{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:J2R5XORAOZJ2R2M3DL5GMSYOTC","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":"a97b3fe536b15f5632f89bb4d818384a8adfdde132120097c45320d4a56e0176","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-12T13:05:25Z","title_canon_sha256":"0cab2173c0a9b26d7467682ab640d9fdd8dc832df20f5155e98808744d45ce84"},"schema_version":"1.0","source":{"id":"2105.05636","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.05636","created_at":"2026-07-05T05:30:54Z"},{"alias_kind":"arxiv_version","alias_value":"2105.05636v3","created_at":"2026-07-05T05:30:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05636","created_at":"2026-07-05T05:30:54Z"},{"alias_kind":"pith_short_12","alias_value":"J2R5XORAOZJ2","created_at":"2026-07-05T05:30:54Z"},{"alias_kind":"pith_short_16","alias_value":"J2R5XORAOZJ2R2M3","created_at":"2026-07-05T05:30:54Z"},{"alias_kind":"pith_short_8","alias_value":"J2R5XORA","created_at":"2026-07-05T05:30:54Z"}],"graph_snapshots":[{"event_id":"sha256:61d26be7348bd4c6e9700cd957bf84d86c3e04d655f12ad258de5f02ff6eecf5","target":"graph","created_at":"2026-07-05T05:30:54Z","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/2105.05636/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The prevailing framework for matching multimodal inputs is based on a two-stage process: 1) detecting proposals with an object detector and 2) matching text queries with proposals. Existing two-stage solutions mostly focus on the matching step. In this paper, we argue that these methods overlook an obvious \\emph{mismatch} between the roles of proposals in the two stages: they generate proposals solely based on the detection confidence (i.e., query-agnostic), hoping that the proposals contain all instances mentioned in the text query (i.e., query-aware). Due to this mismatch, chances are that p","authors_text":"Chenchi Zhang, Hanwang Zhang, Jian Shao, Jun Xiao, Long Chen, Wenbo Ma, Yueting Zhuang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-12T13:05:25Z","title":"VL-NMS: Breaking Proposal Bottlenecks in Two-Stage Visual-Language Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05636","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":"sha256:7eb311e6f9bfd665c8b791d1ff375baa54141c275aaa8b652de810cac72cfe9f","target":"record","created_at":"2026-07-05T05:30:54Z","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":"a97b3fe536b15f5632f89bb4d818384a8adfdde132120097c45320d4a56e0176","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-12T13:05:25Z","title_canon_sha256":"0cab2173c0a9b26d7467682ab640d9fdd8dc832df20f5155e98808744d45ce84"},"schema_version":"1.0","source":{"id":"2105.05636","kind":"arxiv","version":3}},"canonical_sha256":"4ea3dbba207653a8e99b1afa664b0e989c877f8f82a26baee03dbb7528ed8f59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ea3dbba207653a8e99b1afa664b0e989c877f8f82a26baee03dbb7528ed8f59","first_computed_at":"2026-07-05T05:30:54.499432Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:30:54.499432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"40otZj/7y6yvD826j+o5Qn46zdmjN6HRnOJBB7j1T4OvjAjI1vxMXF3Z1LClwfWhE8bNBIfzv1viK2BIWp/HDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:30:54.499844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.05636","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7eb311e6f9bfd665c8b791d1ff375baa54141c275aaa8b652de810cac72cfe9f","sha256:61d26be7348bd4c6e9700cd957bf84d86c3e04d655f12ad258de5f02ff6eecf5"],"state_sha256":"2a60a0cfb042f236c1921f4084a50a1b2df4655ba52aade72ccf6c9594798def"}