{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3GMPPKU6WHXPIMQU3HL2YSEI5S","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":"5ca045a9b69becafe654af8a809658c218d0ac775e30d98a87a09be28a38115d","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-25T05:39:51Z","title_canon_sha256":"e892942400bf4fe35888d26a8ae8e0510d4bc60ab007ab9f4f74f7fedcdfce60"},"schema_version":"1.0","source":{"id":"2607.23052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23052","created_at":"2026-07-28T00:22:09Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23052v1","created_at":"2026-07-28T00:22:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23052","created_at":"2026-07-28T00:22:09Z"},{"alias_kind":"pith_short_12","alias_value":"3GMPPKU6WHXP","created_at":"2026-07-28T00:22:09Z"},{"alias_kind":"pith_short_16","alias_value":"3GMPPKU6WHXPIMQU","created_at":"2026-07-28T00:22:09Z"},{"alias_kind":"pith_short_8","alias_value":"3GMPPKU6","created_at":"2026-07-28T00:22:09Z"}],"graph_snapshots":[{"event_id":"sha256:f3d8f9513772a34f6a5db4e7905cec2340864fe5f27286cc27fe5cb5b753e1ba","target":"graph","created_at":"2026-07-28T00:22:09Z","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/2607.23052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dual-encoder vision-language models (VLMs) expose a similarity interface that enables zero-shot retrieval but fails compositional constraints: queries like \"umbrella and no person\" retrieve images containing both, even when concept detection is reliable. We trace this to an interface-level Bag-of-Concepts effect, where similarity scores approximate mean pooling of concept evidence regardless of operators. Although operator-dependent signals exist in text embeddings, they are too weak or misaligned to affect rankings. Fine-tuning does not reliably resolve this failure because the dominant bottl","authors_text":"Han Zhang, Marios Savvides, Sultan Alshehri, Zhantao Yang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-25T05:39:51Z","title":"Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23052","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":"sha256:31a064c46fb243006154f935a9e3dee202434aca05b3798e2858a5e8c3888a59","target":"record","created_at":"2026-07-28T00:22:09Z","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":"5ca045a9b69becafe654af8a809658c218d0ac775e30d98a87a09be28a38115d","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-25T05:39:51Z","title_canon_sha256":"e892942400bf4fe35888d26a8ae8e0510d4bc60ab007ab9f4f74f7fedcdfce60"},"schema_version":"1.0","source":{"id":"2607.23052","kind":"arxiv","version":1}},"canonical_sha256":"d998f7aa9eb1eef43214d9d7ac4888ec9ad06f60d0f6a411ea1624300be5d6da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d998f7aa9eb1eef43214d9d7ac4888ec9ad06f60d0f6a411ea1624300be5d6da","first_computed_at":"2026-07-28T00:22:09.838769Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T00:22:09.838769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dFSzovulQ9u/po4t3kOEU94r6zfw9nsB6jghQhTv+bKWZUE+Cu40xaeN/B9IcTwMydthFcsHAoXDax7mmSGMAg==","signature_status":"signed_v1","signed_at":"2026-07-28T00:22:09.839613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31a064c46fb243006154f935a9e3dee202434aca05b3798e2858a5e8c3888a59","sha256:f3d8f9513772a34f6a5db4e7905cec2340864fe5f27286cc27fe5cb5b753e1ba"],"state_sha256":"baf745df18b2908a6bacf5c07ec22b35c8e85def7af0e47514a0965f1d728dfb"}