{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FF7HWENTVOH4EJ3HL57M63L4AU","short_pith_number":"pith:FF7HWENT","schema_version":"1.0","canonical_sha256":"297e7b11b3ab8fc227675f7ecf6d7c05031595cde36d4b38717a27baf7e2d4ba","source":{"kind":"arxiv","id":"2606.03273","version":1},"attestation_state":"computed","paper":{"title":"VistaHop: Benchmarking Multi-hop Visual Reasoning for Visual DeepSearch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chengcheng Wan, Chengqi Dong, Chuhuai Yue, Guojun Yin, Haiying Sun, Hang He, Jiajun Chai, Ting Su, Xiaohan Wang","submitted_at":"2026-06-02T07:37:23Z","abstract_excerpt":"Visual DeepSearch requires multimodal large reasoning model (MLRM) agents to answer complex visual queries by repeatedly inspecting image regions, grounding intermediate reasoning in visual evidence, and connecting fine-grained clues across long reasoning chains. However, existing benchmarks mainly focus on single-step visual understanding or static image-question answering, offering limited evaluation of iterative image inspection, visual-anchor grounding, and multi-hop evidence integration. In this work, we introduce VistaHop, a benchmark for evaluating vision-centric search and multi-hop vi"},"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":"2606.03273","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T07:37:23Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"6adb7b666789bde6d8754c46fbf390788d2eb932286bb4e12ac7ff259fa7fec9","abstract_canon_sha256":"1e05a8c1c990bd0d91c3592222b7b347c6a3a6f0740ad4ba72ef2446bb6c09bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:37.656477Z","signature_b64":"HEY5D9zi8Axq/3ialouVgCsYjCrQcCDqgNI9LqWRamlzwHGyHivJk4vIIxx3IGoFUgd35nl2tdEC/VDmJT9vBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"297e7b11b3ab8fc227675f7ecf6d7c05031595cde36d4b38717a27baf7e2d4ba","last_reissued_at":"2026-06-03T01:05:37.656058Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:37.656058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VistaHop: Benchmarking Multi-hop Visual Reasoning for Visual DeepSearch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chengcheng Wan, Chengqi Dong, Chuhuai Yue, Guojun Yin, Haiying Sun, Hang He, Jiajun Chai, Ting Su, Xiaohan Wang","submitted_at":"2026-06-02T07:37:23Z","abstract_excerpt":"Visual DeepSearch requires multimodal large reasoning model (MLRM) agents to answer complex visual queries by repeatedly inspecting image regions, grounding intermediate reasoning in visual evidence, and connecting fine-grained clues across long reasoning chains. However, existing benchmarks mainly focus on single-step visual understanding or static image-question answering, offering limited evaluation of iterative image inspection, visual-anchor grounding, and multi-hop evidence integration. In this work, we introduce VistaHop, a benchmark for evaluating vision-centric search and multi-hop vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03273","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/2606.03273/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":"2606.03273","created_at":"2026-06-03T01:05:37.656116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03273v1","created_at":"2026-06-03T01:05:37.656116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03273","created_at":"2026-06-03T01:05:37.656116+00:00"},{"alias_kind":"pith_short_12","alias_value":"FF7HWENTVOH4","created_at":"2026-06-03T01:05:37.656116+00:00"},{"alias_kind":"pith_short_16","alias_value":"FF7HWENTVOH4EJ3H","created_at":"2026-06-03T01:05:37.656116+00:00"},{"alias_kind":"pith_short_8","alias_value":"FF7HWENT","created_at":"2026-06-03T01:05:37.656116+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/FF7HWENTVOH4EJ3HL57M63L4AU","json":"https://pith.science/pith/FF7HWENTVOH4EJ3HL57M63L4AU.json","graph_json":"https://pith.science/api/pith-number/FF7HWENTVOH4EJ3HL57M63L4AU/graph.json","events_json":"https://pith.science/api/pith-number/FF7HWENTVOH4EJ3HL57M63L4AU/events.json","paper":"https://pith.science/paper/FF7HWENT"},"agent_actions":{"view_html":"https://pith.science/pith/FF7HWENTVOH4EJ3HL57M63L4AU","download_json":"https://pith.science/pith/FF7HWENTVOH4EJ3HL57M63L4AU.json","view_paper":"https://pith.science/paper/FF7HWENT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03273&json=true","fetch_graph":"https://pith.science/api/pith-number/FF7HWENTVOH4EJ3HL57M63L4AU/graph.json","fetch_events":"https://pith.science/api/pith-number/FF7HWENTVOH4EJ3HL57M63L4AU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FF7HWENTVOH4EJ3HL57M63L4AU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FF7HWENTVOH4EJ3HL57M63L4AU/action/storage_attestation","attest_author":"https://pith.science/pith/FF7HWENTVOH4EJ3HL57M63L4AU/action/author_attestation","sign_citation":"https://pith.science/pith/FF7HWENTVOH4EJ3HL57M63L4AU/action/citation_signature","submit_replication":"https://pith.science/pith/FF7HWENTVOH4EJ3HL57M63L4AU/action/replication_record"}},"created_at":"2026-06-03T01:05:37.656116+00:00","updated_at":"2026-06-03T01:05:37.656116+00:00"}