{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ESM274CNO66H44L72GDPY2QGJO","short_pith_number":"pith:ESM274CN","schema_version":"1.0","canonical_sha256":"2499aff04d77bc7e717fd186fc6a064bbbfcd9fcf1b917ed977794cb1088dc2a","source":{"kind":"arxiv","id":"2606.26602","version":1},"attestation_state":"computed","paper":{"title":"DiCoBench: Benchmarking Multi-Image Fine-Grained Perception via Differential and Commonality Visual Cues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Geng Li, Yuxin Peng","submitted_at":"2026-06-25T05:02:38Z","abstract_excerpt":"Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive fine-grained perception capabilities. However, existing benchmarks predominantly rely on explicit textual cues or low-resolution inputs, failing to evaluate a model's ability to autonomously perceive implicit visual cues in high-resolution. To bridge this gap, we introduce DiCoBench, a comprehensive, multi-image high-resolution benchmark designed for cross-image fine-grained perception. DiCoBench consists of 765 meticulously curated samples categorized into two progressive tracks: Differential Visual C"},"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":"2606.26602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T05:02:38Z","cross_cats_sorted":[],"title_canon_sha256":"d4b37a2316b639a4edfe942e2be9f2a2f74685412cb005f4bfb3eafe217a75db","abstract_canon_sha256":"06d16342d1cbca3009874305863295a31d6e6c5e7474df210c50cbfe93b0ad01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:35.966031Z","signature_b64":"olcqT2PxcBMiquWM23h3Su6jrhR8e825bptH0gkWRGWc6wdGmUvQbs3TQha14EwFnjuU4EYqbKMfD5rpsNDLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2499aff04d77bc7e717fd186fc6a064bbbfcd9fcf1b917ed977794cb1088dc2a","last_reissued_at":"2026-06-26T01:15:35.965577Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:35.965577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiCoBench: Benchmarking Multi-Image Fine-Grained Perception via Differential and Commonality Visual Cues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Geng Li, Yuxin Peng","submitted_at":"2026-06-25T05:02:38Z","abstract_excerpt":"Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive fine-grained perception capabilities. However, existing benchmarks predominantly rely on explicit textual cues or low-resolution inputs, failing to evaluate a model's ability to autonomously perceive implicit visual cues in high-resolution. To bridge this gap, we introduce DiCoBench, a comprehensive, multi-image high-resolution benchmark designed for cross-image fine-grained perception. DiCoBench consists of 765 meticulously curated samples categorized into two progressive tracks: Differential Visual C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26602","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/2606.26602/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":"2606.26602","created_at":"2026-06-26T01:15:35.965649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26602v1","created_at":"2026-06-26T01:15:35.965649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26602","created_at":"2026-06-26T01:15:35.965649+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESM274CNO66H","created_at":"2026-06-26T01:15:35.965649+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESM274CNO66H44L7","created_at":"2026-06-26T01:15:35.965649+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESM274CN","created_at":"2026-06-26T01:15:35.965649+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/ESM274CNO66H44L72GDPY2QGJO","json":"https://pith.science/pith/ESM274CNO66H44L72GDPY2QGJO.json","graph_json":"https://pith.science/api/pith-number/ESM274CNO66H44L72GDPY2QGJO/graph.json","events_json":"https://pith.science/api/pith-number/ESM274CNO66H44L72GDPY2QGJO/events.json","paper":"https://pith.science/paper/ESM274CN"},"agent_actions":{"view_html":"https://pith.science/pith/ESM274CNO66H44L72GDPY2QGJO","download_json":"https://pith.science/pith/ESM274CNO66H44L72GDPY2QGJO.json","view_paper":"https://pith.science/paper/ESM274CN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26602&json=true","fetch_graph":"https://pith.science/api/pith-number/ESM274CNO66H44L72GDPY2QGJO/graph.json","fetch_events":"https://pith.science/api/pith-number/ESM274CNO66H44L72GDPY2QGJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESM274CNO66H44L72GDPY2QGJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESM274CNO66H44L72GDPY2QGJO/action/storage_attestation","attest_author":"https://pith.science/pith/ESM274CNO66H44L72GDPY2QGJO/action/author_attestation","sign_citation":"https://pith.science/pith/ESM274CNO66H44L72GDPY2QGJO/action/citation_signature","submit_replication":"https://pith.science/pith/ESM274CNO66H44L72GDPY2QGJO/action/replication_record"}},"created_at":"2026-06-26T01:15:35.965649+00:00","updated_at":"2026-06-26T01:15:35.965649+00:00"}