{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BRBRTYTKJIK2MJBDFPMLA7TAXH","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":"fb5ce204f2e09c3df37dbdb334f921af6362d23e0fd07c96739f54878e97299e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T22:33:02Z","title_canon_sha256":"fa7d1939cb2b64feb797f05896c3a58096d12fcea180c326795470357ba60d34"},"schema_version":"1.0","source":{"id":"2403.08108","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.08108","created_at":"2026-07-05T09:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"2403.08108v2","created_at":"2026-07-05T09:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08108","created_at":"2026-07-05T09:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"BRBRTYTKJIK2","created_at":"2026-07-05T09:03:50Z"},{"alias_kind":"pith_short_16","alias_value":"BRBRTYTKJIK2MJBD","created_at":"2026-07-05T09:03:50Z"},{"alias_kind":"pith_short_8","alias_value":"BRBRTYTK","created_at":"2026-07-05T09:03:50Z"}],"graph_snapshots":[{"event_id":"sha256:ca5bb0c1733c57352355e05e9bc9b2dbf38c3ccec99552a25105d9797614b2cc","target":"graph","created_at":"2026-07-05T09:03:50Z","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/2403.08108/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alvaro Velasquez, Fei Wen, Hanning Chen, Hugo Latapie, Mohsen Imani, Sanggeon Yun, Wenjun Huang, Yang Ni, Yezi Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T22:33:02Z","title":"TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08108","kind":"arxiv","version":2},"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:fe7e6034e8569adafc6490533726088675a57057feb8510c843089589a0b4980","target":"record","created_at":"2026-07-05T09:03:50Z","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":"fb5ce204f2e09c3df37dbdb334f921af6362d23e0fd07c96739f54878e97299e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T22:33:02Z","title_canon_sha256":"fa7d1939cb2b64feb797f05896c3a58096d12fcea180c326795470357ba60d34"},"schema_version":"1.0","source":{"id":"2403.08108","kind":"arxiv","version":2}},"canonical_sha256":"0c4319e26a4a15a624232bd8b07e60b9c0722a8999832d22f0ac7926c7507e73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c4319e26a4a15a624232bd8b07e60b9c0722a8999832d22f0ac7926c7507e73","first_computed_at":"2026-07-05T09:03:50.141640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:03:50.141640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+wVLndJTws2vAnjhRCmhFHysbgb1E28p7b88+Bo+156WIMK4Z/xX7Gna/88nlDCRF+cMVFsUrrZ+9Ok1OKWKCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:03:50.142057Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.08108","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe7e6034e8569adafc6490533726088675a57057feb8510c843089589a0b4980","sha256:ca5bb0c1733c57352355e05e9bc9b2dbf38c3ccec99552a25105d9797614b2cc"],"state_sha256":"e459ec9b94e2390727e5ddb635e0de3e73706fe8fa891cfd0fdfd5225d0f33e0"}