{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VTN4TRS4BFDQTK5XMUIYKJVQLJ","short_pith_number":"pith:VTN4TRS4","canonical_record":{"source":{"id":"2512.06276","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-06T03:59:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b43b04c0fba5a83a7d7d001703f09126a0b4d7fc64cfa18ed8e047f090010f4","abstract_canon_sha256":"c669c9ca0418d0ccf2889e19d07c4f3ed18dcdf75816a23387314cede14e2b5d"},"schema_version":"1.0"},"canonical_sha256":"acdbc9c65c094709abb765118526b05a5b159adc6f88e9ff1e9ef021b06f054d","source":{"kind":"arxiv","id":"2512.06276","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.06276","created_at":"2026-07-29T01:24:26Z"},{"alias_kind":"arxiv_version","alias_value":"2512.06276v3","created_at":"2026-07-29T01:24:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.06276","created_at":"2026-07-29T01:24:26Z"},{"alias_kind":"pith_short_12","alias_value":"VTN4TRS4BFDQ","created_at":"2026-07-29T01:24:26Z"},{"alias_kind":"pith_short_16","alias_value":"VTN4TRS4BFDQTK5X","created_at":"2026-07-29T01:24:26Z"},{"alias_kind":"pith_short_8","alias_value":"VTN4TRS4","created_at":"2026-07-29T01:24:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VTN4TRS4BFDQTK5XMUIYKJVQLJ","target":"record","payload":{"canonical_record":{"source":{"id":"2512.06276","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-06T03:59:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b43b04c0fba5a83a7d7d001703f09126a0b4d7fc64cfa18ed8e047f090010f4","abstract_canon_sha256":"c669c9ca0418d0ccf2889e19d07c4f3ed18dcdf75816a23387314cede14e2b5d"},"schema_version":"1.0"},"canonical_sha256":"acdbc9c65c094709abb765118526b05a5b159adc6f88e9ff1e9ef021b06f054d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:24:26.738735Z","signature_b64":"1J6eILqCfMAewdYvvXOEHwcweMzE58NWPh4H6q3GmzM3opFCekgVwV9v0BJOrCqzeZPGF0yoCKGGam1EdXAHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acdbc9c65c094709abb765118526b05a5b159adc6f88e9ff1e9ef021b06f054d","last_reissued_at":"2026-07-29T01:24:26.737761Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:24:26.737761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.06276","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":"2026-07-29T01:24:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kXhxD0RJHV8jokVKeSYbkh5dhorb5S1bq/PQ3TWXckFfC9k1+iBhd3LZjU7OrV/YkOlKYpBBIJCNWjbD/tF0Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:25:44.255949Z"},"content_sha256":"b210325a0a2e74836945e5069482a74f8378e8cf346c96f9fce71539d1fc18a2","schema_version":"1.0","event_id":"sha256:b210325a0a2e74836945e5069482a74f8378e8cf346c96f9fce71539d1fc18a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VTN4TRS4BFDQTK5XMUIYKJVQLJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Han Fang, Hao Li, Hao Sun, Hongbo Sun, Jinglin Xu, Jingmin Xin, Tianyi Gao, Xiaodong Dong, Xin Wei, Ye Yuan, Zhongjiang He","submitted_at":"2025-12-06T03:59:21Z","abstract_excerpt":"Referring Expression Comprehension (REC) is a vision-language task that localizes a specific image region based on a textual description. Existing REC benchmarks primarily evaluate perceptual capabilities and lack interpretable scoring mechanisms, which cannot reveal the grounding capability of Multi-modal Large Language Model (MLLM) across different cognitive abilities. To address this limitation, we introduce RefBench-PRO, a comprehensive REC benchmark, which decomposes referring expressions into two core dimensions, i.e., perception and reasoning, and further subdivides them into six progre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.06276","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.06276/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":"2026-07-29T01:24:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L/IQiqx5eo9/BL8NuFzs6DWKaBnbt/u/RxjvhSVXnbIr5NuU5xdbhzlGMXbGtNg2hubD+vND3NauvU/4syD8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:25:44.256489Z"},"content_sha256":"ad6951802659fadca0c4f59f735c6be1576dd430c0db20277a12230b1d7c9812","schema_version":"1.0","event_id":"sha256:ad6951802659fadca0c4f59f735c6be1576dd430c0db20277a12230b1d7c9812"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VTN4TRS4BFDQTK5XMUIYKJVQLJ/bundle.json","state_url":"https://pith.science/pith/VTN4TRS4BFDQTK5XMUIYKJVQLJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VTN4TRS4BFDQTK5XMUIYKJVQLJ/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":"2026-08-04T03:25:44Z","links":{"resolver":"https://pith.science/pith/VTN4TRS4BFDQTK5XMUIYKJVQLJ","bundle":"https://pith.science/pith/VTN4TRS4BFDQTK5XMUIYKJVQLJ/bundle.json","state":"https://pith.science/pith/VTN4TRS4BFDQTK5XMUIYKJVQLJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VTN4TRS4BFDQTK5XMUIYKJVQLJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VTN4TRS4BFDQTK5XMUIYKJVQLJ","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":"c669c9ca0418d0ccf2889e19d07c4f3ed18dcdf75816a23387314cede14e2b5d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-06T03:59:21Z","title_canon_sha256":"7b43b04c0fba5a83a7d7d001703f09126a0b4d7fc64cfa18ed8e047f090010f4"},"schema_version":"1.0","source":{"id":"2512.06276","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.06276","created_at":"2026-07-29T01:24:26Z"},{"alias_kind":"arxiv_version","alias_value":"2512.06276v3","created_at":"2026-07-29T01:24:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.06276","created_at":"2026-07-29T01:24:26Z"},{"alias_kind":"pith_short_12","alias_value":"VTN4TRS4BFDQ","created_at":"2026-07-29T01:24:26Z"},{"alias_kind":"pith_short_16","alias_value":"VTN4TRS4BFDQTK5X","created_at":"2026-07-29T01:24:26Z"},{"alias_kind":"pith_short_8","alias_value":"VTN4TRS4","created_at":"2026-07-29T01:24:26Z"}],"graph_snapshots":[{"event_id":"sha256:ad6951802659fadca0c4f59f735c6be1576dd430c0db20277a12230b1d7c9812","target":"graph","created_at":"2026-07-29T01:24:26Z","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/2512.06276/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring Expression Comprehension (REC) is a vision-language task that localizes a specific image region based on a textual description. Existing REC benchmarks primarily evaluate perceptual capabilities and lack interpretable scoring mechanisms, which cannot reveal the grounding capability of Multi-modal Large Language Model (MLLM) across different cognitive abilities. To address this limitation, we introduce RefBench-PRO, a comprehensive REC benchmark, which decomposes referring expressions into two core dimensions, i.e., perception and reasoning, and further subdivides them into six progre","authors_text":"Han Fang, Hao Li, Hao Sun, Hongbo Sun, Jinglin Xu, Jingmin Xin, Tianyi Gao, Xiaodong Dong, Xin Wei, Ye Yuan, Zhongjiang He","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-06T03:59:21Z","title":"RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.06276","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:b210325a0a2e74836945e5069482a74f8378e8cf346c96f9fce71539d1fc18a2","target":"record","created_at":"2026-07-29T01:24:26Z","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":"c669c9ca0418d0ccf2889e19d07c4f3ed18dcdf75816a23387314cede14e2b5d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-06T03:59:21Z","title_canon_sha256":"7b43b04c0fba5a83a7d7d001703f09126a0b4d7fc64cfa18ed8e047f090010f4"},"schema_version":"1.0","source":{"id":"2512.06276","kind":"arxiv","version":3}},"canonical_sha256":"acdbc9c65c094709abb765118526b05a5b159adc6f88e9ff1e9ef021b06f054d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acdbc9c65c094709abb765118526b05a5b159adc6f88e9ff1e9ef021b06f054d","first_computed_at":"2026-07-29T01:24:26.737761Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T01:24:26.737761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1J6eILqCfMAewdYvvXOEHwcweMzE58NWPh4H6q3GmzM3opFCekgVwV9v0BJOrCqzeZPGF0yoCKGGam1EdXAHAw==","signature_status":"signed_v1","signed_at":"2026-07-29T01:24:26.738735Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.06276","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b210325a0a2e74836945e5069482a74f8378e8cf346c96f9fce71539d1fc18a2","sha256:ad6951802659fadca0c4f59f735c6be1576dd430c0db20277a12230b1d7c9812"],"state_sha256":"04c3928fe04847d762c19b7d3e15bd91c9817f4ac44d8b74f988d551e1b09fc3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8H8NH4vjiQT3qq/zy8PuFxcL1kSzfXWJeMla5JCFESVtpgqUdvKMODdHGOSyKdjwUL1Sfx/yfHwGp/6w5i75DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:25:44.261427Z","bundle_sha256":"58a8010ddfe8817df0e6e0b826722b1db4fd4037809faf9c0271e81a3fb09dbd"}}