{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5HUVFJONZHHUAJGTN7GCEALNPM","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":"1f49b592d1ee5148b224c84da71b156480ded28fa830cafe078d83e4d99dc8d4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-24T20:30:01Z","title_canon_sha256":"b6b1c7f0fc028b315e55749e3e574748472de8f23cf333be3aeaebf743ad0fa9"},"schema_version":"1.0","source":{"id":"2512.21414","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.21414","created_at":"2026-07-10T00:18:42Z"},{"alias_kind":"arxiv_version","alias_value":"2512.21414v2","created_at":"2026-07-10T00:18:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.21414","created_at":"2026-07-10T00:18:42Z"},{"alias_kind":"pith_short_12","alias_value":"5HUVFJONZHHU","created_at":"2026-07-10T00:18:42Z"},{"alias_kind":"pith_short_16","alias_value":"5HUVFJONZHHUAJGT","created_at":"2026-07-10T00:18:42Z"},{"alias_kind":"pith_short_8","alias_value":"5HUVFJON","created_at":"2026-07-10T00:18:42Z"}],"graph_snapshots":[{"event_id":"sha256:1214ff1d1caf123bf78dd0f887dd7a5111b15cccd624d949573ece4560704fad","target":"graph","created_at":"2026-07-10T00:18:42Z","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/2512.21414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent tool-use frameworks powered by vision-language models (VLMs) improve image understanding by grounding model predictions with specialized tools. Broadly, these frameworks leverage VLMs and a pre-specified toolbox to decompose the prediction task into multiple tool calls (often deep learning models) which are composed to make a prediction. The dominant approach to composing tools is using text, via function calls embedded in VLM-generated code or natural language. However, these methods often perform poorly on medical image understanding, where salient information is encoded as spatially-","authors_text":"Alan Q. Wang, Christina Liu, Ehsan Adeli, Jiajun Wu, Joy Hsu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-24T20:30:01Z","title":"A Tool Bottleneck Framework for Clinically-Informed and Interpretable Medical Image Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.21414","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":"sha256:1cf5bb77fd645bee848db340a0eb034cb3225642acdb4ba71d0529ef46f88fca","target":"record","created_at":"2026-07-10T00:18:42Z","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":"1f49b592d1ee5148b224c84da71b156480ded28fa830cafe078d83e4d99dc8d4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-24T20:30:01Z","title_canon_sha256":"b6b1c7f0fc028b315e55749e3e574748472de8f23cf333be3aeaebf743ad0fa9"},"schema_version":"1.0","source":{"id":"2512.21414","kind":"arxiv","version":2}},"canonical_sha256":"e9e952a5cdc9cf4024d36fcc22016d7b096e3c9e11b7d7a667eed722d1b00223","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9e952a5cdc9cf4024d36fcc22016d7b096e3c9e11b7d7a667eed722d1b00223","first_computed_at":"2026-07-10T00:18:42.733078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T00:18:42.733078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PRfmIoOtvczeKj3gHDM6UjLlvXHY6pOphnw1dhG5D8zw/LvJc+ZgcuEgoJnHMjXBXRPs93SV+fXLQTIA540oCw==","signature_status":"signed_v1","signed_at":"2026-07-10T00:18:42.733689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.21414","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cf5bb77fd645bee848db340a0eb034cb3225642acdb4ba71d0529ef46f88fca","sha256:1214ff1d1caf123bf78dd0f887dd7a5111b15cccd624d949573ece4560704fad"],"state_sha256":"b16fa04d40b65113a28a53f61de827d8ec478f0eee92577e56ef7b019cce135a"}