{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KBZXEVP4HH7M3E7KUV6BLHOUIK","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":"eb166ab49f4e27aa8c762bf0cd617d40c7425160e4b726e25dd20f17a19c9ceb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-09T12:56:54Z","title_canon_sha256":"fe9b130c307b7ef920f0cc9c9b388fb20900d3c2a56fb5fcd9b9ff4defead7d1"},"schema_version":"1.0","source":{"id":"2304.04231","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.04231","created_at":"2026-07-05T05:59:13Z"},{"alias_kind":"arxiv_version","alias_value":"2304.04231v1","created_at":"2026-07-05T05:59:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04231","created_at":"2026-07-05T05:59:13Z"},{"alias_kind":"pith_short_12","alias_value":"KBZXEVP4HH7M","created_at":"2026-07-05T05:59:13Z"},{"alias_kind":"pith_short_16","alias_value":"KBZXEVP4HH7M3E7K","created_at":"2026-07-05T05:59:13Z"},{"alias_kind":"pith_short_8","alias_value":"KBZXEVP4","created_at":"2026-07-05T05:59:13Z"}],"graph_snapshots":[{"event_id":"sha256:c1ce7a289b42a709b8da55192e61526c7f0a482f887c693078fd013577aa31cd","target":"graph","created_at":"2026-07-05T05:59:13Z","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/2304.04231/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised crowd counting relies heavily on costly manual labeling, which is difficult and expensive, especially in dense scenes. To alleviate the problem, we propose a novel unsupervised framework for crowd counting, named CrowdCLIP. The core idea is built on two observations: 1) the recent contrastive pre-trained vision-language model (CLIP) has presented impressive performance on various downstream tasks; 2) there is a natural mapping between crowd patches and count text. To the best of our knowledge, CrowdCLIP is the first to investigate the vision language knowledge to solve the counting ","authors_text":"Dingkang Liang, Jiahao Xie, Wei Xu, Xiang Bai, Xiaoqing Ye, Zhikang Zou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-09T12:56:54Z","title":"CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04231","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:e2607481c12b0d063c9d889c82badfa2bbc9bee26d80cba8ba2964e2f03fd433","target":"record","created_at":"2026-07-05T05:59:13Z","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":"eb166ab49f4e27aa8c762bf0cd617d40c7425160e4b726e25dd20f17a19c9ceb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-09T12:56:54Z","title_canon_sha256":"fe9b130c307b7ef920f0cc9c9b388fb20900d3c2a56fb5fcd9b9ff4defead7d1"},"schema_version":"1.0","source":{"id":"2304.04231","kind":"arxiv","version":1}},"canonical_sha256":"50737255fc39fecd93eaa57c159dd4429a5089d7418689f88ab119c96fbc77dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50737255fc39fecd93eaa57c159dd4429a5089d7418689f88ab119c96fbc77dd","first_computed_at":"2026-07-05T05:59:13.651689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:59:13.651689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Qa5B9cFWO/W1Qjejln8hUZ8wbyqbc/qabQj6GzxZbfPZAiNdujB+6BvoOsXBV1aHtgsg++UEhSefCOva2ZUDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:59:13.652171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.04231","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2607481c12b0d063c9d889c82badfa2bbc9bee26d80cba8ba2964e2f03fd433","sha256:c1ce7a289b42a709b8da55192e61526c7f0a482f887c693078fd013577aa31cd"],"state_sha256":"fcaea77e99c7ddea46e64c2537bf8f6176f99ba502bb7c5d0ce25687a00f181b"}