{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4C2AVCDTIFKDJ5DYESBUU27MKY","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":"ffec1735f173b208a5f394d068ead4c41dd9486378c4af021780c8b794d4e4c6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T20:39:16Z","title_canon_sha256":"a6798a8e9380e7414744ee25e58275683e7e120ca82cdc5ac0c52111439de385"},"schema_version":"1.0","source":{"id":"2608.08907","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08907","created_at":"2026-08-11T01:25:41Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08907v1","created_at":"2026-08-11T01:25:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08907","created_at":"2026-08-11T01:25:41Z"},{"alias_kind":"pith_short_12","alias_value":"4C2AVCDTIFKD","created_at":"2026-08-11T01:25:41Z"},{"alias_kind":"pith_short_16","alias_value":"4C2AVCDTIFKDJ5DY","created_at":"2026-08-11T01:25:41Z"},{"alias_kind":"pith_short_8","alias_value":"4C2AVCDT","created_at":"2026-08-11T01:25:41Z"}],"graph_snapshots":[{"event_id":"sha256:5b0a877ec9a8fbc0c37df7ae3c7d083d04c0ad0f888bf713075e27190e64d641","target":"graph","created_at":"2026-08-11T01:25:41Z","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/2608.08907/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Thinking with images allows a multimodal model to compensate for limited perception by invoking visual tools through code. Yet the prevailing SFT-then-RL recipe creates a different supervision misalignment at each stage. SFT is expected to teach how to use tools, but trajectories from stronger teachers may succeed through perceptual capabilities that a smaller student cannot reliably reproduce or exploit, causing the student to imitate tool-call patterns without learning how to make them useful. RL is expected to teach when to use tools, but outcome-only rewards make fallible tool execution a ","authors_text":"Chenghao Sun, Chishui Chen, Delin Mao, Jingwei Song, Linfeng Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T20:39:16Z","title":"ToolVision: Learning When and How to Use Visual Tools with Capability-Aligned Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08907","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":"sha256:8c27a6f932686d01c78d1c6aec14e3334dfe033af5050f038c522f337f7f4f85","target":"record","created_at":"2026-08-11T01:25:41Z","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":"ffec1735f173b208a5f394d068ead4c41dd9486378c4af021780c8b794d4e4c6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T20:39:16Z","title_canon_sha256":"a6798a8e9380e7414744ee25e58275683e7e120ca82cdc5ac0c52111439de385"},"schema_version":"1.0","source":{"id":"2608.08907","kind":"arxiv","version":1}},"canonical_sha256":"e0b40a8873415434f47824834a6bec56162bfa57ea0b1bbe7139133d358a89c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0b40a8873415434f47824834a6bec56162bfa57ea0b1bbe7139133d358a89c8","first_computed_at":"2026-08-11T01:25:41.614862Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:25:41.614862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tGn5uIraYILgDMBYkc4RVSAPMRbQPwRWjMHrQOp7nzt4wD49pULspkCouha9DPWV0VgufDcAhcyYEdAHgeA1BQ==","signature_status":"signed_v1","signed_at":"2026-08-11T01:25:41.617396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08907","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c27a6f932686d01c78d1c6aec14e3334dfe033af5050f038c522f337f7f4f85","sha256:5b0a877ec9a8fbc0c37df7ae3c7d083d04c0ad0f888bf713075e27190e64d641"],"state_sha256":"f80f716ff0fef5b7a99c77e2603136c4f5fe314a678b3f989ab3e21f7f01fd36"}