{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DIJL72J34BEET6OPLHDYVBMNCJ","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":"6cc8a475dc0922d125b7620be7af2437690c7679ded94faa4e869439e47ccc68","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T20:37:30Z","title_canon_sha256":"c7445efb75dc285dc7d2b7c4a09496d757244a8e5ba66514ebdcc192336c2451"},"schema_version":"1.0","source":{"id":"1909.02097","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.02097","created_at":"2026-07-05T00:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"1909.02097v1","created_at":"2026-07-05T00:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02097","created_at":"2026-07-05T00:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"DIJL72J34BEE","created_at":"2026-07-05T00:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"DIJL72J34BEET6OP","created_at":"2026-07-05T00:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"DIJL72J3","created_at":"2026-07-05T00:02:30Z"}],"graph_snapshots":[{"event_id":"sha256:e0cfeccb1fbd2b4bd10c3bca69501078b7a130c4b44d797e97f54af4d3e4c671","target":"graph","created_at":"2026-07-05T00:02:30Z","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/1909.02097/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Object detection plays an important role in current solutions to vision and language tasks like image captioning and visual question answering. However, popular models like Faster R-CNN rely on a costly process of annotating ground-truths for both the bounding boxes and their corresponding semantic labels, making it less amenable as a primitive task for transfer learning. In this paper, we examine the effect of decoupling box proposal and featurization for down-stream tasks. The key insight is that this allows us to leverage a large amount of labeled annotations that were previously unavailabl","authors_text":"Bo Pang, Piyush Sharma, Radu Soricut, Soravit Changpinyo","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T20:37:30Z","title":"Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02097","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":"sha256:6fda750fbd8ffa15d3871cf01a33308cda797a8c2a92a18e72767087373d77da","target":"record","created_at":"2026-07-05T00:02:30Z","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":"6cc8a475dc0922d125b7620be7af2437690c7679ded94faa4e869439e47ccc68","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T20:37:30Z","title_canon_sha256":"c7445efb75dc285dc7d2b7c4a09496d757244a8e5ba66514ebdcc192336c2451"},"schema_version":"1.0","source":{"id":"1909.02097","kind":"arxiv","version":1}},"canonical_sha256":"1a12bfe93be04849f9cf59c78a858d1250c2048b698ecd3a7e0a02edec8684bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a12bfe93be04849f9cf59c78a858d1250c2048b698ecd3a7e0a02edec8684bf","first_computed_at":"2026-07-05T00:02:30.320090Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:02:30.320090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YvPM9PvLeV18vs5DjASIi0lnu/BlYFMlp7EK9wXeixIWccUDCrHFFq1vg29QGRs95qDVhsclWTWGBr65f/7FAw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:02:30.320499Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.02097","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fda750fbd8ffa15d3871cf01a33308cda797a8c2a92a18e72767087373d77da","sha256:e0cfeccb1fbd2b4bd10c3bca69501078b7a130c4b44d797e97f54af4d3e4c671"],"state_sha256":"46ca085972ed3b6edc8f5fdce7fb191f50f60c62056881f47d781338aabc6d3a"}