{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZLCSEVNPM7G753H4M7654JUUBS","short_pith_number":"pith:ZLCSEVNP","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"},"canonical_sha256":"cac52255af67cdfeecfc67fdde26940c9afa86ae951fb8d0137e3ecba34ab68e","source":{"kind":"arxiv","id":"2407.04998","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZLCSEVNPM7G753H4M7654JUUBS","target":"record","payload":{"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"},"canonical_sha256":"cac52255af67cdfeecfc67fdde26940c9afa86ae951fb8d0137e3ecba34ab68e","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"},"source_kind":"arxiv","source_id":"2407.04998","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:41:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fDBl8haTm5Es74DlFr9E58gRx89EJXtZT0Yht33rC1Fd24bRYUdGe+KduvpmHK7Wq9Y/popMm+E/qmuWomb0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:51:17.257775Z"},"content_sha256":"73582e12dabbea8c1fd83245d90e671e796168fc5e2da643a8c229f25d76d051","schema_version":"1.0","event_id":"sha256:73582e12dabbea8c1fd83245d90e671e796168fc5e2da643a8c229f25d76d051"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZLCSEVNPM7G753H4M7654JUUBS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:41:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yU/k+cBCYPHlBnZbd+OWDv5qG8RAH7ruDjH+Y2Gx+gDVYvynyqFyDnpJ+fdrdsOFQ6PqRi9y3HFVBe4bkA3tCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:51:17.258769Z"},"content_sha256":"445adf6830dc9796dd333eaf674a7834d6d73f8b9cedc1ef8d6d81e0f2ba5f49","schema_version":"1.0","event_id":"sha256:445adf6830dc9796dd333eaf674a7834d6d73f8b9cedc1ef8d6d81e0f2ba5f49"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLCSEVNPM7G753H4M7654JUUBS/bundle.json","state_url":"https://pith.science/pith/ZLCSEVNPM7G753H4M7654JUUBS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLCSEVNPM7G753H4M7654JUUBS/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":"2026-08-17T20:51:17Z","links":{"resolver":"https://pith.science/pith/ZLCSEVNPM7G753H4M7654JUUBS","bundle":"https://pith.science/pith/ZLCSEVNPM7G753H4M7654JUUBS/bundle.json","state":"https://pith.science/pith/ZLCSEVNPM7G753H4M7654JUUBS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLCSEVNPM7G753H4M7654JUUBS/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eG8+hpcgl3f+asfsSzLI8rP5+dMQuO9C2t7pjaUZ0WY9n6NP+b1NqvBPXsDYvUn8zImUwaT89t5jDC1A6PqOCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:51:17.301762Z","bundle_sha256":"304d7d6559367067d91af27cfa27e5b4226c1dcab9ef331624fa99d80439bb27"}}