{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3ALO7SHLEHDZVESOJ3L3VEO2JO","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":"4247243578964ae049b2c7f1db8df0f9b4dccc884c799287e244b245ce690ba6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T15:04:25Z","title_canon_sha256":"9a30e33267fa977dcff202ab77f829c2316a245dfa59ee2a766750353ed4190b"},"schema_version":"1.0","source":{"id":"2606.02357","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02357","created_at":"2026-06-02T03:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02357v1","created_at":"2026-06-02T03:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02357","created_at":"2026-06-02T03:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"3ALO7SHLEHDZ","created_at":"2026-06-02T03:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"3ALO7SHLEHDZVESO","created_at":"2026-06-02T03:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"3ALO7SHL","created_at":"2026-06-02T03:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:5f3719cf07b9069bff7eb3bd54d8eb22045a1063e28706f051143248661b101e","target":"graph","created_at":"2026-06-02T03:04:57Z","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/2606.02357/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tool-augmented multimodal agents show strong benchmark gains, often taken as evidence that agents have learned to use tools. We argue that this interpretation can be premature: a tool-call trace alone does not show whether the tool supplied answer-critical information. We study two representative ``thinking with images'' agents, Thyme and DeepEyesV2, across real-world understanding, OCR, chart understanding, and mathematical reasoning. Each agent is compared with its Tool-Free counterpart and with a Pure-Text Reasoner trained from the same source pool without tool-calling trajectories. Tool ac","authors_text":"Donglei Yu, Garvin Guo, Huaxing Liu, Minpeng Liao, Qinghao Wang, Shuai Li, Xiang Wang, Xinpei Zhao, Yu Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T15:04:25Z","title":"Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02357","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":"sha256:4ceeb91bbac4654f831aef604dbed38e5678f8fa010d4b8a2c9c4fbd06729084","target":"record","created_at":"2026-06-02T03:04:57Z","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":"4247243578964ae049b2c7f1db8df0f9b4dccc884c799287e244b245ce690ba6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T15:04:25Z","title_canon_sha256":"9a30e33267fa977dcff202ab77f829c2316a245dfa59ee2a766750353ed4190b"},"schema_version":"1.0","source":{"id":"2606.02357","kind":"arxiv","version":1}},"canonical_sha256":"d816efc8eb21c79a924e4ed7ba91da4bbe9fb9d001f245d66c595011614c3cca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d816efc8eb21c79a924e4ed7ba91da4bbe9fb9d001f245d66c595011614c3cca","first_computed_at":"2026-06-02T03:04:57.040238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T03:04:57.040238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lJnwsb+pYouibql1zbpUPRD7bp7GsPP5cpHxCq/7mHdYQRz1KH5mrK/+HvXNiCS14Ufn0hsIgvwPPs3fsu+3Dw==","signature_status":"signed_v1","signed_at":"2026-06-02T03:04:57.040628Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02357","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ceeb91bbac4654f831aef604dbed38e5678f8fa010d4b8a2c9c4fbd06729084","sha256:5f3719cf07b9069bff7eb3bd54d8eb22045a1063e28706f051143248661b101e"],"state_sha256":"a9bfb571ff5d588303acac69d263177f99d3ffd10a2a56073acd61deccd6b1ad"}