{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BZAJDH2GCB6FLCULNRY7QRWEEG","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":"972384e77f9ca585bb693e1430b4e196aa166e1ff77b3fcd5cccbc643e751341","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T01:41:05Z","title_canon_sha256":"6a237ff5526304ca3bcaf47dd72006b0cd11c409694e4be2de0a0e995df6ad55"},"schema_version":"1.0","source":{"id":"2408.04810","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04810","created_at":"2026-07-05T08:53:44Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04810v1","created_at":"2026-07-05T08:53:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04810","created_at":"2026-07-05T08:53:44Z"},{"alias_kind":"pith_short_12","alias_value":"BZAJDH2GCB6F","created_at":"2026-07-05T08:53:44Z"},{"alias_kind":"pith_short_16","alias_value":"BZAJDH2GCB6FLCUL","created_at":"2026-07-05T08:53:44Z"},{"alias_kind":"pith_short_8","alias_value":"BZAJDH2G","created_at":"2026-07-05T08:53:44Z"}],"graph_snapshots":[{"event_id":"sha256:2070c5409a2295906b28a01c6e7bd719c8f2839483c8770bc0e93e3019f87022","target":"graph","created_at":"2026-07-05T08:53:44Z","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/2408.04810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Significant research efforts have been made to scale and improve vision-language model (VLM) training approaches. Yet, with an ever-growing number of benchmarks, researchers are tasked with the heavy burden of implementing each protocol, bearing a non-trivial computational cost, and making sense of how all these benchmarks translate into meaningful axes of progress. To facilitate a systematic evaluation of VLM progress, we introduce UniBench: a unified implementation of 50+ VLM benchmarks spanning a comprehensive range of carefully categorized capabilities from object recognition to spatial aw","authors_text":"Caner Hazirbas, Diane Bouchacourt, Haider Al-Tahan, Mark Ibrahim, Quentin Garrido, Randall Balestriero","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T01:41:05Z","title":"UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04810","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:b58f2a65eaa85cb0bde7eee56d072fe832938a8c4dc0ef199eee73c13c4fdc04","target":"record","created_at":"2026-07-05T08:53:44Z","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":"972384e77f9ca585bb693e1430b4e196aa166e1ff77b3fcd5cccbc643e751341","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T01:41:05Z","title_canon_sha256":"6a237ff5526304ca3bcaf47dd72006b0cd11c409694e4be2de0a0e995df6ad55"},"schema_version":"1.0","source":{"id":"2408.04810","kind":"arxiv","version":1}},"canonical_sha256":"0e40919f46107c558a8b6c71f846c421b7ea4e2fae57142c568475a0ecab66ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e40919f46107c558a8b6c71f846c421b7ea4e2fae57142c568475a0ecab66ee","first_computed_at":"2026-07-05T08:53:44.397224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:44.397224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hJrSzC+r9pEbn0jAYdAZBZFVa2Yrc+HYwu9M1/IBJF/+JpjG92Ci5KgkaCBxUECzSWg/l8IzvqTr3SgvN99/Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:44.397712Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.04810","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b58f2a65eaa85cb0bde7eee56d072fe832938a8c4dc0ef199eee73c13c4fdc04","sha256:2070c5409a2295906b28a01c6e7bd719c8f2839483c8770bc0e93e3019f87022"],"state_sha256":"20ccbc4c2cf3a1331ef63ff0833d04a80aec0f826ba0ce2c92da4881d73607b7"}