{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F466FGMCIDFW7IUCFQP3NE7PYF","short_pith_number":"pith:F466FGMC","canonical_record":{"source":{"id":"2409.15125","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-23T15:31:25Z","cross_cats_sorted":[],"title_canon_sha256":"42489ff03f0f90bb5d5577c4cdd8d3782a16cf106f86210a2f19f9bf8b03d88a","abstract_canon_sha256":"2580a2706115467cecdf32fb90500da692bbbdc6530170691134027873590a04"},"schema_version":"1.0"},"canonical_sha256":"2f3de2998240cb6fa2822c1fb693efc147f05c4c52edfe994885abb1d52e3dd3","source":{"kind":"arxiv","id":"2409.15125","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15125","created_at":"2026-07-05T09:10:36Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15125v1","created_at":"2026-07-05T09:10:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15125","created_at":"2026-07-05T09:10:36Z"},{"alias_kind":"pith_short_12","alias_value":"F466FGMCIDFW","created_at":"2026-07-05T09:10:36Z"},{"alias_kind":"pith_short_16","alias_value":"F466FGMCIDFW7IUC","created_at":"2026-07-05T09:10:36Z"},{"alias_kind":"pith_short_8","alias_value":"F466FGMC","created_at":"2026-07-05T09:10:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F466FGMCIDFW7IUCFQP3NE7PYF","target":"record","payload":{"canonical_record":{"source":{"id":"2409.15125","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-23T15:31:25Z","cross_cats_sorted":[],"title_canon_sha256":"42489ff03f0f90bb5d5577c4cdd8d3782a16cf106f86210a2f19f9bf8b03d88a","abstract_canon_sha256":"2580a2706115467cecdf32fb90500da692bbbdc6530170691134027873590a04"},"schema_version":"1.0"},"canonical_sha256":"2f3de2998240cb6fa2822c1fb693efc147f05c4c52edfe994885abb1d52e3dd3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:36.568269Z","signature_b64":"4kEFju3bESs9tNiwVrYM8oo45qNtUOp82LKTjo3hLLJVayv6TBVl+Kvrjk/JVPfj3P1yk+yqb+E7vvzHwxVwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f3de2998240cb6fa2822c1fb693efc147f05c4c52edfe994885abb1d52e3dd3","last_reissued_at":"2026-07-05T09:10:36.567859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:36.567859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.15125","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":"2026-07-05T09:10:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7WgjJjhhYhEIoIm1DJGjManQI6ACgpgg8jLKrAUNjXES41Lx+F8t0n8uVCTA9ZBT9pS25KcUxWTeFgC2Ly0YCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:00:11.026774Z"},"content_sha256":"893b8f1cfdfb9c293c2751af58ac349ed555bab9efe8e0e7329011b0fd0e6f71","schema_version":"1.0","event_id":"sha256:893b8f1cfdfb9c293c2751af58ac349ed555bab9efe8e0e7329011b0fd0e6f71"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F466FGMCIDFW7IUCFQP3NE7PYF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Detect, Describe, Discriminate: Moving Beyond VQA for MLLM Evaluation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Darshan Singh S, Makarand Tapaswi, Manu Gaur","submitted_at":"2024-09-23T15:31:25Z","abstract_excerpt":"Visual Question Answering (VQA) with multiple choice questions enables a vision-centric evaluation of Multimodal Large Language Models (MLLMs). Although it reliably checks the existence of specific visual abilities, it is easier for the model to select an answer from multiple choices (VQA evaluation) than to generate the answer itself. In this work, we offer a novel perspective: we evaluate how well an MLLM understands a specific visual concept by its ability to uniquely describe two extremely similar images that differ only in the targeted visual concept. Specifically, we assess the ability o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15125","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/2409.15125/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":"2026-07-05T09:10:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eU1T9di8h0AEidfnquW589GhNaws0klijCPI1eKCieLvJuBSePFC6uK2VQ7+QKfWhZRfRU2IyZx26a1cOLSBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:00:11.027522Z"},"content_sha256":"dc24082e83adc36fb997e46c31da6af5ee5dc53a5d9c34ac2950bb2dd5351aa4","schema_version":"1.0","event_id":"sha256:dc24082e83adc36fb997e46c31da6af5ee5dc53a5d9c34ac2950bb2dd5351aa4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F466FGMCIDFW7IUCFQP3NE7PYF/bundle.json","state_url":"https://pith.science/pith/F466FGMCIDFW7IUCFQP3NE7PYF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F466FGMCIDFW7IUCFQP3NE7PYF/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":"2026-08-06T21:00:11Z","links":{"resolver":"https://pith.science/pith/F466FGMCIDFW7IUCFQP3NE7PYF","bundle":"https://pith.science/pith/F466FGMCIDFW7IUCFQP3NE7PYF/bundle.json","state":"https://pith.science/pith/F466FGMCIDFW7IUCFQP3NE7PYF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F466FGMCIDFW7IUCFQP3NE7PYF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F466FGMCIDFW7IUCFQP3NE7PYF","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":"2580a2706115467cecdf32fb90500da692bbbdc6530170691134027873590a04","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-23T15:31:25Z","title_canon_sha256":"42489ff03f0f90bb5d5577c4cdd8d3782a16cf106f86210a2f19f9bf8b03d88a"},"schema_version":"1.0","source":{"id":"2409.15125","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15125","created_at":"2026-07-05T09:10:36Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15125v1","created_at":"2026-07-05T09:10:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15125","created_at":"2026-07-05T09:10:36Z"},{"alias_kind":"pith_short_12","alias_value":"F466FGMCIDFW","created_at":"2026-07-05T09:10:36Z"},{"alias_kind":"pith_short_16","alias_value":"F466FGMCIDFW7IUC","created_at":"2026-07-05T09:10:36Z"},{"alias_kind":"pith_short_8","alias_value":"F466FGMC","created_at":"2026-07-05T09:10:36Z"}],"graph_snapshots":[{"event_id":"sha256:dc24082e83adc36fb997e46c31da6af5ee5dc53a5d9c34ac2950bb2dd5351aa4","target":"graph","created_at":"2026-07-05T09:10:36Z","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/2409.15125/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Question Answering (VQA) with multiple choice questions enables a vision-centric evaluation of Multimodal Large Language Models (MLLMs). Although it reliably checks the existence of specific visual abilities, it is easier for the model to select an answer from multiple choices (VQA evaluation) than to generate the answer itself. In this work, we offer a novel perspective: we evaluate how well an MLLM understands a specific visual concept by its ability to uniquely describe two extremely similar images that differ only in the targeted visual concept. Specifically, we assess the ability o","authors_text":"Darshan Singh S, Makarand Tapaswi, Manu Gaur","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-23T15:31:25Z","title":"Detect, Describe, Discriminate: Moving Beyond VQA for MLLM Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15125","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":"sha256:893b8f1cfdfb9c293c2751af58ac349ed555bab9efe8e0e7329011b0fd0e6f71","target":"record","created_at":"2026-07-05T09:10:36Z","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":"2580a2706115467cecdf32fb90500da692bbbdc6530170691134027873590a04","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-23T15:31:25Z","title_canon_sha256":"42489ff03f0f90bb5d5577c4cdd8d3782a16cf106f86210a2f19f9bf8b03d88a"},"schema_version":"1.0","source":{"id":"2409.15125","kind":"arxiv","version":1}},"canonical_sha256":"2f3de2998240cb6fa2822c1fb693efc147f05c4c52edfe994885abb1d52e3dd3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f3de2998240cb6fa2822c1fb693efc147f05c4c52edfe994885abb1d52e3dd3","first_computed_at":"2026-07-05T09:10:36.567859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:36.567859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4kEFju3bESs9tNiwVrYM8oo45qNtUOp82LKTjo3hLLJVayv6TBVl+Kvrjk/JVPfj3P1yk+yqb+E7vvzHwxVwDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:36.568269Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.15125","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:893b8f1cfdfb9c293c2751af58ac349ed555bab9efe8e0e7329011b0fd0e6f71","sha256:dc24082e83adc36fb997e46c31da6af5ee5dc53a5d9c34ac2950bb2dd5351aa4"],"state_sha256":"788b874c7c696abcc85f00a98966fc94d75d22b8bab71d19732c3e662b194723"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tqItg7C0m7qW7BBN8EboCfB/M9Uof2tYPV4SiTeI9H+y5QE51Waojlc9CttJBjPoW/Ztj5wCZ+7Zf3DSyE5RCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:00:11.033222Z","bundle_sha256":"4bc7aac7f3c578e52575c10388435731ca7432f9ff70400e40bed5d59955fba2"}}