{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4A6NIF3X6UNPNADO2FNHQVEVRJ","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":"e2626c12519f6752512f1f2972d802b7be261dafe2bf81631f4e9304776ec4e9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-11-20T23:05:46Z","title_canon_sha256":"34bf9eae34cb8f3a176499e0c5f64c32041f56d409623a795f6243d953e3ef78"},"schema_version":"1.0","source":{"id":"2011.10678","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.10678","created_at":"2026-07-05T02:22:39Z"},{"alias_kind":"arxiv_version","alias_value":"2011.10678v2","created_at":"2026-07-05T02:22:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.10678","created_at":"2026-07-05T02:22:39Z"},{"alias_kind":"pith_short_12","alias_value":"4A6NIF3X6UNP","created_at":"2026-07-05T02:22:39Z"},{"alias_kind":"pith_short_16","alias_value":"4A6NIF3X6UNPNADO","created_at":"2026-07-05T02:22:39Z"},{"alias_kind":"pith_short_8","alias_value":"4A6NIF3X","created_at":"2026-07-05T02:22:39Z"}],"graph_snapshots":[{"event_id":"sha256:2dec69d04c60550119e6b4b222c8ae9b5467b6c21fa1bf365dc95af6e81f746d","target":"graph","created_at":"2026-07-05T02:22:39Z","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/2011.10678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the remarkable accuracy of deep neural networks in object detection, they are costly to train and scale due to supervision requirements. Particularly, learning more object categories typically requires proportionally more bounding box annotations. Weakly supervised and zero-shot learning techniques have been explored to scale object detectors to more categories with less supervision, but they have not been as successful and widely adopted as supervised models. In this paper, we put forth a novel formulation of the object detection problem, namely open-vocabulary object detection, which","authors_text":"Alireza Zareian, Derek Hao Hu, Kevin Dela Rosa, Shih-Fu Chang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-11-20T23:05:46Z","title":"Open-Vocabulary Object Detection Using Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.10678","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":"sha256:3d66caeecfd32dd7be56702bbb775d649cd7c9f48c59612441898b4d87d1f912","target":"record","created_at":"2026-07-05T02:22:39Z","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":"e2626c12519f6752512f1f2972d802b7be261dafe2bf81631f4e9304776ec4e9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-11-20T23:05:46Z","title_canon_sha256":"34bf9eae34cb8f3a176499e0c5f64c32041f56d409623a795f6243d953e3ef78"},"schema_version":"1.0","source":{"id":"2011.10678","kind":"arxiv","version":2}},"canonical_sha256":"e03cd41777f51af6806ed15a7854958a5ab6b6ba8a76278515ce968d5fdf6c4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e03cd41777f51af6806ed15a7854958a5ab6b6ba8a76278515ce968d5fdf6c4d","first_computed_at":"2026-07-05T02:22:39.325077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:22:39.325077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fpIqoETyLTZEEFc0LMgjsNm3ttealXQ7S6IxLOOnO4YekW7tAqxZwPxgwyn2zBbSfktyhnu+OdNZwtYuVUVHCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:22:39.325464Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.10678","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d66caeecfd32dd7be56702bbb775d649cd7c9f48c59612441898b4d87d1f912","sha256:2dec69d04c60550119e6b4b222c8ae9b5467b6c21fa1bf365dc95af6e81f746d"],"state_sha256":"a1f6f40e33ac9b5a93e2747f769b4a78fc940339b4aeeb67fc7aaf88b33c6079"}