{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SDDIYYPKZYOMXPKTPIZMB34X3P","short_pith_number":"pith:SDDIYYPK","schema_version":"1.0","canonical_sha256":"90c68c61eace1ccbbd537a32c0ef97dbdfcc5cd780ecaad1b6c00ac7654fbe53","source":{"kind":"arxiv","id":"2112.01518","version":2},"attestation_state":"computed","paper":{"title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Guangyi Chen, Guan Huang, Jie Zhou, Jiwen Lu, Wenliang Zhao, Yansong Tang, Yongming Rao, Zheng Zhu","submitted_at":"2021-12-02T18:59:32Z","abstract_excerpt":"Recent progress has shown that large-scale pre-training using contrastive image-text pairs can be a promising alternative for high-quality visual representation learning from natural language supervision. Benefiting from a broader source of supervision, this new paradigm exhibits impressive transferability to downstream classification tasks and datasets. However, the problem of transferring the knowledge learned from image-text pairs to more complex dense prediction tasks has barely been visited. In this work, we present a new framework for dense prediction by implicitly and explicitly leverag"},"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":"2112.01518","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-02T18:59:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"df61475b392700ddedaaf18037d4decb946ee19d61646db16c2395793e0654aa","abstract_canon_sha256":"0df83f4bfd4381c4f6b78214f5dbd43e7e247c77b36d03cc99635b441c96bdb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:47.420937Z","signature_b64":"s/BOiaQQ2K8BaX72VQSjXllcZ9TYio8q9X6OXmmylu8ShuGoJBEBGobiFpjcRDL55tvclkiGR6ks50rZ/QDJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90c68c61eace1ccbbd537a32c0ef97dbdfcc5cd780ecaad1b6c00ac7654fbe53","last_reissued_at":"2026-07-05T04:06:47.420382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:47.420382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Guangyi Chen, Guan Huang, Jie Zhou, Jiwen Lu, Wenliang Zhao, Yansong Tang, Yongming Rao, Zheng Zhu","submitted_at":"2021-12-02T18:59:32Z","abstract_excerpt":"Recent progress has shown that large-scale pre-training using contrastive image-text pairs can be a promising alternative for high-quality visual representation learning from natural language supervision. Benefiting from a broader source of supervision, this new paradigm exhibits impressive transferability to downstream classification tasks and datasets. However, the problem of transferring the knowledge learned from image-text pairs to more complex dense prediction tasks has barely been visited. In this work, we present a new framework for dense prediction by implicitly and explicitly leverag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01518","kind":"arxiv","version":2},"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/2112.01518/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":"2112.01518","created_at":"2026-07-05T04:06:47.420467+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.01518v2","created_at":"2026-07-05T04:06:47.420467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01518","created_at":"2026-07-05T04:06:47.420467+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDDIYYPKZYOM","created_at":"2026-07-05T04:06:47.420467+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDDIYYPKZYOMXPKT","created_at":"2026-07-05T04:06:47.420467+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDDIYYPK","created_at":"2026-07-05T04:06:47.420467+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.07855","citing_title":"Vision-Language Models for Edge Networks: A Comprehensive Survey","ref_index":70,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SDDIYYPKZYOMXPKTPIZMB34X3P","json":"https://pith.science/pith/SDDIYYPKZYOMXPKTPIZMB34X3P.json","graph_json":"https://pith.science/api/pith-number/SDDIYYPKZYOMXPKTPIZMB34X3P/graph.json","events_json":"https://pith.science/api/pith-number/SDDIYYPKZYOMXPKTPIZMB34X3P/events.json","paper":"https://pith.science/paper/SDDIYYPK"},"agent_actions":{"view_html":"https://pith.science/pith/SDDIYYPKZYOMXPKTPIZMB34X3P","download_json":"https://pith.science/pith/SDDIYYPKZYOMXPKTPIZMB34X3P.json","view_paper":"https://pith.science/paper/SDDIYYPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.01518&json=true","fetch_graph":"https://pith.science/api/pith-number/SDDIYYPKZYOMXPKTPIZMB34X3P/graph.json","fetch_events":"https://pith.science/api/pith-number/SDDIYYPKZYOMXPKTPIZMB34X3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDDIYYPKZYOMXPKTPIZMB34X3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDDIYYPKZYOMXPKTPIZMB34X3P/action/storage_attestation","attest_author":"https://pith.science/pith/SDDIYYPKZYOMXPKTPIZMB34X3P/action/author_attestation","sign_citation":"https://pith.science/pith/SDDIYYPKZYOMXPKTPIZMB34X3P/action/citation_signature","submit_replication":"https://pith.science/pith/SDDIYYPKZYOMXPKTPIZMB34X3P/action/replication_record"}},"created_at":"2026-07-05T04:06:47.420467+00:00","updated_at":"2026-07-05T04:06:47.420467+00:00"}