{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:N6QMLDIVZ4YHTNTQTMQZVZQ5E5","short_pith_number":"pith:N6QMLDIV","canonical_record":{"source":{"id":"1902.04213","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-12T02:04:49Z","cross_cats_sorted":[],"title_canon_sha256":"c38fea95355563d101db03e92c0c189d4f4382bcf8e2096ed190fade27b35c02","abstract_canon_sha256":"1c346c1354d754083e09d8261744a74ef4f195a607696895cba2b92f4ca88401"},"schema_version":"1.0"},"canonical_sha256":"6fa0c58d15cf3079b6709b219ae61d277c2bcdc86c735cad1473fce4191fed97","source":{"kind":"arxiv","id":"1902.04213","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.04213","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"arxiv_version","alias_value":"1902.04213v3","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04213","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"pith_short_12","alias_value":"N6QMLDIVZ4YH","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"N6QMLDIVZ4YHTNTQ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"N6QMLDIV","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:N6QMLDIVZ4YHTNTQTMQZVZQ5E5","target":"record","payload":{"canonical_record":{"source":{"id":"1902.04213","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-12T02:04:49Z","cross_cats_sorted":[],"title_canon_sha256":"c38fea95355563d101db03e92c0c189d4f4382bcf8e2096ed190fade27b35c02","abstract_canon_sha256":"1c346c1354d754083e09d8261744a74ef4f195a607696895cba2b92f4ca88401"},"schema_version":"1.0"},"canonical_sha256":"6fa0c58d15cf3079b6709b219ae61d277c2bcdc86c735cad1473fce4191fed97","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:04.979189Z","signature_b64":"FSXJ56zz1PcL5enD/eHeWeKuLATJIwRcR3TKsAeivF7HqHibeCao0HQZ9ZLTNqOO1FLiObPyAv0Scen3mxJtDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fa0c58d15cf3079b6709b219ae61d277c2bcdc86c735cad1473fce4191fed97","last_reissued_at":"2026-05-17T23:51:04.978676Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:04.978676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.04213","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Uuem31iDEyQdIpQGo32aC+yg1H9JC42JouWlpuO2mNQGgQlHqF4yJ4fvF4V/pM4+7nZtXx5M5VOs8ddl5SkDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:29:21.930858Z"},"content_sha256":"5f82c59062f696e45e94f295416789600e7492eded892d893ce2c49e75b585b1","schema_version":"1.0","event_id":"sha256:5f82c59062f696e45e94f295416789600e7492eded892d893ce2c49e75b585b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:N6QMLDIVZ4YHTNTQTMQZVZQ5E5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"You Only Look & Listen Once: Towards Fast and Accurate Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaorui Deng, Guanghui Xu, Kui Jia, Mingkui Tan, Qi Wu, Yanwu Xu, ZhuLiang Yu","submitted_at":"2019-02-12T02:04:49Z","abstract_excerpt":"Visual Grounding (VG) aims to locate the most relevant region in an image, based on a flexible natural language query but not a pre-defined label, thus it can be a more useful technique than object detection in practice. Most state-of-the-art methods in VG operate in a two-stage manner, wherein the first stage an object detector is adopted to generate a set of object proposals from the input image and the second stage is simply formulated as a cross-modal matching problem that finds the best match between the language query and all region proposals. This is rather inefficient because there mig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04213","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:51:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"shUMdWee2EMHA0CvQKIcyO+WVe909YZOpA7ErLiJd1LkPq7w3BydELeESv456w86oF3/qGp/o5o/Dm4poQb3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:29:21.931594Z"},"content_sha256":"33415ae736f45c4b8efa1bbfb3c1cb47d4f735fdb09cf24ae9182cdf79f5ce22","schema_version":"1.0","event_id":"sha256:33415ae736f45c4b8efa1bbfb3c1cb47d4f735fdb09cf24ae9182cdf79f5ce22"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N6QMLDIVZ4YHTNTQTMQZVZQ5E5/bundle.json","state_url":"https://pith.science/pith/N6QMLDIVZ4YHTNTQTMQZVZQ5E5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N6QMLDIVZ4YHTNTQTMQZVZQ5E5/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":"2026-05-25T18:29:21Z","links":{"resolver":"https://pith.science/pith/N6QMLDIVZ4YHTNTQTMQZVZQ5E5","bundle":"https://pith.science/pith/N6QMLDIVZ4YHTNTQTMQZVZQ5E5/bundle.json","state":"https://pith.science/pith/N6QMLDIVZ4YHTNTQTMQZVZQ5E5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N6QMLDIVZ4YHTNTQTMQZVZQ5E5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:N6QMLDIVZ4YHTNTQTMQZVZQ5E5","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":"1c346c1354d754083e09d8261744a74ef4f195a607696895cba2b92f4ca88401","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-12T02:04:49Z","title_canon_sha256":"c38fea95355563d101db03e92c0c189d4f4382bcf8e2096ed190fade27b35c02"},"schema_version":"1.0","source":{"id":"1902.04213","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.04213","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"arxiv_version","alias_value":"1902.04213v3","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04213","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"pith_short_12","alias_value":"N6QMLDIVZ4YH","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"N6QMLDIVZ4YHTNTQ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"N6QMLDIV","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:33415ae736f45c4b8efa1bbfb3c1cb47d4f735fdb09cf24ae9182cdf79f5ce22","target":"graph","created_at":"2026-05-17T23:51:04Z","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"},"paper":{"abstract_excerpt":"Visual Grounding (VG) aims to locate the most relevant region in an image, based on a flexible natural language query but not a pre-defined label, thus it can be a more useful technique than object detection in practice. Most state-of-the-art methods in VG operate in a two-stage manner, wherein the first stage an object detector is adopted to generate a set of object proposals from the input image and the second stage is simply formulated as a cross-modal matching problem that finds the best match between the language query and all region proposals. This is rather inefficient because there mig","authors_text":"Chaorui Deng, Guanghui Xu, Kui Jia, Mingkui Tan, Qi Wu, Yanwu Xu, ZhuLiang Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-12T02:04:49Z","title":"You Only Look & Listen Once: Towards Fast and Accurate Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04213","kind":"arxiv","version":3},"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":"sha256:5f82c59062f696e45e94f295416789600e7492eded892d893ce2c49e75b585b1","target":"record","created_at":"2026-05-17T23:51:04Z","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":"1c346c1354d754083e09d8261744a74ef4f195a607696895cba2b92f4ca88401","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-12T02:04:49Z","title_canon_sha256":"c38fea95355563d101db03e92c0c189d4f4382bcf8e2096ed190fade27b35c02"},"schema_version":"1.0","source":{"id":"1902.04213","kind":"arxiv","version":3}},"canonical_sha256":"6fa0c58d15cf3079b6709b219ae61d277c2bcdc86c735cad1473fce4191fed97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fa0c58d15cf3079b6709b219ae61d277c2bcdc86c735cad1473fce4191fed97","first_computed_at":"2026-05-17T23:51:04.978676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:04.978676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FSXJ56zz1PcL5enD/eHeWeKuLATJIwRcR3TKsAeivF7HqHibeCao0HQZ9ZLTNqOO1FLiObPyAv0Scen3mxJtDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:04.979189Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.04213","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f82c59062f696e45e94f295416789600e7492eded892d893ce2c49e75b585b1","sha256:33415ae736f45c4b8efa1bbfb3c1cb47d4f735fdb09cf24ae9182cdf79f5ce22"],"state_sha256":"b9fa3f0d252e3dfa881d7d191639e9b1135738f344eb2e5d12a232fca8cf47e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cGkADsvtNa/s8gjgw02o2YCbsmtEbh6ANsRsm5MXMJg7zbgSbH3ziEMdHx/zXnLNBcIZw8mS/867z+ZwlmqTDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T18:29:21.935463Z","bundle_sha256":"18c0dc27adcc9af41b1e80bf446b0730f1860b44ff9e21025c0b79fe014c37ef"}}