{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MR6BKH7AXSDXF55SOOQHW4MLJ6","short_pith_number":"pith:MR6BKH7A","schema_version":"1.0","canonical_sha256":"647c151fe0bc8772f7b273a07b718b4fb87f904c0e962e6ab5ace249888cd9b4","source":{"kind":"arxiv","id":"2409.15035","version":1},"attestation_state":"computed","paper":{"title":"Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Mingqian Feng, Zeliang Zhang, Zhuo Liu","submitted_at":"2024-09-23T14:01:16Z","abstract_excerpt":"CLIP has demonstrated great versatility in adapting to various downstream tasks, such as image editing and generation, visual question answering, and video understanding. However, CLIP-based applications often suffer from misunderstandings regarding user intent, leading to discrepancies between the required number of objects and the actual outputs in image generation tasks. In this work, we empirically investigate the quantity bias in CLIP. By carefully designing different experimental settings and datasets, we comprehensively evaluate CLIP's understanding of quantity from text, image, and cro"},"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":"2409.15035","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-23T14:01:16Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"63f0e0aa6fb028b363969db82382cd0b8cd4ccfe3dce05e9104de6d8132326c1","abstract_canon_sha256":"c8fdbe590e45ea6cf94cab49aa09aa207a0c2d1f7add9ab136df35add6b58a10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:35.494391Z","signature_b64":"lL08ACXlJ/vN9BvRzumdu6TmdcxfIETfTTZanzWir3Kwpyka3t2xCWmaWs32tsIxLhqC1KZTu6VYPOU8Ph+HBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"647c151fe0bc8772f7b273a07b718b4fb87f904c0e962e6ab5ace249888cd9b4","last_reissued_at":"2026-07-05T09:10:35.493864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:35.493864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Mingqian Feng, Zeliang Zhang, Zhuo Liu","submitted_at":"2024-09-23T14:01:16Z","abstract_excerpt":"CLIP has demonstrated great versatility in adapting to various downstream tasks, such as image editing and generation, visual question answering, and video understanding. However, CLIP-based applications often suffer from misunderstandings regarding user intent, leading to discrepancies between the required number of objects and the actual outputs in image generation tasks. In this work, we empirically investigate the quantity bias in CLIP. By carefully designing different experimental settings and datasets, we comprehensively evaluate CLIP's understanding of quantity from text, image, and cro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15035","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/2409.15035/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":"2409.15035","created_at":"2026-07-05T09:10:35.493922+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15035v1","created_at":"2026-07-05T09:10:35.493922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15035","created_at":"2026-07-05T09:10:35.493922+00:00"},{"alias_kind":"pith_short_12","alias_value":"MR6BKH7AXSDX","created_at":"2026-07-05T09:10:35.493922+00:00"},{"alias_kind":"pith_short_16","alias_value":"MR6BKH7AXSDXF55S","created_at":"2026-07-05T09:10:35.493922+00:00"},{"alias_kind":"pith_short_8","alias_value":"MR6BKH7A","created_at":"2026-07-05T09:10:35.493922+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/MR6BKH7AXSDXF55SOOQHW4MLJ6","json":"https://pith.science/pith/MR6BKH7AXSDXF55SOOQHW4MLJ6.json","graph_json":"https://pith.science/api/pith-number/MR6BKH7AXSDXF55SOOQHW4MLJ6/graph.json","events_json":"https://pith.science/api/pith-number/MR6BKH7AXSDXF55SOOQHW4MLJ6/events.json","paper":"https://pith.science/paper/MR6BKH7A"},"agent_actions":{"view_html":"https://pith.science/pith/MR6BKH7AXSDXF55SOOQHW4MLJ6","download_json":"https://pith.science/pith/MR6BKH7AXSDXF55SOOQHW4MLJ6.json","view_paper":"https://pith.science/paper/MR6BKH7A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15035&json=true","fetch_graph":"https://pith.science/api/pith-number/MR6BKH7AXSDXF55SOOQHW4MLJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/MR6BKH7AXSDXF55SOOQHW4MLJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MR6BKH7AXSDXF55SOOQHW4MLJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MR6BKH7AXSDXF55SOOQHW4MLJ6/action/storage_attestation","attest_author":"https://pith.science/pith/MR6BKH7AXSDXF55SOOQHW4MLJ6/action/author_attestation","sign_citation":"https://pith.science/pith/MR6BKH7AXSDXF55SOOQHW4MLJ6/action/citation_signature","submit_replication":"https://pith.science/pith/MR6BKH7AXSDXF55SOOQHW4MLJ6/action/replication_record"}},"created_at":"2026-07-05T09:10:35.493922+00:00","updated_at":"2026-07-05T09:10:35.493922+00:00"}