{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EAOAA6PGX2GKYP4KQG2IF2A2NW","short_pith_number":"pith:EAOAA6PG","schema_version":"1.0","canonical_sha256":"201c0079e6be8cac3f8a81b482e81a6d8430b15d9f9dd8fa65f972576b3b4cfd","source":{"kind":"arxiv","id":"2605.17826","version":1},"attestation_state":"computed","paper":{"title":"CounterCount: A Diagnostic Framework for Counting Bias in Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Abdelrahman Eldesokey, Bernard Ghanem, Bushra Bin Hemid, Hassan Alshanqiti, Reem Alzahrani, Zaid Alyafeai","submitted_at":"2026-05-18T04:00:05Z","abstract_excerpt":"Vision-Language Models (VLMs) excel at multimodal reasoning, yet it remains unclear whether their answers are grounded in visual evidence or driven by learned language and world priors. Counting provides a precise testbed: when visual evidence conflicts with canonical object knowledge, a model must rely on the image rather than a prototypical count. We introduce CounterCount, a diagnostic framework for counterfactual counting in VLMs, consisting of paired factual and counterfactual images with edited count-relevant attributes, verified answers, and localized evidence annotations. Evaluating re"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.17826","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T04:00:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"10d3bfab922a38b6603994b2fb094d043d7ce3afbb90b976938efd0a6d6c8945","abstract_canon_sha256":"b9bce5adb81ccf7d021199b4723881c91a035c73aaff4ba9bd713c0347e329d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:00.355004Z","signature_b64":"Cj2Zq63xzB2eOB2hxnuiVmoDbwQg94ehCTKIHkGEOGCLeRszjqhhVmRtw34XNPZu8lVVpJ2WGcGZnafX4mB2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"201c0079e6be8cac3f8a81b482e81a6d8430b15d9f9dd8fa65f972576b3b4cfd","last_reissued_at":"2026-05-20T00:05:00.353938Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:00.353938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CounterCount: A Diagnostic Framework for Counting Bias in Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Abdelrahman Eldesokey, Bernard Ghanem, Bushra Bin Hemid, Hassan Alshanqiti, Reem Alzahrani, Zaid Alyafeai","submitted_at":"2026-05-18T04:00:05Z","abstract_excerpt":"Vision-Language Models (VLMs) excel at multimodal reasoning, yet it remains unclear whether their answers are grounded in visual evidence or driven by learned language and world priors. Counting provides a precise testbed: when visual evidence conflicts with canonical object knowledge, a model must rely on the image rather than a prototypical count. We introduce CounterCount, a diagnostic framework for counterfactual counting in VLMs, consisting of paired factual and counterfactual images with edited count-relevant attributes, verified answers, and localized evidence annotations. Evaluating re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17826","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17826/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.17826","created_at":"2026-05-20T00:05:00.354099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17826v1","created_at":"2026-05-20T00:05:00.354099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17826","created_at":"2026-05-20T00:05:00.354099+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAOAA6PGX2GK","created_at":"2026-05-20T00:05:00.354099+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAOAA6PGX2GKYP4K","created_at":"2026-05-20T00:05:00.354099+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAOAA6PG","created_at":"2026-05-20T00:05:00.354099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EAOAA6PGX2GKYP4KQG2IF2A2NW","json":"https://pith.science/pith/EAOAA6PGX2GKYP4KQG2IF2A2NW.json","graph_json":"https://pith.science/api/pith-number/EAOAA6PGX2GKYP4KQG2IF2A2NW/graph.json","events_json":"https://pith.science/api/pith-number/EAOAA6PGX2GKYP4KQG2IF2A2NW/events.json","paper":"https://pith.science/paper/EAOAA6PG"},"agent_actions":{"view_html":"https://pith.science/pith/EAOAA6PGX2GKYP4KQG2IF2A2NW","download_json":"https://pith.science/pith/EAOAA6PGX2GKYP4KQG2IF2A2NW.json","view_paper":"https://pith.science/paper/EAOAA6PG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17826&json=true","fetch_graph":"https://pith.science/api/pith-number/EAOAA6PGX2GKYP4KQG2IF2A2NW/graph.json","fetch_events":"https://pith.science/api/pith-number/EAOAA6PGX2GKYP4KQG2IF2A2NW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAOAA6PGX2GKYP4KQG2IF2A2NW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAOAA6PGX2GKYP4KQG2IF2A2NW/action/storage_attestation","attest_author":"https://pith.science/pith/EAOAA6PGX2GKYP4KQG2IF2A2NW/action/author_attestation","sign_citation":"https://pith.science/pith/EAOAA6PGX2GKYP4KQG2IF2A2NW/action/citation_signature","submit_replication":"https://pith.science/pith/EAOAA6PGX2GKYP4KQG2IF2A2NW/action/replication_record"}},"created_at":"2026-05-20T00:05:00.354099+00:00","updated_at":"2026-05-20T00:05:00.354099+00:00"}