{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S56JJUAE7LC2PFIDPNJQ2ZJ6IU","short_pith_number":"pith:S56JJUAE","schema_version":"1.0","canonical_sha256":"977c94d004fac5a795037b530d653e452341c9fc18d4261c54d1577a66eb5230","source":{"kind":"arxiv","id":"2508.04043","version":1},"attestation_state":"computed","paper":{"title":"VisualTrans: A Benchmark for Real-World Visual Transformation Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaihai Lyu, Xiaolong Zheng, Xiaoshuai Hao, Yipu Wang, Yue Liu, Yuheng Ji, Yuting Zhao, Yuyang Liu","submitted_at":"2025-08-06T03:07:05Z","abstract_excerpt":"Visual transformation reasoning (VTR) is a vital cognitive capability that empowers intelligent agents to understand dynamic scenes, model causal relationships, and predict future states, and thereby guiding actions and laying the foundation for advanced intelligent systems. However, existing benchmarks suffer from a sim-to-real gap, limited task complexity, and incomplete reasoning coverage, limiting their practical use in real-world scenarios. To address these limitations, we introduce VisualTrans, the first comprehensive benchmark specifically designed for VTR in real-world human-object int"},"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":"2508.04043","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-06T03:07:05Z","cross_cats_sorted":[],"title_canon_sha256":"c65e40272525730a2162adfd1de59cb27aee5f6afdd2741c262b5d502986dc57","abstract_canon_sha256":"7957b248eca5c3812c673bf820de9123bf3aac98ecf6895d59b0721df4344a09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:19.658470Z","signature_b64":"af4FXO3cWhAVL82vpHH9Lc//NL/Mux1emE20Ddl4cDerJQB4s3/DRaXRd9YlAtNh/2JuWM6IAORAdqHoRKLvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"977c94d004fac5a795037b530d653e452341c9fc18d4261c54d1577a66eb5230","last_reissued_at":"2026-07-05T11:49:19.657987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:19.657987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisualTrans: A Benchmark for Real-World Visual Transformation Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaihai Lyu, Xiaolong Zheng, Xiaoshuai Hao, Yipu Wang, Yue Liu, Yuheng Ji, Yuting Zhao, Yuyang Liu","submitted_at":"2025-08-06T03:07:05Z","abstract_excerpt":"Visual transformation reasoning (VTR) is a vital cognitive capability that empowers intelligent agents to understand dynamic scenes, model causal relationships, and predict future states, and thereby guiding actions and laying the foundation for advanced intelligent systems. However, existing benchmarks suffer from a sim-to-real gap, limited task complexity, and incomplete reasoning coverage, limiting their practical use in real-world scenarios. To address these limitations, we introduce VisualTrans, the first comprehensive benchmark specifically designed for VTR in real-world human-object int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04043","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/2508.04043/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":"2508.04043","created_at":"2026-07-05T11:49:19.658050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.04043v1","created_at":"2026-07-05T11:49:19.658050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04043","created_at":"2026-07-05T11:49:19.658050+00:00"},{"alias_kind":"pith_short_12","alias_value":"S56JJUAE7LC2","created_at":"2026-07-05T11:49:19.658050+00:00"},{"alias_kind":"pith_short_16","alias_value":"S56JJUAE7LC2PFID","created_at":"2026-07-05T11:49:19.658050+00:00"},{"alias_kind":"pith_short_8","alias_value":"S56JJUAE","created_at":"2026-07-05T11:49:19.658050+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.12982","citing_title":"Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S56JJUAE7LC2PFIDPNJQ2ZJ6IU","json":"https://pith.science/pith/S56JJUAE7LC2PFIDPNJQ2ZJ6IU.json","graph_json":"https://pith.science/api/pith-number/S56JJUAE7LC2PFIDPNJQ2ZJ6IU/graph.json","events_json":"https://pith.science/api/pith-number/S56JJUAE7LC2PFIDPNJQ2ZJ6IU/events.json","paper":"https://pith.science/paper/S56JJUAE"},"agent_actions":{"view_html":"https://pith.science/pith/S56JJUAE7LC2PFIDPNJQ2ZJ6IU","download_json":"https://pith.science/pith/S56JJUAE7LC2PFIDPNJQ2ZJ6IU.json","view_paper":"https://pith.science/paper/S56JJUAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.04043&json=true","fetch_graph":"https://pith.science/api/pith-number/S56JJUAE7LC2PFIDPNJQ2ZJ6IU/graph.json","fetch_events":"https://pith.science/api/pith-number/S56JJUAE7LC2PFIDPNJQ2ZJ6IU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S56JJUAE7LC2PFIDPNJQ2ZJ6IU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S56JJUAE7LC2PFIDPNJQ2ZJ6IU/action/storage_attestation","attest_author":"https://pith.science/pith/S56JJUAE7LC2PFIDPNJQ2ZJ6IU/action/author_attestation","sign_citation":"https://pith.science/pith/S56JJUAE7LC2PFIDPNJQ2ZJ6IU/action/citation_signature","submit_replication":"https://pith.science/pith/S56JJUAE7LC2PFIDPNJQ2ZJ6IU/action/replication_record"}},"created_at":"2026-07-05T11:49:19.658050+00:00","updated_at":"2026-07-05T11:49:19.658050+00:00"}