Z","title_canon_sha256":"f6910fb601ab6b666235cfc8c46374266fe31524696d9ef7f5193f9848f35074"},"schema_version":"1.0","source":{"id":"2605.14928","kind":"arxiv","version":1}},"canonical_sha256":"bd60669193755157e79dd967d8eb925a21c5eb604e833a64ac4f4ce095b876df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd60669193755157e79dd967d8eb925a21c5eb604e833a64ac4f4ce095b876df","first_computed_at":"2026-05-17T23:38:55.594056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:55.594056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hPFmKAMVlnLQGLNLSZ5QRwymMK/3yfAUcRlN3UDxTHxcXLQNe+KVQl6AJRXOcclF7t4yLmRuA2PzNPWpTFlECQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:55.594829Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14928","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a7f1f7ec23a9b22d5c0f8b2bb4ba0f69ae370fd994b574ddda580a697afe9bf","sha256:5e7645b44f5133d2d24049158f49cd8e489d99b80d2ddffb72ca07f0b055a4a8"],"state_sha256":"cf6ace11156a41306b148042683b444c1436c7ec0771838576f759fdb8edf716"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"riYGDgntio8mMlELQtO7WFywHsSXHzORSTGAnTqrfrUyqT6XhV9OkU5M2ozvoBj+l/bc8KgIlXK7y2EBABwPAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T09:25:10.008560Z","bundle_sha256":"a8627c2f645ae019881f835efcdfa33b0dd66e8be48de38a8d3ceef8eca9e8ea"}}