{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L5DT2XKQ27B55FIII23KPLGIZJ","short_pith_number":"pith:L5DT2XKQ","schema_version":"1.0","canonical_sha256":"5f473d5d50d7c3de950846b6a7acc8ca50cf00cade1e4e16e7c946187a5513f1","source":{"kind":"arxiv","id":"2304.10817","version":1},"attestation_state":"computed","paper":{"title":"Can SAM Count Anything? An Empirical Study on SAM Counting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Qinnan Shangguan, Xiaopeng Hong, Zhiheng Ma","submitted_at":"2023-04-21T08:59:48Z","abstract_excerpt":"Meta AI recently released the Segment Anything model (SAM), which has garnered attention due to its impressive performance in class-agnostic segmenting. In this study, we explore the use of SAM for the challenging task of few-shot object counting, which involves counting objects of an unseen category by providing a few bounding boxes of examples. We compare SAM's performance with other few-shot counting methods and find that it is currently unsatisfactory without further fine-tuning, particularly for small and crowded objects. Code can be found at \\url{https://github.com/Vision-Intelligence-an"},"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":"2304.10817","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-21T08:59:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"302e3430ffeb1a853c7bff74ca5e0b17a186302b2ad735ef8ceaea3623f12d7d","abstract_canon_sha256":"46b38a47858e6b45cd4ef0181f33ef301d42d5baaaab24718c00e5e234ce9c60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:15.659429Z","signature_b64":"Qby4GFHjhfFLP/abJ/0zccZiUFHfozpT6ppT/3ytM+j+SzMtO/iPJ0GHnlTzxw5inl8MFAJANn//89ybMSofCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f473d5d50d7c3de950846b6a7acc8ca50cf00cade1e4e16e7c946187a5513f1","last_reissued_at":"2026-07-05T06:03:15.659029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:15.659029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can SAM Count Anything? An Empirical Study on SAM Counting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Qinnan Shangguan, Xiaopeng Hong, Zhiheng Ma","submitted_at":"2023-04-21T08:59:48Z","abstract_excerpt":"Meta AI recently released the Segment Anything model (SAM), which has garnered attention due to its impressive performance in class-agnostic segmenting. In this study, we explore the use of SAM for the challenging task of few-shot object counting, which involves counting objects of an unseen category by providing a few bounding boxes of examples. We compare SAM's performance with other few-shot counting methods and find that it is currently unsatisfactory without further fine-tuning, particularly for small and crowded objects. Code can be found at \\url{https://github.com/Vision-Intelligence-an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10817","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/2304.10817/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":"2304.10817","created_at":"2026-07-05T06:03:15.659085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.10817v1","created_at":"2026-07-05T06:03:15.659085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10817","created_at":"2026-07-05T06:03:15.659085+00:00"},{"alias_kind":"pith_short_12","alias_value":"L5DT2XKQ27B5","created_at":"2026-07-05T06:03:15.659085+00:00"},{"alias_kind":"pith_short_16","alias_value":"L5DT2XKQ27B55FII","created_at":"2026-07-05T06:03:15.659085+00:00"},{"alias_kind":"pith_short_8","alias_value":"L5DT2XKQ","created_at":"2026-07-05T06:03:15.659085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02139","citing_title":"AdaCount: Training-Free Similarity-Guided Spatial and Feature Adaptation for Zero-Shot Object Counting","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L5DT2XKQ27B55FIII23KPLGIZJ","json":"https://pith.science/pith/L5DT2XKQ27B55FIII23KPLGIZJ.json","graph_json":"https://pith.science/api/pith-number/L5DT2XKQ27B55FIII23KPLGIZJ/graph.json","events_json":"https://pith.science/api/pith-number/L5DT2XKQ27B55FIII23KPLGIZJ/events.json","paper":"https://pith.science/paper/L5DT2XKQ"},"agent_actions":{"view_html":"https://pith.science/pith/L5DT2XKQ27B55FIII23KPLGIZJ","download_json":"https://pith.science/pith/L5DT2XKQ27B55FIII23KPLGIZJ.json","view_paper":"https://pith.science/paper/L5DT2XKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.10817&json=true","fetch_graph":"https://pith.science/api/pith-number/L5DT2XKQ27B55FIII23KPLGIZJ/graph.json","fetch_events":"https://pith.science/api/pith-number/L5DT2XKQ27B55FIII23KPLGIZJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L5DT2XKQ27B55FIII23KPLGIZJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L5DT2XKQ27B55FIII23KPLGIZJ/action/storage_attestation","attest_author":"https://pith.science/pith/L5DT2XKQ27B55FIII23KPLGIZJ/action/author_attestation","sign_citation":"https://pith.science/pith/L5DT2XKQ27B55FIII23KPLGIZJ/action/citation_signature","submit_replication":"https://pith.science/pith/L5DT2XKQ27B55FIII23KPLGIZJ/action/replication_record"}},"created_at":"2026-07-05T06:03:15.659085+00:00","updated_at":"2026-07-05T06:03:15.659085+00:00"}