{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JY4XZCERA4LAZSADWR2FT75NNC","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":"7699d4133ee8288ea9e2b7a706d5fb8523ec77f9874d88aa8109530678b7e090","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-09T08:30:28Z","title_canon_sha256":"49e06a2de5fb0df3a987a33dc07f16ee90dbe7fa29b90315b6ba8f5538cc5cc1"},"schema_version":"1.0","source":{"id":"2603.08090","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.08090","created_at":"2026-07-01T01:17:13Z"},{"alias_kind":"arxiv_version","alias_value":"2603.08090v3","created_at":"2026-07-01T01:17:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.08090","created_at":"2026-07-01T01:17:13Z"},{"alias_kind":"pith_short_12","alias_value":"JY4XZCERA4LA","created_at":"2026-07-01T01:17:13Z"},{"alias_kind":"pith_short_16","alias_value":"JY4XZCERA4LAZSAD","created_at":"2026-07-01T01:17:13Z"},{"alias_kind":"pith_short_8","alias_value":"JY4XZCER","created_at":"2026-07-01T01:17:13Z"}],"graph_snapshots":[{"event_id":"sha256:7f2cbb9080d9b757510055b08e91f311197905972827ace62b81c2e0dcb3c230","target":"graph","created_at":"2026-07-01T01:17:13Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"DSH-Bench enables systematic multi-perspective analysis of subject-driven T2I models through four principal innovations: hierarchical taxonomy sampling, difficulty and scenario classification, the SICS metric with 9.4% higher human correlation, and diagnostic insights for model optimization."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the chosen hierarchical taxonomy and difficulty/scenario labels are sufficiently comprehensive and unbiased, and that the reported 9.4% correlation improvement for SICS generalizes beyond the specific human evaluators and model set used in the study."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DSH-Bench is a benchmark for subject-driven T2I generation that uses hierarchical taxonomy sampling, difficulty/scenario classification, and a new SICS metric showing 9.4% higher human correlation than prior measures."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"DSH-Bench supplies a hierarchical taxonomy and difficulty-scenario labels to expose where subject-driven text-to-image models lose identity."}],"snapshot_sha256":"2856dc4eb7249d7c68e586f81f744d7bcf9d09dc39de0ecdac832c929c77bf76"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"866d851962e16abf12a6f4c6d82bc8bb7da7fed262412480a65abef9e8bef40b"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.08090/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Significant progress has been achieved in subject-driven text-to-image (T2I) generation, which aims to synthesize new images depicting target subjects according to user instructions. However, evaluating these models remains a significant challenge. Existing benchmarks exhibit critical limitations: 1) insufficient diversity and comprehensiveness in subject images, 2) inadequate granularity in assessing model performance across different subject difficulty levels and prompt scenarios, and 3) a profound lack of actionable insights and diagnostic guidance for subsequent model refinement. To addres","authors_text":"Chao Deng, Hang Chen, Huan Yu, Jie Jiang, Liqun Liu, Longfei Lu, Luo Liao, Mengge Xue, Peng Shu, Qing Wang, Shuang Li, Te Cao, Yuan Chen, Zhenyu Hu","cross_cats":["cs.AI"],"headline":"DSH-Bench supplies a hierarchical taxonomy and difficulty-scenario labels to expose where subject-driven text-to-image models lose identity.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-09T08:30:28Z","title":"DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.08090","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T15:13:21.785111Z","id":"ce162a79-d45e-42c0-8f1d-cc6f950a0c40","model_set":{"reader":"grok-4.3"},"one_line_summary":"DSH-Bench is a benchmark for subject-driven T2I generation that uses hierarchical taxonomy sampling, difficulty/scenario classification, and a new SICS metric showing 9.4% higher human correlation than prior measures.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"DSH-Bench supplies a hierarchical taxonomy and difficulty-scenario labels to expose where subject-driven text-to-image models lose identity.","strongest_claim":"DSH-Bench enables systematic multi-perspective analysis of subject-driven T2I models through four principal innovations: hierarchical taxonomy sampling, difficulty and scenario classification, the SICS metric with 9.4% higher human correlation, and diagnostic insights for model optimization.","weakest_assumption":"The assumption that the chosen hierarchical taxonomy and difficulty/scenario labels are sufficiently comprehensive and unbiased, and that the reported 9.4% correlation improvement for SICS generalizes beyond the specific human evaluators and model set used in the study."}},"verdict_id":"ce162a79-d45e-42c0-8f1d-cc6f950a0c40"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:48aef666fcdb87eb0d59051ba9419f56cfab224e689890d3fc7390f673c35ddc","target":"record","created_at":"2026-07-01T01:17:13Z","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":"7699d4133ee8288ea9e2b7a706d5fb8523ec77f9874d88aa8109530678b7e090","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-09T08:30:28Z","title_canon_sha256":"49e06a2de5fb0df3a987a33dc07f16ee90dbe7fa29b90315b6ba8f5538cc5cc1"},"schema_version":"1.0","source":{"id":"2603.08090","kind":"arxiv","version":3}},"canonical_sha256":"4e397c889107160cc803b47459ffad6887bc814bd3593be5850ee0d64fc9745d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e397c889107160cc803b47459ffad6887bc814bd3593be5850ee0d64fc9745d","first_computed_at":"2026-07-01T01:17:13.897447Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:17:13.897447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sx5OX1Ap5bVtEoRO071+Akk7UvxLMP3/TCetktv+zXDbimL7QVWmVxgK4UrFFgsRKGJzq7vl2/RctlkNq7/MDQ==","signature_status":"signed_v1","signed_at":"2026-07-01T01:17:13.898239Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.08090","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48aef666fcdb87eb0d59051ba9419f56cfab224e689890d3fc7390f673c35ddc","sha256:7f2cbb9080d9b757510055b08e91f311197905972827ace62b81c2e0dcb3c230"],"state_sha256":"72a2a3e5754b53d140392af4c7afa6da1b88289604185306d6603e92c41e5ba2"}