{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JY4XZCERA4LAZSADWR2FT75NNC","short_pith_number":"pith:JY4XZCER","schema_version":"1.0","canonical_sha256":"4e397c889107160cc803b47459ffad6887bc814bd3593be5850ee0d64fc9745d","source":{"kind":"arxiv","id":"2603.08090","version":3},"attestation_state":"computed","paper":{"title":"DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"DSH-Bench supplies a hierarchical taxonomy and difficulty-scenario labels to expose where subject-driven text-to-image models lose identity.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","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","submitted_at":"2026-03-09T08:30:28Z","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"},"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":true},"canonical_record":{"source":{"id":"2603.08090","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-09T08:30:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"49e06a2de5fb0df3a987a33dc07f16ee90dbe7fa29b90315b6ba8f5538cc5cc1","abstract_canon_sha256":"7699d4133ee8288ea9e2b7a706d5fb8523ec77f9874d88aa8109530678b7e090"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:13.898239Z","signature_b64":"Sx5OX1Ap5bVtEoRO071+Akk7UvxLMP3/TCetktv+zXDbimL7QVWmVxgK4UrFFgsRKGJzq7vl2/RctlkNq7/MDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e397c889107160cc803b47459ffad6887bc814bd3593be5850ee0d64fc9745d","last_reissued_at":"2026-07-01T01:17:13.897447Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:13.897447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"DSH-Bench supplies a hierarchical taxonomy and difficulty-scenario labels to expose where subject-driven text-to-image models lose identity.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","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","submitted_at":"2026-03-09T08:30:28Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"DSH-Bench supplies a hierarchical taxonomy and difficulty-scenario labels to expose where subject-driven text-to-image models lose identity.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2856dc4eb7249d7c68e586f81f744d7bcf9d09dc39de0ecdac832c929c77bf76"},"source":{"id":"2603.08090","kind":"arxiv","version":3},"verdict":{"id":"ce162a79-d45e-42c0-8f1d-cc6f950a0c40","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T15:13:21.785111Z","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.","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","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.","pith_extraction_headline":"DSH-Bench supplies a hierarchical taxonomy and difficulty-scenario labels to expose where subject-driven text-to-image models lose identity."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.08090/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":2,"snapshot_sha256":"866d851962e16abf12a6f4c6d82bc8bb7da7fed262412480a65abef9e8bef40b"},"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":"2603.08090","created_at":"2026-07-01T01:17:13.897556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.08090v3","created_at":"2026-07-01T01:17:13.897556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.08090","created_at":"2026-07-01T01:17:13.897556+00:00"},{"alias_kind":"pith_short_12","alias_value":"JY4XZCERA4LA","created_at":"2026-07-01T01:17:13.897556+00:00"},{"alias_kind":"pith_short_16","alias_value":"JY4XZCERA4LAZSAD","created_at":"2026-07-01T01:17:13.897556+00:00"},{"alias_kind":"pith_short_8","alias_value":"JY4XZCER","created_at":"2026-07-01T01:17:13.897556+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JY4XZCERA4LAZSADWR2FT75NNC","json":"https://pith.science/pith/JY4XZCERA4LAZSADWR2FT75NNC.json","graph_json":"https://pith.science/api/pith-number/JY4XZCERA4LAZSADWR2FT75NNC/graph.json","events_json":"https://pith.science/api/pith-number/JY4XZCERA4LAZSADWR2FT75NNC/events.json","paper":"https://pith.science/paper/JY4XZCER"},"agent_actions":{"view_html":"https://pith.science/pith/JY4XZCERA4LAZSADWR2FT75NNC","download_json":"https://pith.science/pith/JY4XZCERA4LAZSADWR2FT75NNC.json","view_paper":"https://pith.science/paper/JY4XZCER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.08090&json=true","fetch_graph":"https://pith.science/api/pith-number/JY4XZCERA4LAZSADWR2FT75NNC/graph.json","fetch_events":"https://pith.science/api/pith-number/JY4XZCERA4LAZSADWR2FT75NNC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JY4XZCERA4LAZSADWR2FT75NNC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JY4XZCERA4LAZSADWR2FT75NNC/action/storage_attestation","attest_author":"https://pith.science/pith/JY4XZCERA4LAZSADWR2FT75NNC/action/author_attestation","sign_citation":"https://pith.science/pith/JY4XZCERA4LAZSADWR2FT75NNC/action/citation_signature","submit_replication":"https://pith.science/pith/JY4XZCERA4LAZSADWR2FT75NNC/action/replication_record"}},"created_at":"2026-07-01T01:17:13.897556+00:00","updated_at":"2026-07-01T01:17:13.897556+00:00"}