{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CFQFRK52VBWYLG7H4DTTAZUIKV","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":"8f2c90f1903ee82d33a78465159021d0be1d74047615e375b53c71073811a69c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T17:59:53Z","title_canon_sha256":"aef7604de0b4286d629306ef6d76ebd3af84e25053521b00ac2f013e647ef58a"},"schema_version":"1.0","source":{"id":"2505.24876","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24876","created_at":"2026-05-26T01:03:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24876v2","created_at":"2026-05-26T01:03:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24876","created_at":"2026-05-26T01:03:12Z"},{"alias_kind":"pith_short_12","alias_value":"CFQFRK52VBWY","created_at":"2026-05-26T01:03:12Z"},{"alias_kind":"pith_short_16","alias_value":"CFQFRK52VBWYLG7H","created_at":"2026-05-26T01:03:12Z"},{"alias_kind":"pith_short_8","alias_value":"CFQFRK52","created_at":"2026-05-26T01:03:12Z"}],"graph_snapshots":[{"event_id":"sha256:5a5746e1cde80535755f429d2d1de2304e42ccd45bc86c2d563749d83fc293c3","target":"graph","created_at":"2026-05-26T01:03:12Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.24876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reasoning is fundamental for solving complex tasks, especially in vision-centric scenarios that demand sequential, multimodal understanding. However, existing benchmarks typically evaluate agents with fully synthetic, single-turn queries, limited visual modalities, and lack a framework to assess reasoning quality over multiple steps as required in real-world settings. To address this, we introduce Agent-X, a large-scale benchmark for evaluating vision-centric agents multi-step and deep reasoning capabilities in real-world, multimodal settings. Agent- X features 828 agentic tasks with auth","authors_text":"Amal Saqib, Fahad Shahbaz Khan, Hanan Ghani, Hisham Cholakkal, Jean Lahoud, Mubarak Shah, Muhra AlMahri, Noor Ahsan, Philip Torr, Rao Muhammad Anwer, Salman Khan, Tajamul Ashraf, Umair Nawaz, Yuhao Li","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T17:59:53Z","title":"Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24876","kind":"arxiv","version":2},"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":"sha256:8bfc1f7481b668e51613e6ad4903a1ecbd47229400b7a71d4b15a28f56939584","target":"record","created_at":"2026-05-26T01:03:12Z","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":"8f2c90f1903ee82d33a78465159021d0be1d74047615e375b53c71073811a69c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T17:59:53Z","title_canon_sha256":"aef7604de0b4286d629306ef6d76ebd3af84e25053521b00ac2f013e647ef58a"},"schema_version":"1.0","source":{"id":"2505.24876","kind":"arxiv","version":2}},"canonical_sha256":"116058abbaa86d859be7e0e7306688555f994a01499f80a073bbfdb358b38729","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"116058abbaa86d859be7e0e7306688555f994a01499f80a073bbfdb358b38729","first_computed_at":"2026-05-26T01:03:12.950124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:12.950124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cGQr2/eygD3nH/LGG2tYwXRz5B3orlkxDOF5Wxia75E928qJsJXFvlfyIDKtZw7TZFC06okWxEwlv6hUWbZfCA==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:12.951143Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24876","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bfc1f7481b668e51613e6ad4903a1ecbd47229400b7a71d4b15a28f56939584","sha256:5a5746e1cde80535755f429d2d1de2304e42ccd45bc86c2d563749d83fc293c3"],"state_sha256":"d7f321dcb6b7c5de0dce7e34e1ed0bef78a3cf3d506b52eec167584ae8d0de06"}