{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WAMDGQNGQ34OEXDXV423QYDWZL","short_pith_number":"pith:WAMDGQNG","canonical_record":{"source":{"id":"2405.19854","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T09:03:23Z","cross_cats_sorted":[],"title_canon_sha256":"d6d12c747216073f67539966a1d0a90892ce44b8e7ee819dfd8a817a62258806","abstract_canon_sha256":"ae9aa1ca6407126a6b9dc83b6f635d62130951a14acf7fa3933f067f67e9f163"},"schema_version":"1.0"},"canonical_sha256":"b0183341a686f8e25c77af35b86076cafe88bbc133cadfcb014fc3175f8606b9","source":{"kind":"arxiv","id":"2405.19854","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19854","created_at":"2026-07-05T08:25:13Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19854v1","created_at":"2026-07-05T08:25:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19854","created_at":"2026-07-05T08:25:13Z"},{"alias_kind":"pith_short_12","alias_value":"WAMDGQNGQ34O","created_at":"2026-07-05T08:25:13Z"},{"alias_kind":"pith_short_16","alias_value":"WAMDGQNGQ34OEXDX","created_at":"2026-07-05T08:25:13Z"},{"alias_kind":"pith_short_8","alias_value":"WAMDGQNG","created_at":"2026-07-05T08:25:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WAMDGQNGQ34OEXDXV423QYDWZL","target":"record","payload":{"canonical_record":{"source":{"id":"2405.19854","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T09:03:23Z","cross_cats_sorted":[],"title_canon_sha256":"d6d12c747216073f67539966a1d0a90892ce44b8e7ee819dfd8a817a62258806","abstract_canon_sha256":"ae9aa1ca6407126a6b9dc83b6f635d62130951a14acf7fa3933f067f67e9f163"},"schema_version":"1.0"},"canonical_sha256":"b0183341a686f8e25c77af35b86076cafe88bbc133cadfcb014fc3175f8606b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:13.376334Z","signature_b64":"GzA9IyEnvaRkZNYwC2qUL4+lm/jdYbVRx2Z+xk48KMiPPnTuze7gk5/QburdstP4WPHJkcYrZURfO0Vuf9ZRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0183341a686f8e25c77af35b86076cafe88bbc133cadfcb014fc3175f8606b9","last_reissued_at":"2026-07-05T08:25:13.375974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:13.375974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.19854","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":"2026-07-05T08:25:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FcssjVWvmrswn9VuKxdxxZrmafKZZWelBsp1wsPx3lB00dYJK3XbFiSYXcXVF71l4qXadWVVztzda3uEuJjRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:36:48.859772Z"},"content_sha256":"c0b8830e38430297aa767a9bdaaf9916aabf3387bc6dd9bb73a9619f4d9b7b41","schema_version":"1.0","event_id":"sha256:c0b8830e38430297aa767a9bdaaf9916aabf3387bc6dd9bb73a9619f4d9b7b41"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WAMDGQNGQ34OEXDXV423QYDWZL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangyi Chen, Han Zhang, Hao Chen, Kai Hu, Marios Savvides, Zhantao Yang","submitted_at":"2024-05-30T09:03:23Z","abstract_excerpt":"Open-vocabulary object detection (OVD) requires solid modeling of the region-semantic relationship, which could be learned from massive region-text pairs. However, such data is limited in practice due to significant annotation costs. In this work, we propose RTGen to generate scalable open-vocabulary region-text pairs and demonstrate its capability to boost the performance of open-vocabulary object detection. RTGen includes both text-to-region and region-to-text generation processes on scalable image-caption data. The text-to-region generation is powered by image inpainting, directed by our pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19854","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/2405.19854/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":"2026-07-05T08:25:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GVqK7ClehDTnSlsQoUfvehrH5+46rXMfbkkC0+Jl2JtNdcESAKx+hd0Ylt6gEDIWj3HluwWU00qnKbEmPt80DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:36:48.860293Z"},"content_sha256":"999ce8db21f045c9781bf50b654bd5b2cdc29fdabc4dfb955bacff0ca67beddf","schema_version":"1.0","event_id":"sha256:999ce8db21f045c9781bf50b654bd5b2cdc29fdabc4dfb955bacff0ca67beddf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WAMDGQNGQ34OEXDXV423QYDWZL/bundle.json","state_url":"https://pith.science/pith/WAMDGQNGQ34OEXDXV423QYDWZL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WAMDGQNGQ34OEXDXV423QYDWZL/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":"2026-08-14T13:36:48Z","links":{"resolver":"https://pith.science/pith/WAMDGQNGQ34OEXDXV423QYDWZL","bundle":"https://pith.science/pith/WAMDGQNGQ34OEXDXV423QYDWZL/bundle.json","state":"https://pith.science/pith/WAMDGQNGQ34OEXDXV423QYDWZL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WAMDGQNGQ34OEXDXV423QYDWZL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WAMDGQNGQ34OEXDXV423QYDWZL","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":"ae9aa1ca6407126a6b9dc83b6f635d62130951a14acf7fa3933f067f67e9f163","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T09:03:23Z","title_canon_sha256":"d6d12c747216073f67539966a1d0a90892ce44b8e7ee819dfd8a817a62258806"},"schema_version":"1.0","source":{"id":"2405.19854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19854","created_at":"2026-07-05T08:25:13Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19854v1","created_at":"2026-07-05T08:25:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19854","created_at":"2026-07-05T08:25:13Z"},{"alias_kind":"pith_short_12","alias_value":"WAMDGQNGQ34O","created_at":"2026-07-05T08:25:13Z"},{"alias_kind":"pith_short_16","alias_value":"WAMDGQNGQ34OEXDX","created_at":"2026-07-05T08:25:13Z"},{"alias_kind":"pith_short_8","alias_value":"WAMDGQNG","created_at":"2026-07-05T08:25:13Z"}],"graph_snapshots":[{"event_id":"sha256:999ce8db21f045c9781bf50b654bd5b2cdc29fdabc4dfb955bacff0ca67beddf","target":"graph","created_at":"2026-07-05T08:25:13Z","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/2405.19854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-vocabulary object detection (OVD) requires solid modeling of the region-semantic relationship, which could be learned from massive region-text pairs. However, such data is limited in practice due to significant annotation costs. In this work, we propose RTGen to generate scalable open-vocabulary region-text pairs and demonstrate its capability to boost the performance of open-vocabulary object detection. RTGen includes both text-to-region and region-to-text generation processes on scalable image-caption data. The text-to-region generation is powered by image inpainting, directed by our pr","authors_text":"Fangyi Chen, Han Zhang, Hao Chen, Kai Hu, Marios Savvides, Zhantao Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T09:03:23Z","title":"RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19854","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:c0b8830e38430297aa767a9bdaaf9916aabf3387bc6dd9bb73a9619f4d9b7b41","target":"record","created_at":"2026-07-05T08:25:13Z","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":"ae9aa1ca6407126a6b9dc83b6f635d62130951a14acf7fa3933f067f67e9f163","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T09:03:23Z","title_canon_sha256":"d6d12c747216073f67539966a1d0a90892ce44b8e7ee819dfd8a817a62258806"},"schema_version":"1.0","source":{"id":"2405.19854","kind":"arxiv","version":1}},"canonical_sha256":"b0183341a686f8e25c77af35b86076cafe88bbc133cadfcb014fc3175f8606b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0183341a686f8e25c77af35b86076cafe88bbc133cadfcb014fc3175f8606b9","first_computed_at":"2026-07-05T08:25:13.375974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:13.375974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GzA9IyEnvaRkZNYwC2qUL4+lm/jdYbVRx2Z+xk48KMiPPnTuze7gk5/QburdstP4WPHJkcYrZURfO0Vuf9ZRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:13.376334Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0b8830e38430297aa767a9bdaaf9916aabf3387bc6dd9bb73a9619f4d9b7b41","sha256:999ce8db21f045c9781bf50b654bd5b2cdc29fdabc4dfb955bacff0ca67beddf"],"state_sha256":"ee2be042e09efd8863507ae67bbac91a4f7104041ac252345921999a1708ce82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VOrBWO+NXOMtaB6Gc8NyfQDgDsqGxtGFwcNPvjlbYMmgjKtaxlilo+kPCs+f2oqsjvhKqhz1IlASixTcdoLKBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T13:36:48.866242Z","bundle_sha256":"86058658ae3a8c96ab7a2259531c68d1ae962311a0afae8cecca266d50bdb31f"}}