{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TLMYCJDLNGGESQ2TDVPH3EBJ66","short_pith_number":"pith:TLMYCJDL","schema_version":"1.0","canonical_sha256":"9ad981246b698c4943531d5e7d9029f79d3637816fde3f24421b30a74b6594a0","source":{"kind":"arxiv","id":"2404.05016","version":1},"attestation_state":"computed","paper":{"title":"Hyperbolic Learning with Synthetic Captions for Open-World Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Davide Modolo, Fanjie Kong, Jiarui Cai, Yanbei Chen","submitted_at":"2024-04-07T17:06:22Z","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"},"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":"2404.05016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-07T17:06:22Z","cross_cats_sorted":[],"title_canon_sha256":"f7273499d81dfc5f422455bf9e721b3633088b3aa98366451a0148d173a0189d","abstract_canon_sha256":"d8f52946a48d6d0489abbe81dc9d2210adf817a3f31a1814568f28aa7c6a6179"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:25.003325Z","signature_b64":"AFktgxBTE9VAEk1/vzJV3b/6kUV6Zs6vVCiOZFvExy/5AgKR4uVeG5Wptmw/2lWTfgq0xJyX/kELVOPgUQdsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ad981246b698c4943531d5e7d9029f79d3637816fde3f24421b30a74b6594a0","last_reissued_at":"2026-07-05T08:05:25.002929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:25.002929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hyperbolic Learning with Synthetic Captions for Open-World Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Davide Modolo, Fanjie Kong, Jiarui Cai, Yanbei Chen","submitted_at":"2024-04-07T17:06:22Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05016","kind":"arxiv","version":1},"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/2404.05016/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":"2404.05016","created_at":"2026-07-05T08:05:25.002984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05016v1","created_at":"2026-07-05T08:05:25.002984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05016","created_at":"2026-07-05T08:05:25.002984+00:00"},{"alias_kind":"pith_short_12","alias_value":"TLMYCJDLNGGE","created_at":"2026-07-05T08:05:25.002984+00:00"},{"alias_kind":"pith_short_16","alias_value":"TLMYCJDLNGGESQ2T","created_at":"2026-07-05T08:05:25.002984+00:00"},{"alias_kind":"pith_short_8","alias_value":"TLMYCJDL","created_at":"2026-07-05T08:05:25.002984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.08753","citing_title":"Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TLMYCJDLNGGESQ2TDVPH3EBJ66","json":"https://pith.science/pith/TLMYCJDLNGGESQ2TDVPH3EBJ66.json","graph_json":"https://pith.science/api/pith-number/TLMYCJDLNGGESQ2TDVPH3EBJ66/graph.json","events_json":"https://pith.science/api/pith-number/TLMYCJDLNGGESQ2TDVPH3EBJ66/events.json","paper":"https://pith.science/paper/TLMYCJDL"},"agent_actions":{"view_html":"https://pith.science/pith/TLMYCJDLNGGESQ2TDVPH3EBJ66","download_json":"https://pith.science/pith/TLMYCJDLNGGESQ2TDVPH3EBJ66.json","view_paper":"https://pith.science/paper/TLMYCJDL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05016&json=true","fetch_graph":"https://pith.science/api/pith-number/TLMYCJDLNGGESQ2TDVPH3EBJ66/graph.json","fetch_events":"https://pith.science/api/pith-number/TLMYCJDLNGGESQ2TDVPH3EBJ66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TLMYCJDLNGGESQ2TDVPH3EBJ66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TLMYCJDLNGGESQ2TDVPH3EBJ66/action/storage_attestation","attest_author":"https://pith.science/pith/TLMYCJDLNGGESQ2TDVPH3EBJ66/action/author_attestation","sign_citation":"https://pith.science/pith/TLMYCJDLNGGESQ2TDVPH3EBJ66/action/citation_signature","submit_replication":"https://pith.science/pith/TLMYCJDLNGGESQ2TDVPH3EBJ66/action/replication_record"}},"created_at":"2026-07-05T08:05:25.002984+00:00","updated_at":"2026-07-05T08:05:25.002984+00:00"}