{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VGWZLYCOGGNZJEVV5B7B5TATCQ","short_pith_number":"pith:VGWZLYCO","canonical_record":{"source":{"id":"2402.04630","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T07:26:49Z","cross_cats_sorted":[],"title_canon_sha256":"bacd311c6660489fb444e4d4d7773ee616c485f0eb8e5240f6c762e0ffee3a53","abstract_canon_sha256":"0a53fbdd01ed3304dbd0bab2db55c306d5f0dc4251c0559c6d9602c8c8bfe3ba"},"schema_version":"1.0"},"canonical_sha256":"a9ad95e04e319b9492b5e87e1ecc1314008bd426167c5b3a86f72b7fb1d238ab","source":{"kind":"arxiv","id":"2402.04630","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04630","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04630v1","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04630","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"pith_short_12","alias_value":"VGWZLYCOGGNZ","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"pith_short_16","alias_value":"VGWZLYCOGGNZJEVV","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"pith_short_8","alias_value":"VGWZLYCO","created_at":"2026-07-05T07:42:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VGWZLYCOGGNZJEVV5B7B5TATCQ","target":"record","payload":{"canonical_record":{"source":{"id":"2402.04630","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T07:26:49Z","cross_cats_sorted":[],"title_canon_sha256":"bacd311c6660489fb444e4d4d7773ee616c485f0eb8e5240f6c762e0ffee3a53","abstract_canon_sha256":"0a53fbdd01ed3304dbd0bab2db55c306d5f0dc4251c0559c6d9602c8c8bfe3ba"},"schema_version":"1.0"},"canonical_sha256":"a9ad95e04e319b9492b5e87e1ecc1314008bd426167c5b3a86f72b7fb1d238ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:29.723836Z","signature_b64":"BKHun3EAE6EVzsoTS1lR4abx81xlFeSPSfGhDp0bTRF5brssIQJ2e5kEjVVF6LT6s1eT1xsvUDDoRgUnzc2KAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9ad95e04e319b9492b5e87e1ecc1314008bd426167c5b3a86f72b7fb1d238ab","last_reissued_at":"2026-07-05T07:42:29.723369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:29.723369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.04630","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:42:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YVjAPV8FwwCidAevLgWPY2DsC7NtS6jXjId51jF+HLTc2PNWZw1p3ccG3wlz1/vNTDJoWE+tnUfOMp/2ijhmCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T01:58:47.575395Z"},"content_sha256":"e8ed218112852ade9cd5c9d14941d35826dea1fbd349b819c07bb68397715782","schema_version":"1.0","event_id":"sha256:e8ed218112852ade9cd5c9d14941d35826dea1fbd349b819c07bb68397715782"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VGWZLYCOGGNZJEVV5B7B5TATCQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaxing Huang, Lewei Lu, Sheng Jin, Shijian Lu, Xueying Jiang","submitted_at":"2024-02-07T07:26:49Z","abstract_excerpt":"Inspired by the outstanding zero-shot capability of vision language models (VLMs) in image classification tasks, open-vocabulary object detection has attracted increasing interest by distilling the broad VLM knowledge into detector training. However, most existing open-vocabulary detectors learn by aligning region embeddings with categorical labels (e.g., bicycle) only, disregarding the capability of VLMs on aligning visual embeddings with fine-grained text description of object parts (e.g., pedals and bells). This paper presents DVDet, a Descriptor-Enhanced Open Vocabulary Detector that intro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04630","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/2402.04630/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:42:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2J0E7mkekTZxQqc/tGki616yN8qf6UmFYv/NM9DGWPtYizjjG9iROwNNYJIIwB6kwbpkMF+80Z0VmPi2tIhEDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T01:58:47.575902Z"},"content_sha256":"158d8ab7a6a39351d2e8f1858a6c0f6330712754a9e7cd975fdd10d3db3d3115","schema_version":"1.0","event_id":"sha256:158d8ab7a6a39351d2e8f1858a6c0f6330712754a9e7cd975fdd10d3db3d3115"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VGWZLYCOGGNZJEVV5B7B5TATCQ/bundle.json","state_url":"https://pith.science/pith/VGWZLYCOGGNZJEVV5B7B5TATCQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VGWZLYCOGGNZJEVV5B7B5TATCQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T01:58:47Z","links":{"resolver":"https://pith.science/pith/VGWZLYCOGGNZJEVV5B7B5TATCQ","bundle":"https://pith.science/pith/VGWZLYCOGGNZJEVV5B7B5TATCQ/bundle.json","state":"https://pith.science/pith/VGWZLYCOGGNZJEVV5B7B5TATCQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VGWZLYCOGGNZJEVV5B7B5TATCQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VGWZLYCOGGNZJEVV5B7B5TATCQ","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":"0a53fbdd01ed3304dbd0bab2db55c306d5f0dc4251c0559c6d9602c8c8bfe3ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T07:26:49Z","title_canon_sha256":"bacd311c6660489fb444e4d4d7773ee616c485f0eb8e5240f6c762e0ffee3a53"},"schema_version":"1.0","source":{"id":"2402.04630","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04630","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04630v1","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04630","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"pith_short_12","alias_value":"VGWZLYCOGGNZ","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"pith_short_16","alias_value":"VGWZLYCOGGNZJEVV","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"pith_short_8","alias_value":"VGWZLYCO","created_at":"2026-07-05T07:42:29Z"}],"graph_snapshots":[{"event_id":"sha256:158d8ab7a6a39351d2e8f1858a6c0f6330712754a9e7cd975fdd10d3db3d3115","target":"graph","created_at":"2026-07-05T07:42:29Z","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/2402.04630/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inspired by the outstanding zero-shot capability of vision language models (VLMs) in image classification tasks, open-vocabulary object detection has attracted increasing interest by distilling the broad VLM knowledge into detector training. However, most existing open-vocabulary detectors learn by aligning region embeddings with categorical labels (e.g., bicycle) only, disregarding the capability of VLMs on aligning visual embeddings with fine-grained text description of object parts (e.g., pedals and bells). This paper presents DVDet, a Descriptor-Enhanced Open Vocabulary Detector that intro","authors_text":"Jiaxing Huang, Lewei Lu, Sheng Jin, Shijian Lu, Xueying Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T07:26:49Z","title":"LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04630","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:e8ed218112852ade9cd5c9d14941d35826dea1fbd349b819c07bb68397715782","target":"record","created_at":"2026-07-05T07:42:29Z","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":"0a53fbdd01ed3304dbd0bab2db55c306d5f0dc4251c0559c6d9602c8c8bfe3ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T07:26:49Z","title_canon_sha256":"bacd311c6660489fb444e4d4d7773ee616c485f0eb8e5240f6c762e0ffee3a53"},"schema_version":"1.0","source":{"id":"2402.04630","kind":"arxiv","version":1}},"canonical_sha256":"a9ad95e04e319b9492b5e87e1ecc1314008bd426167c5b3a86f72b7fb1d238ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9ad95e04e319b9492b5e87e1ecc1314008bd426167c5b3a86f72b7fb1d238ab","first_computed_at":"2026-07-05T07:42:29.723369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:42:29.723369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BKHun3EAE6EVzsoTS1lR4abx81xlFeSPSfGhDp0bTRF5brssIQJ2e5kEjVVF6LT6s1eT1xsvUDDoRgUnzc2KAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:42:29.723836Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.04630","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8ed218112852ade9cd5c9d14941d35826dea1fbd349b819c07bb68397715782","sha256:158d8ab7a6a39351d2e8f1858a6c0f6330712754a9e7cd975fdd10d3db3d3115"],"state_sha256":"9a788097ecc614314b087663b3076af9735b3bad23841dab05f18457c3351cdf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B1qhk6xAe7qvIhsRgHlTZ9qxxqkYOkoflloz9VW64A+yytWMSXTPwKyg//AcZnfm+4PrIydTRHw/ShWkDLU0DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T01:58:47.581790Z","bundle_sha256":"88585f0f0b0503dade456e311807baaa4a40e809eff6a500293c66cb9ef68e5c"}}