{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZLCSEVNPM7G753H4M7654JUUBS","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":"d5522bb8e305c3c58926cf0ed28d6d94495c211212c02ec23b54fde881875f38","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-06T08:31:33Z","title_canon_sha256":"270dd6940a40bdd8f8f3f789a0ed027959b705000c9c71bc540119fa0e74dea2"},"schema_version":"1.0","source":{"id":"2407.04998","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04998","created_at":"2026-07-05T08:41:06Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04998v1","created_at":"2026-07-05T08:41:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04998","created_at":"2026-07-05T08:41:06Z"},{"alias_kind":"pith_short_12","alias_value":"ZLCSEVNPM7G7","created_at":"2026-07-05T08:41:06Z"},{"alias_kind":"pith_short_16","alias_value":"ZLCSEVNPM7G753H4","created_at":"2026-07-05T08:41:06Z"},{"alias_kind":"pith_short_8","alias_value":"ZLCSEVNP","created_at":"2026-07-05T08:41:06Z"}],"graph_snapshots":[{"event_id":"sha256:445adf6830dc9796dd333eaf674a7834d6d73f8b9cedc1ef8d6d81e0f2ba5f49","target":"graph","created_at":"2026-07-05T08:41:06Z","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/2407.04998/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This report presents a solution for the zero-shot referring expression comprehension task. Visual-language multimodal base models (such as CLIP, SAM) have gained significant attention in recent years as a cornerstone of mainstream research. One of the key applications of multimodal base models lies in their ability to generalize to zero-shot downstream tasks. Unlike traditional referring expression comprehension, zero-shot referring expression comprehension aims to apply pre-trained visual-language models directly to the task without specific training. Recent studies have enhanced the zero-sho","authors_text":"Feng Yu, Longfei Huang, Yang Yang, Zhihao Guan, Zhonghua Wan","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-06T08:31:33Z","title":"The Solution for the 5th GCAIAC Zero-shot Referring Expression Comprehension Challenge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04998","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":"sha256:73582e12dabbea8c1fd83245d90e671e796168fc5e2da643a8c229f25d76d051","target":"record","created_at":"2026-07-05T08:41:06Z","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":"d5522bb8e305c3c58926cf0ed28d6d94495c211212c02ec23b54fde881875f38","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-06T08:31:33Z","title_canon_sha256":"270dd6940a40bdd8f8f3f789a0ed027959b705000c9c71bc540119fa0e74dea2"},"schema_version":"1.0","source":{"id":"2407.04998","kind":"arxiv","version":1}},"canonical_sha256":"cac52255af67cdfeecfc67fdde26940c9afa86ae951fb8d0137e3ecba34ab68e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cac52255af67cdfeecfc67fdde26940c9afa86ae951fb8d0137e3ecba34ab68e","first_computed_at":"2026-07-05T08:41:06.433345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:41:06.433345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jJvIu9g1QObxiAFMQTD32gmOyK9diE8AZolZLY8Abd7aDNhhDBGmo+xSD+lJgASMxySgvn+lk+1oezRGjxhKCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:41:06.433956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04998","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73582e12dabbea8c1fd83245d90e671e796168fc5e2da643a8c229f25d76d051","sha256:445adf6830dc9796dd333eaf674a7834d6d73f8b9cedc1ef8d6d81e0f2ba5f49"],"state_sha256":"0794d477f61accd62b99aa3eba0480acf5074319ab0e68b8d7374d438b4b718a"}