{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BRBRTYTKJIK2MJBDFPMLA7TAXH","short_pith_number":"pith:BRBRTYTK","schema_version":"1.0","canonical_sha256":"0c4319e26a4a15a624232bd8b07e60b9c0722a8999832d22f0ac7926c7507e73","source":{"kind":"arxiv","id":"2403.08108","version":2},"attestation_state":"computed","paper":{"title":"TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alvaro Velasquez, Fei Wen, Hanning Chen, Hugo Latapie, Mohsen Imani, Sanggeon Yun, Wenjun Huang, Yang Ni, Yezi Liu","submitted_at":"2024-03-12T22:33:02Z","abstract_excerpt":"Task-oriented object detection aims to find objects suitable for accomplishing specific tasks. As a challenging task, it requires simultaneous visual data processing and reasoning under ambiguous semantics. Recent solutions are mainly all-in-one models. However, the object detection backbones are pre-trained without text supervision. Thus, to incorporate task requirements, their intricate models undergo extensive learning on a highly imbalanced and scarce dataset, resulting in capped performance, laborious training, and poor generalizability. In contrast, we propose TaskCLIP, a more natural tw"},"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":"2403.08108","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T22:33:02Z","cross_cats_sorted":[],"title_canon_sha256":"fa7d1939cb2b64feb797f05896c3a58096d12fcea180c326795470357ba60d34","abstract_canon_sha256":"fb5ce204f2e09c3df37dbdb334f921af6362d23e0fd07c96739f54878e97299e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:50.142057Z","signature_b64":"+wVLndJTws2vAnjhRCmhFHysbgb1E28p7b88+Bo+156WIMK4Z/xX7Gna/88nlDCRF+cMVFsUrrZ+9Ok1OKWKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c4319e26a4a15a624232bd8b07e60b9c0722a8999832d22f0ac7926c7507e73","last_reissued_at":"2026-07-05T09:03:50.141640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:50.141640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alvaro Velasquez, Fei Wen, Hanning Chen, Hugo Latapie, Mohsen Imani, Sanggeon Yun, Wenjun Huang, Yang Ni, Yezi Liu","submitted_at":"2024-03-12T22:33:02Z","abstract_excerpt":"Task-oriented object detection aims to find objects suitable for accomplishing specific tasks. As a challenging task, it requires simultaneous visual data processing and reasoning under ambiguous semantics. Recent solutions are mainly all-in-one models. However, the object detection backbones are pre-trained without text supervision. Thus, to incorporate task requirements, their intricate models undergo extensive learning on a highly imbalanced and scarce dataset, resulting in capped performance, laborious training, and poor generalizability. In contrast, we propose TaskCLIP, a more natural tw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08108","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/2403.08108/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":"2403.08108","created_at":"2026-07-05T09:03:50.141697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.08108v2","created_at":"2026-07-05T09:03:50.141697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08108","created_at":"2026-07-05T09:03:50.141697+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRBRTYTKJIK2","created_at":"2026-07-05T09:03:50.141697+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRBRTYTKJIK2MJBD","created_at":"2026-07-05T09:03:50.141697+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRBRTYTK","created_at":"2026-07-05T09:03:50.141697+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10505","citing_title":"J-DDL: Surface Damage Detection and Localization System for Fighter Aircraft","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BRBRTYTKJIK2MJBDFPMLA7TAXH","json":"https://pith.science/pith/BRBRTYTKJIK2MJBDFPMLA7TAXH.json","graph_json":"https://pith.science/api/pith-number/BRBRTYTKJIK2MJBDFPMLA7TAXH/graph.json","events_json":"https://pith.science/api/pith-number/BRBRTYTKJIK2MJBDFPMLA7TAXH/events.json","paper":"https://pith.science/paper/BRBRTYTK"},"agent_actions":{"view_html":"https://pith.science/pith/BRBRTYTKJIK2MJBDFPMLA7TAXH","download_json":"https://pith.science/pith/BRBRTYTKJIK2MJBDFPMLA7TAXH.json","view_paper":"https://pith.science/paper/BRBRTYTK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.08108&json=true","fetch_graph":"https://pith.science/api/pith-number/BRBRTYTKJIK2MJBDFPMLA7TAXH/graph.json","fetch_events":"https://pith.science/api/pith-number/BRBRTYTKJIK2MJBDFPMLA7TAXH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRBRTYTKJIK2MJBDFPMLA7TAXH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRBRTYTKJIK2MJBDFPMLA7TAXH/action/storage_attestation","attest_author":"https://pith.science/pith/BRBRTYTKJIK2MJBDFPMLA7TAXH/action/author_attestation","sign_citation":"https://pith.science/pith/BRBRTYTKJIK2MJBDFPMLA7TAXH/action/citation_signature","submit_replication":"https://pith.science/pith/BRBRTYTKJIK2MJBDFPMLA7TAXH/action/replication_record"}},"created_at":"2026-07-05T09:03:50.141697+00:00","updated_at":"2026-07-05T09:03:50.141697+00:00"}