{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LSV2EWQXJNCCGKXMNKN3L64WGN","short_pith_number":"pith:LSV2EWQX","schema_version":"1.0","canonical_sha256":"5caba25a174b44232aec6a9bb5fb9633684b70f9e763505c1ecc74e75f469bf5","source":{"kind":"arxiv","id":"2309.13097","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Object Counting with Language-Vision Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitris Samaras, Hieu Le, Jingyi Xu","submitted_at":"2023-09-22T14:48:42Z","abstract_excerpt":"Class-agnostic object counting aims to count object instances of an arbitrary class at test time. It is challenging but also enables many potential applications. Current methods require human-annotated exemplars as inputs which are often unavailable for novel categories, especially for autonomous systems. Thus, we propose zero-shot object counting (ZSC), a new setting where only the class name is available during test time. This obviates the need for human annotators and enables automated operation. To perform ZSC, we propose finding a few object crops from the input image and use them as coun"},"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":"2309.13097","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-22T14:48:42Z","cross_cats_sorted":[],"title_canon_sha256":"307d381b37f99a11f8a4e1968254a12db528ee0d6af5079403d98a234af5fe7e","abstract_canon_sha256":"a2af584879dbe75224f043252f0a2b13ff54888b40a8828b0cb50d4f4be9aabb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:47.013870Z","signature_b64":"4XDXZ+NFD2wpUBljTQSq8Y8wBASLXjhT+Q5BYH88RJNODVamP9FiK9Kwa3VU0jx8tCDerDzpLyWQ89dBiHpVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5caba25a174b44232aec6a9bb5fb9633684b70f9e763505c1ecc74e75f469bf5","last_reissued_at":"2026-07-05T06:53:47.013466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:47.013466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Object Counting with Language-Vision Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitris Samaras, Hieu Le, Jingyi Xu","submitted_at":"2023-09-22T14:48:42Z","abstract_excerpt":"Class-agnostic object counting aims to count object instances of an arbitrary class at test time. It is challenging but also enables many potential applications. Current methods require human-annotated exemplars as inputs which are often unavailable for novel categories, especially for autonomous systems. Thus, we propose zero-shot object counting (ZSC), a new setting where only the class name is available during test time. This obviates the need for human annotators and enables automated operation. To perform ZSC, we propose finding a few object crops from the input image and use them as coun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13097","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/2309.13097/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":"2309.13097","created_at":"2026-07-05T06:53:47.013515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.13097v1","created_at":"2026-07-05T06:53:47.013515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13097","created_at":"2026-07-05T06:53:47.013515+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSV2EWQXJNCC","created_at":"2026-07-05T06:53:47.013515+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSV2EWQXJNCCGKXM","created_at":"2026-07-05T06:53:47.013515+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSV2EWQX","created_at":"2026-07-05T06:53:47.013515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29894","citing_title":"Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual Reasoning","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LSV2EWQXJNCCGKXMNKN3L64WGN","json":"https://pith.science/pith/LSV2EWQXJNCCGKXMNKN3L64WGN.json","graph_json":"https://pith.science/api/pith-number/LSV2EWQXJNCCGKXMNKN3L64WGN/graph.json","events_json":"https://pith.science/api/pith-number/LSV2EWQXJNCCGKXMNKN3L64WGN/events.json","paper":"https://pith.science/paper/LSV2EWQX"},"agent_actions":{"view_html":"https://pith.science/pith/LSV2EWQXJNCCGKXMNKN3L64WGN","download_json":"https://pith.science/pith/LSV2EWQXJNCCGKXMNKN3L64WGN.json","view_paper":"https://pith.science/paper/LSV2EWQX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.13097&json=true","fetch_graph":"https://pith.science/api/pith-number/LSV2EWQXJNCCGKXMNKN3L64WGN/graph.json","fetch_events":"https://pith.science/api/pith-number/LSV2EWQXJNCCGKXMNKN3L64WGN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSV2EWQXJNCCGKXMNKN3L64WGN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSV2EWQXJNCCGKXMNKN3L64WGN/action/storage_attestation","attest_author":"https://pith.science/pith/LSV2EWQXJNCCGKXMNKN3L64WGN/action/author_attestation","sign_citation":"https://pith.science/pith/LSV2EWQXJNCCGKXMNKN3L64WGN/action/citation_signature","submit_replication":"https://pith.science/pith/LSV2EWQXJNCCGKXMNKN3L64WGN/action/replication_record"}},"created_at":"2026-07-05T06:53:47.013515+00:00","updated_at":"2026-07-05T06:53:47.013515+00:00"}