{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZLCSEVNPM7G753H4M7654JUUBS","short_pith_number":"pith:ZLCSEVNP","schema_version":"1.0","canonical_sha256":"cac52255af67cdfeecfc67fdde26940c9afa86ae951fb8d0137e3ecba34ab68e","source":{"kind":"arxiv","id":"2407.04998","version":1},"attestation_state":"computed","paper":{"title":"The Solution for the 5th GCAIAC Zero-shot Referring Expression Comprehension Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Feng Yu, Longfei Huang, Yang Yang, Zhihao Guan, Zhonghua Wan","submitted_at":"2024-07-06T08:31:33Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.04998","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-06T08:31:33Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"270dd6940a40bdd8f8f3f789a0ed027959b705000c9c71bc540119fa0e74dea2","abstract_canon_sha256":"d5522bb8e305c3c58926cf0ed28d6d94495c211212c02ec23b54fde881875f38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:06.433956Z","signature_b64":"jJvIu9g1QObxiAFMQTD32gmOyK9diE8AZolZLY8Abd7aDNhhDBGmo+xSD+lJgASMxySgvn+lk+1oezRGjxhKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cac52255af67cdfeecfc67fdde26940c9afa86ae951fb8d0137e3ecba34ab68e","last_reissued_at":"2026-07-05T08:41:06.433345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:06.433345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Solution for the 5th GCAIAC Zero-shot Referring Expression Comprehension Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Feng Yu, Longfei Huang, Yang Yang, Zhihao Guan, Zhonghua Wan","submitted_at":"2024-07-06T08:31:33Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04998","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/2407.04998/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.04998","created_at":"2026-07-05T08:41:06.433415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.04998v1","created_at":"2026-07-05T08:41:06.433415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04998","created_at":"2026-07-05T08:41:06.433415+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZLCSEVNPM7G7","created_at":"2026-07-05T08:41:06.433415+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZLCSEVNPM7G753H4","created_at":"2026-07-05T08:41:06.433415+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZLCSEVNP","created_at":"2026-07-05T08:41:06.433415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZLCSEVNPM7G753H4M7654JUUBS","json":"https://pith.science/pith/ZLCSEVNPM7G753H4M7654JUUBS.json","graph_json":"https://pith.science/api/pith-number/ZLCSEVNPM7G753H4M7654JUUBS/graph.json","events_json":"https://pith.science/api/pith-number/ZLCSEVNPM7G753H4M7654JUUBS/events.json","paper":"https://pith.science/paper/ZLCSEVNP"},"agent_actions":{"view_html":"https://pith.science/pith/ZLCSEVNPM7G753H4M7654JUUBS","download_json":"https://pith.science/pith/ZLCSEVNPM7G753H4M7654JUUBS.json","view_paper":"https://pith.science/paper/ZLCSEVNP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.04998&json=true","fetch_graph":"https://pith.science/api/pith-number/ZLCSEVNPM7G753H4M7654JUUBS/graph.json","fetch_events":"https://pith.science/api/pith-number/ZLCSEVNPM7G753H4M7654JUUBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZLCSEVNPM7G753H4M7654JUUBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZLCSEVNPM7G753H4M7654JUUBS/action/storage_attestation","attest_author":"https://pith.science/pith/ZLCSEVNPM7G753H4M7654JUUBS/action/author_attestation","sign_citation":"https://pith.science/pith/ZLCSEVNPM7G753H4M7654JUUBS/action/citation_signature","submit_replication":"https://pith.science/pith/ZLCSEVNPM7G753H4M7654JUUBS/action/replication_record"}},"created_at":"2026-07-05T08:41:06.433415+00:00","updated_at":"2026-07-05T08:41:06.433415+00:00"}