{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LMJAOPU2Y3L2SUZMTO4RBEMJTI","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":"98dad29e60d07b58e21d8a93c2719c991a8a2232a0cff16a163576f7d136d118","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T13:08:03Z","title_canon_sha256":"c6fd8e6b73852482a9bc96123b636d4d0ff3a6c1d3a4243f184c9f6bbac30126"},"schema_version":"1.0","source":{"id":"2509.09732","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09732","created_at":"2026-07-05T12:09:48Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09732v1","created_at":"2026-07-05T12:09:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09732","created_at":"2026-07-05T12:09:48Z"},{"alias_kind":"pith_short_12","alias_value":"LMJAOPU2Y3L2","created_at":"2026-07-05T12:09:48Z"},{"alias_kind":"pith_short_16","alias_value":"LMJAOPU2Y3L2SUZM","created_at":"2026-07-05T12:09:48Z"},{"alias_kind":"pith_short_8","alias_value":"LMJAOPU2","created_at":"2026-07-05T12:09:48Z"}],"graph_snapshots":[{"event_id":"sha256:8984998f69261dbafd41cc5feb909e61622ed38ac7afaff238b3c98e7557051a","target":"graph","created_at":"2026-07-05T12:09:48Z","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/2509.09732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision language models (VLMs) excel at zero-shot visual classification, but their performance on fine-grained tasks and large hierarchical label spaces is understudied. This paper investigates whether structured, tree-based reasoning can enhance VLM performance. We introduce a framework that decomposes classification into interpretable decisions using decision trees and evaluates it on fine-grained (GTSRB) and coarse-grained (CIFAR-10) datasets. Although the model achieves 98.2% accuracy in understanding the tree knowledge, tree-based reasoning consistently underperforms standard zero-shot pro","authors_text":"Daniel Kondermann, Gerrit Gro{\\ss}mann, Islam Mesabah, Peter Neigel, Raj Bhalwankar, Sary Elmansoury, Sebastian J. Vollmer","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T13:08:03Z","title":"Decomposing Visual Classification: Assessing Tree-Based Reasoning in VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09732","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":"sha256:6c52b48e2fdf23817b9c6ce55b900cdc3179b081054fcdd889c6b0273b4860f6","target":"record","created_at":"2026-07-05T12:09:48Z","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":"98dad29e60d07b58e21d8a93c2719c991a8a2232a0cff16a163576f7d136d118","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T13:08:03Z","title_canon_sha256":"c6fd8e6b73852482a9bc96123b636d4d0ff3a6c1d3a4243f184c9f6bbac30126"},"schema_version":"1.0","source":{"id":"2509.09732","kind":"arxiv","version":1}},"canonical_sha256":"5b12073e9ac6d7a9532c9bb91091899a05d0d7605074dfceceac2f3049f5f5ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b12073e9ac6d7a9532c9bb91091899a05d0d7605074dfceceac2f3049f5f5ab","first_computed_at":"2026-07-05T12:09:48.241987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:48.241987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dJo22zsZ6qGrdtO1WNiggpun3vXgwz1PDNqjt5ijWZOnQSKq+Y7RP3Ne1KEpaxrWqtoj16FhWGVT5d7tRtr4Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:48.242683Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.09732","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c52b48e2fdf23817b9c6ce55b900cdc3179b081054fcdd889c6b0273b4860f6","sha256:8984998f69261dbafd41cc5feb909e61622ed38ac7afaff238b3c98e7557051a"],"state_sha256":"e14acacc875889c90c664c945508ae6222f8a77b987ecbc52f932df4eef335a7"}