{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:J5BMPQQUBGKXTAJWOEYQVQKCZJ","short_pith_number":"pith:J5BMPQQU","canonical_record":{"source":{"id":"2605.08146","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-03T09:33:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7153c6f145462aa0c5d989c242797b5c908e84b964a44cb2019a6ce2618cee86","abstract_canon_sha256":"874d5956ef14f00c6686366a54db343343c6c3e8e54f8143fb3f1475435c9d13"},"schema_version":"1.0"},"canonical_sha256":"4f42c7c214099579813671310ac142ca5374ac84726a238c83742875c44c1eeb","source":{"kind":"arxiv","id":"2605.08146","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08146","created_at":"2026-05-20T01:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08146v2","created_at":"2026-05-20T01:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08146","created_at":"2026-05-20T01:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"J5BMPQQUBGKX","created_at":"2026-05-20T01:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"J5BMPQQUBGKXTAJW","created_at":"2026-05-20T01:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"J5BMPQQU","created_at":"2026-05-20T01:06:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:J5BMPQQUBGKXTAJWOEYQVQKCZJ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.08146","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-03T09:33:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7153c6f145462aa0c5d989c242797b5c908e84b964a44cb2019a6ce2618cee86","abstract_canon_sha256":"874d5956ef14f00c6686366a54db343343c6c3e8e54f8143fb3f1475435c9d13"},"schema_version":"1.0"},"canonical_sha256":"4f42c7c214099579813671310ac142ca5374ac84726a238c83742875c44c1eeb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:06:09.996258Z","signature_b64":"5ZaSvnKcBksBQ2AaeaRG1txJsdQ7R8CNyed0of7TlLiaskg54lxlPR85Bf7TWzQ3lh5Sicj6V4HJknY+xr8QAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f42c7c214099579813671310ac142ca5374ac84726a238c83742875c44c1eeb","last_reissued_at":"2026-05-20T01:06:09.995755Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:06:09.995755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.08146","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T01:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q94C3O00BGTubg+nePkB0fvtaKfsMd49YVhhRPGFm4b8+XWR/rDs4c7GK/w8ZKQvBQAoDBRQbxRaWOFpiXsSBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T03:38:24.768195Z"},"content_sha256":"79d6afc3e16204e014942bffbd466cd68379fb9b7e7087c494cfe7207be90886","schema_version":"1.0","event_id":"sha256:79d6afc3e16204e014942bffbd466cd68379fb9b7e7087c494cfe7207be90886"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:J5BMPQQUBGKXTAJWOEYQVQKCZJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"VT-Bench is the first unified benchmark to standardize evaluation of models that combine images with tabular data.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kun-Yang Yu, Lan-Zhe Guo, Xin-Yue Zhang, Yu-Feng Li, Zhi Zhou, Zi-Jian Cheng, Zi-Yi Jia","submitted_at":"2026-05-03T09:33:08Z","abstract_excerpt":"Multi-model learning has attracted great attention in visual-text tasks. However, visual-tabular data, which plays a pivotal role in high-stakes domains like healthcare and industry, remains underexplored. In this paper, we introduce \\textit{VT-Bench}, the first unified benchmark for standardizing vision-tabular discriminative prediction and generative reasoning tasks. VT-Bench aggregates 14 datasets across 9 domains (medical-centric, while covering pets, media, and transportation) with over 756K samples. We evaluate 23 representative models, including unimodal experts, specialized visual-tabu"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"VT-Bench is the first unified benchmark for standardizing vision-tabular discriminative prediction and generative reasoning tasks, aggregating 14 datasets across 9 domains with over 756K samples and evaluating 23 models to highlight substantial challenges of visual-tabular learning.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The 14 chosen datasets and the evaluation setup for 23 models accurately represent the core difficulties of visual-tabular multi-modal learning without selection bias or incomplete coverage of real-world use cases.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VT-Bench is the first unified benchmark aggregating 14 visual-tabular datasets with over 756K samples and evaluating 23 models to expose challenges in this multi-modal area.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"VT-Bench is the first unified benchmark to standardize evaluation of models that combine images with tabular data.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"630166a41d53b8720d1a3727ee152abc8e7be4fda30354d9950fdbc7dcf2848f"},"source":{"id":"2605.08146","kind":"arxiv","version":2},"verdict":{"id":"c3d06200-9728-4f77-bb15-ff51847de43d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T01:27:29.175402Z","strongest_claim":"VT-Bench is the first unified benchmark for standardizing vision-tabular discriminative prediction and generative reasoning tasks, aggregating 14 datasets across 9 domains with over 756K samples and evaluating 23 models to highlight substantial challenges of visual-tabular learning.","one_line_summary":"VT-Bench is the first unified benchmark aggregating 14 visual-tabular datasets with over 756K samples and evaluating 23 models to expose challenges in this multi-modal area.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The 14 chosen datasets and the evaluation setup for 23 models accurately represent the core difficulties of visual-tabular multi-modal learning without selection bias or incomplete coverage of real-world use cases.","pith_extraction_headline":"VT-Bench is the first unified benchmark to standardize evaluation of models that combine images with tabular data."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.08146/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T16:58:08.700136Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"40632a24a8bca50f020569bc4f8352a4cefa842bf25027e0500b91050bdce321"},"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":"c3d06200-9728-4f77-bb15-ff51847de43d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T01:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YEddMSPOJJmpoHTLWAGJEYmdhuiLyvz/WHPGPoV9vlFBVCx040nq1McM0hioy+qMi+8LVcB9GWhC/DU2VMOxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T03:38:24.769127Z"},"content_sha256":"bfe4a377537ff662f90cdb1c1cfc74cee894ca7768e093613b8a28dcda2f077c","schema_version":"1.0","event_id":"sha256:bfe4a377537ff662f90cdb1c1cfc74cee894ca7768e093613b8a28dcda2f077c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J5BMPQQUBGKXTAJWOEYQVQKCZJ/bundle.json","state_url":"https://pith.science/pith/J5BMPQQUBGKXTAJWOEYQVQKCZJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J5BMPQQUBGKXTAJWOEYQVQKCZJ/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":"2026-05-23T03:38:24Z","links":{"resolver":"https://pith.science/pith/J5BMPQQUBGKXTAJWOEYQVQKCZJ","bundle":"https://pith.science/pith/J5BMPQQUBGKXTAJWOEYQVQKCZJ/bundle.json","state":"https://pith.science/pith/J5BMPQQUBGKXTAJWOEYQVQKCZJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J5BMPQQUBGKXTAJWOEYQVQKCZJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:J5BMPQQUBGKXTAJWOEYQVQKCZJ","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":"874d5956ef14f00c6686366a54db343343c6c3e8e54f8143fb3f1475435c9d13","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-03T09:33:08Z","title_canon_sha256":"7153c6f145462aa0c5d989c242797b5c908e84b964a44cb2019a6ce2618cee86"},"schema_version":"1.0","source":{"id":"2605.08146","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08146","created_at":"2026-05-20T01:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08146v2","created_at":"2026-05-20T01:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08146","created_at":"2026-05-20T01:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"J5BMPQQUBGKX","created_at":"2026-05-20T01:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"J5BMPQQUBGKXTAJW","created_at":"2026-05-20T01:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"J5BMPQQU","created_at":"2026-05-20T01:06:09Z"}],"graph_snapshots":[{"event_id":"sha256:bfe4a377537ff662f90cdb1c1cfc74cee894ca7768e093613b8a28dcda2f077c","target":"graph","created_at":"2026-05-20T01:06:09Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"VT-Bench is the first unified benchmark for standardizing vision-tabular discriminative prediction and generative reasoning tasks, aggregating 14 datasets across 9 domains with over 756K samples and evaluating 23 models to highlight substantial challenges of visual-tabular learning."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The 14 chosen datasets and the evaluation setup for 23 models accurately represent the core difficulties of visual-tabular multi-modal learning without selection bias or incomplete coverage of real-world use cases."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"VT-Bench is the first unified benchmark aggregating 14 visual-tabular datasets with over 756K samples and evaluating 23 models to expose challenges in this multi-modal area."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"VT-Bench is the first unified benchmark to standardize evaluation of models that combine images with tabular data."}],"snapshot_sha256":"630166a41d53b8720d1a3727ee152abc8e7be4fda30354d9950fdbc7dcf2848f"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T16:58:08.700136Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.08146/integrity.json","findings":[],"snapshot_sha256":"40632a24a8bca50f020569bc4f8352a4cefa842bf25027e0500b91050bdce321","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-model learning has attracted great attention in visual-text tasks. However, visual-tabular data, which plays a pivotal role in high-stakes domains like healthcare and industry, remains underexplored. In this paper, we introduce \\textit{VT-Bench}, the first unified benchmark for standardizing vision-tabular discriminative prediction and generative reasoning tasks. VT-Bench aggregates 14 datasets across 9 domains (medical-centric, while covering pets, media, and transportation) with over 756K samples. We evaluate 23 representative models, including unimodal experts, specialized visual-tabu","authors_text":"Kun-Yang Yu, Lan-Zhe Guo, Xin-Yue Zhang, Yu-Feng Li, Zhi Zhou, Zi-Jian Cheng, Zi-Yi Jia","cross_cats":["cs.AI"],"headline":"VT-Bench is the first unified benchmark to standardize evaluation of models that combine images with tabular data.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-03T09:33:08Z","title":"VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.08146","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T01:27:29.175402Z","id":"c3d06200-9728-4f77-bb15-ff51847de43d","model_set":{"reader":"grok-4.3"},"one_line_summary":"VT-Bench is the first unified benchmark aggregating 14 visual-tabular datasets with over 756K samples and evaluating 23 models to expose challenges in this multi-modal area.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"VT-Bench is the first unified benchmark to standardize evaluation of models that combine images with tabular data.","strongest_claim":"VT-Bench is the first unified benchmark for standardizing vision-tabular discriminative prediction and generative reasoning tasks, aggregating 14 datasets across 9 domains with over 756K samples and evaluating 23 models to highlight substantial challenges of visual-tabular learning.","weakest_assumption":"The 14 chosen datasets and the evaluation setup for 23 models accurately represent the core difficulties of visual-tabular multi-modal learning without selection bias or incomplete coverage of real-world use cases."}},"verdict_id":"c3d06200-9728-4f77-bb15-ff51847de43d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:79d6afc3e16204e014942bffbd466cd68379fb9b7e7087c494cfe7207be90886","target":"record","created_at":"2026-05-20T01:06:09Z","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":"874d5956ef14f00c6686366a54db343343c6c3e8e54f8143fb3f1475435c9d13","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-03T09:33:08Z","title_canon_sha256":"7153c6f145462aa0c5d989c242797b5c908e84b964a44cb2019a6ce2618cee86"},"schema_version":"1.0","source":{"id":"2605.08146","kind":"arxiv","version":2}},"canonical_sha256":"4f42c7c214099579813671310ac142ca5374ac84726a238c83742875c44c1eeb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f42c7c214099579813671310ac142ca5374ac84726a238c83742875c44c1eeb","first_computed_at":"2026-05-20T01:06:09.995755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:06:09.995755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5ZaSvnKcBksBQ2AaeaRG1txJsdQ7R8CNyed0of7TlLiaskg54lxlPR85Bf7TWzQ3lh5Sicj6V4HJknY+xr8QAw==","signature_status":"signed_v1","signed_at":"2026-05-20T01:06:09.996258Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.08146","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79d6afc3e16204e014942bffbd466cd68379fb9b7e7087c494cfe7207be90886","sha256:bfe4a377537ff662f90cdb1c1cfc74cee894ca7768e093613b8a28dcda2f077c"],"state_sha256":"7eeb7c87610018d218969b5b92a2ee76dc5d0f8549c9e1597ebbd42814f5ea05"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OxXK10FfS1v6gypWyp2yA8gxtH1SFmpoQNEBRdzBhsJVgFWQk1da82CGsTROrbDXkj/oflDWlcHPdHbJN3UvBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T03:38:24.773971Z","bundle_sha256":"673270c6faaebd295db73bfe3806006ea2b3ebf169843f910915acf5a79aefec"}}