{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TLMYCJDLNGGESQ2TDVPH3EBJ66","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":"d8f52946a48d6d0489abbe81dc9d2210adf817a3f31a1814568f28aa7c6a6179","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-07T17:06:22Z","title_canon_sha256":"f7273499d81dfc5f422455bf9e721b3633088b3aa98366451a0148d173a0189d"},"schema_version":"1.0","source":{"id":"2404.05016","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05016","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05016v1","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05016","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"pith_short_12","alias_value":"TLMYCJDLNGGE","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"pith_short_16","alias_value":"TLMYCJDLNGGESQ2T","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"pith_short_8","alias_value":"TLMYCJDL","created_at":"2026-07-05T08:05:25Z"}],"graph_snapshots":[{"event_id":"sha256:a4e1201339d14078083b220dc285a2a7176ec8678149a11a2463eee19dd94485","target":"graph","created_at":"2026-07-05T08:05:25Z","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/2404.05016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-world detection poses significant challenges, as it requires the detection of any object using either object class labels or free-form texts. Existing related works often use large-scale manual annotated caption datasets for training, which are extremely expensive to collect. Instead, we propose to transfer knowledge from vision-language models (VLMs) to enrich the open-vocabulary descriptions automatically. Specifically, we bootstrap dense synthetic captions using pre-trained VLMs to provide rich descriptions on different regions in images, and incorporate these captions to train a novel","authors_text":"Davide Modolo, Fanjie Kong, Jiarui Cai, Yanbei Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-07T17:06:22Z","title":"Hyperbolic Learning with Synthetic Captions for Open-World Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05016","kind":"arxiv","version":1},"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":"sha256:70863a82fd5bb51d4bf3d86fde68f6a82391b6383b449bb5904834b0a63b78fb","target":"record","created_at":"2026-07-05T08:05:25Z","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":"d8f52946a48d6d0489abbe81dc9d2210adf817a3f31a1814568f28aa7c6a6179","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-07T17:06:22Z","title_canon_sha256":"f7273499d81dfc5f422455bf9e721b3633088b3aa98366451a0148d173a0189d"},"schema_version":"1.0","source":{"id":"2404.05016","kind":"arxiv","version":1}},"canonical_sha256":"9ad981246b698c4943531d5e7d9029f79d3637816fde3f24421b30a74b6594a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ad981246b698c4943531d5e7d9029f79d3637816fde3f24421b30a74b6594a0","first_computed_at":"2026-07-05T08:05:25.002929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:25.002929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AFktgxBTE9VAEk1/vzJV3b/6kUV6Zs6vVCiOZFvExy/5AgKR4uVeG5Wptmw/2lWTfgq0xJyX/kELVOPgUQdsDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:25.003325Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05016","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70863a82fd5bb51d4bf3d86fde68f6a82391b6383b449bb5904834b0a63b78fb","sha256:a4e1201339d14078083b220dc285a2a7176ec8678149a11a2463eee19dd94485"],"state_sha256":"c6d131701685ee7588faf3b508880ba400667270074589e42f580901582264ca"}