{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ESM274CNO66H44L72GDPY2QGJO","short_pith_number":"pith:ESM274CN","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"},"canonical_sha256":"2499aff04d77bc7e717fd186fc6a064bbbfcd9fcf1b917ed977794cb1088dc2a","source":{"kind":"arxiv","id":"2606.26602","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26602","created_at":"2026-06-26T01:15:35Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26602v1","created_at":"2026-06-26T01:15:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26602","created_at":"2026-06-26T01:15:35Z"},{"alias_kind":"pith_short_12","alias_value":"ESM274CNO66H","created_at":"2026-06-26T01:15:35Z"},{"alias_kind":"pith_short_16","alias_value":"ESM274CNO66H44L7","created_at":"2026-06-26T01:15:35Z"},{"alias_kind":"pith_short_8","alias_value":"ESM274CN","created_at":"2026-06-26T01:15:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ESM274CNO66H44L72GDPY2QGJO","target":"record","payload":{"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"},"canonical_sha256":"2499aff04d77bc7e717fd186fc6a064bbbfcd9fcf1b917ed977794cb1088dc2a","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"},"source_kind":"arxiv","source_id":"2606.26602","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":"2026-06-26T01:15:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1xecOW/om4latLRWPivmVTc5mFyJok5GsP43/grwRpjEEnwlJyYc9AB2/ejH/kKXPR5iaWofcW9BxoBbbtRPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T13:23:30.439273Z"},"content_sha256":"245a4682f3bc1339042a666cdae49d9d8c64b87631c77d35e86898fe8fca48fd","schema_version":"1.0","event_id":"sha256:245a4682f3bc1339042a666cdae49d9d8c64b87631c77d35e86898fe8fca48fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ESM274CNO66H44L72GDPY2QGJO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-26T01:15:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U1YhupKBD21YGn6Pj7MFhXrfVA9voeivMtsQbtKbnbiyXJ8cyEwvxOTKlVhfMWZwzLG3giCGTOrgLA3X5ucDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T13:23:30.439661Z"},"content_sha256":"3badbdfb6bef2c3332cbd8e0594e959baf9ff25a15f37b1aa36b41c6cfca1b03","schema_version":"1.0","event_id":"sha256:3badbdfb6bef2c3332cbd8e0594e959baf9ff25a15f37b1aa36b41c6cfca1b03"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ESM274CNO66H44L72GDPY2QGJO/bundle.json","state_url":"https://pith.science/pith/ESM274CNO66H44L72GDPY2QGJO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ESM274CNO66H44L72GDPY2QGJO/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":"2026-07-02T13:23:30Z","links":{"resolver":"https://pith.science/pith/ESM274CNO66H44L72GDPY2QGJO","bundle":"https://pith.science/pith/ESM274CNO66H44L72GDPY2QGJO/bundle.json","state":"https://pith.science/pith/ESM274CNO66H44L72GDPY2QGJO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ESM274CNO66H44L72GDPY2QGJO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ESM274CNO66H44L72GDPY2QGJO","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":"06d16342d1cbca3009874305863295a31d6e6c5e7474df210c50cbfe93b0ad01","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T05:02:38Z","title_canon_sha256":"d4b37a2316b639a4edfe942e2be9f2a2f74685412cb005f4bfb3eafe217a75db"},"schema_version":"1.0","source":{"id":"2606.26602","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26602","created_at":"2026-06-26T01:15:35Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26602v1","created_at":"2026-06-26T01:15:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26602","created_at":"2026-06-26T01:15:35Z"},{"alias_kind":"pith_short_12","alias_value":"ESM274CNO66H","created_at":"2026-06-26T01:15:35Z"},{"alias_kind":"pith_short_16","alias_value":"ESM274CNO66H44L7","created_at":"2026-06-26T01:15:35Z"},{"alias_kind":"pith_short_8","alias_value":"ESM274CN","created_at":"2026-06-26T01:15:35Z"}],"graph_snapshots":[{"event_id":"sha256:3badbdfb6bef2c3332cbd8e0594e959baf9ff25a15f37b1aa36b41c6cfca1b03","target":"graph","created_at":"2026-06-26T01:15:35Z","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/2606.26602/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Geng Li, Yuxin Peng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T05:02:38Z","title":"DiCoBench: Benchmarking Multi-Image Fine-Grained Perception via Differential and Commonality Visual Cues"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26602","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":"sha256:245a4682f3bc1339042a666cdae49d9d8c64b87631c77d35e86898fe8fca48fd","target":"record","created_at":"2026-06-26T01:15:35Z","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":"06d16342d1cbca3009874305863295a31d6e6c5e7474df210c50cbfe93b0ad01","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T05:02:38Z","title_canon_sha256":"d4b37a2316b639a4edfe942e2be9f2a2f74685412cb005f4bfb3eafe217a75db"},"schema_version":"1.0","source":{"id":"2606.26602","kind":"arxiv","version":1}},"canonical_sha256":"2499aff04d77bc7e717fd186fc6a064bbbfcd9fcf1b917ed977794cb1088dc2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2499aff04d77bc7e717fd186fc6a064bbbfcd9fcf1b917ed977794cb1088dc2a","first_computed_at":"2026-06-26T01:15:35.965577Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:15:35.965577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"olcqT2PxcBMiquWM23h3Su6jrhR8e825bptH0gkWRGWc6wdGmUvQbs3TQha14EwFnjuU4EYqbKMfD5rpsNDLCg==","signature_status":"signed_v1","signed_at":"2026-06-26T01:15:35.966031Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.26602","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:245a4682f3bc1339042a666cdae49d9d8c64b87631c77d35e86898fe8fca48fd","sha256:3badbdfb6bef2c3332cbd8e0594e959baf9ff25a15f37b1aa36b41c6cfca1b03"],"state_sha256":"afe19a4e4e944a4fd9374eff220a0c15d74239ff1d604b303b601e8a4b9698de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GyQpnbPFk9V0giwpORgwt2cghHJEAM7DQhxEJSEeYjbyuyk+ozmdHYfd3ibgGug2a/WZy5Rx5ZsQahZifavLCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T13:23:30.441680Z","bundle_sha256":"50101f729d5f26483c9d00375c42e030cb54ead136c5663e1988eedf67e9e623"}}