{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4WYWFNOGBEINDWHXI5YYQ2NC3U","short_pith_number":"pith:4WYWFNOG","schema_version":"1.0","canonical_sha256":"e5b162b5c60910d1d8f747718869a2dd283db509747f870099b54a17276767aa","source":{"kind":"arxiv","id":"2305.08685","version":5},"attestation_state":"computed","paper":{"title":"CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Fang Peng, Linhui Xiao, Ming Yan, Xiaoshan Yang, Yaowei Wang","submitted_at":"2023-05-15T14:42:02Z","abstract_excerpt":"Visual Grounding (VG) is a crucial topic in the field of vision and language, which involves locating a specific region described by expressions within an image. To reduce the reliance on manually labeled data, unsupervised visual grounding have been developed to locate regions using pseudo-labels. However, the performance of existing unsupervised methods is highly dependent on the quality of pseudo-labels and these methods always encounter issues with limited diversity. In order to utilize vision and language pre-trained models to address the grounding problem, and reasonably take advantage o"},"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":"2305.08685","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-15T14:42:02Z","cross_cats_sorted":[],"title_canon_sha256":"f91a515b527ba374d5be008f8451bd885ebd806764ca5e9713b1883b2a9cf146","abstract_canon_sha256":"65751cecd92f394af1791e086d87aebcb100dbe6e09541eb3a1b762869d4738d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:31.312761Z","signature_b64":"bnAkQQq41oakb7gvDKEovrBZLDlZgPvB4OfINf9rhsKys5R3L/pRjAMIisgmtUL8cFVMR32GWVEdfqT/21ilCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5b162b5c60910d1d8f747718869a2dd283db509747f870099b54a17276767aa","last_reissued_at":"2026-07-05T09:37:31.312405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:31.312405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Fang Peng, Linhui Xiao, Ming Yan, Xiaoshan Yang, Yaowei Wang","submitted_at":"2023-05-15T14:42:02Z","abstract_excerpt":"Visual Grounding (VG) is a crucial topic in the field of vision and language, which involves locating a specific region described by expressions within an image. To reduce the reliance on manually labeled data, unsupervised visual grounding have been developed to locate regions using pseudo-labels. However, the performance of existing unsupervised methods is highly dependent on the quality of pseudo-labels and these methods always encounter issues with limited diversity. In order to utilize vision and language pre-trained models to address the grounding problem, and reasonably take advantage o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08685","kind":"arxiv","version":5},"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/2305.08685/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":"2305.08685","created_at":"2026-07-05T09:37:31.312465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.08685v5","created_at":"2026-07-05T09:37:31.312465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08685","created_at":"2026-07-05T09:37:31.312465+00:00"},{"alias_kind":"pith_short_12","alias_value":"4WYWFNOGBEIN","created_at":"2026-07-05T09:37:31.312465+00:00"},{"alias_kind":"pith_short_16","alias_value":"4WYWFNOGBEINDWHX","created_at":"2026-07-05T09:37:31.312465+00:00"},{"alias_kind":"pith_short_8","alias_value":"4WYWFNOG","created_at":"2026-07-05T09:37:31.312465+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/4WYWFNOGBEINDWHXI5YYQ2NC3U","json":"https://pith.science/pith/4WYWFNOGBEINDWHXI5YYQ2NC3U.json","graph_json":"https://pith.science/api/pith-number/4WYWFNOGBEINDWHXI5YYQ2NC3U/graph.json","events_json":"https://pith.science/api/pith-number/4WYWFNOGBEINDWHXI5YYQ2NC3U/events.json","paper":"https://pith.science/paper/4WYWFNOG"},"agent_actions":{"view_html":"https://pith.science/pith/4WYWFNOGBEINDWHXI5YYQ2NC3U","download_json":"https://pith.science/pith/4WYWFNOGBEINDWHXI5YYQ2NC3U.json","view_paper":"https://pith.science/paper/4WYWFNOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.08685&json=true","fetch_graph":"https://pith.science/api/pith-number/4WYWFNOGBEINDWHXI5YYQ2NC3U/graph.json","fetch_events":"https://pith.science/api/pith-number/4WYWFNOGBEINDWHXI5YYQ2NC3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4WYWFNOGBEINDWHXI5YYQ2NC3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4WYWFNOGBEINDWHXI5YYQ2NC3U/action/storage_attestation","attest_author":"https://pith.science/pith/4WYWFNOGBEINDWHXI5YYQ2NC3U/action/author_attestation","sign_citation":"https://pith.science/pith/4WYWFNOGBEINDWHXI5YYQ2NC3U/action/citation_signature","submit_replication":"https://pith.science/pith/4WYWFNOGBEINDWHXI5YYQ2NC3U/action/replication_record"}},"created_at":"2026-07-05T09:37:31.312465+00:00","updated_at":"2026-07-05T09:37:31.312465+00:00"}