{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QOUUIX2SBJIPH5RMKJJTS3R3P3","short_pith_number":"pith:QOUUIX2S","schema_version":"1.0","canonical_sha256":"83a9445f520a50f3f62c5253396e3b7ed7f37dfc42140f145d02c86f5bbb1a52","source":{"kind":"arxiv","id":"2505.20935","version":3},"attestation_state":"computed","paper":{"title":"ISAC: Training-Free Instance-to-Semantic Attention Control for Multi-Instance Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jaesik Park, Jonghyun Choi, Kyungsu Kim, Sanghyun Jo, Wooyeol Lee, Ziseok Lee","submitted_at":"2025-05-27T09:23:10Z","abstract_excerpt":"Recent open-weight text-to-image (T2I) diffusion models still struggle with multi-instance prompts, often omitting or merging instances and mixing semantics among similar objects. We trace these failures to early denoising steps, before instance boundaries are reliably stabilized. Existing training-free guidance is largely driven by cross-attention or other token-conditioned semantic signals. Such guidance can separate concepts at the token level, but largely assumes that distinct instance regions have already emerged. In early denoising steps, it cannot reliably carve out these regions, so co"},"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":false},"canonical_record":{"source":{"id":"2505.20935","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T09:23:10Z","cross_cats_sorted":[],"title_canon_sha256":"60f5361e6a6f7b7d7f064a11b5d83f2b033205d10c5f5d939d673a4a9e031390","abstract_canon_sha256":"13016111bc05ce24f4403622b1d2c9402bebb8839dd6b294d17b30c8ae19660a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:23.477852Z","signature_b64":"3NT5ti6u53TobnweXpee/y0Y4Uuo2OGD1k1Qupxg6x70H9at1yDCJWxkKjwMGlJXf+rPJ2wT4EriRG2YM8FkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83a9445f520a50f3f62c5253396e3b7ed7f37dfc42140f145d02c86f5bbb1a52","last_reissued_at":"2026-06-30T01:16:23.477137Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:23.477137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ISAC: Training-Free Instance-to-Semantic Attention Control for Multi-Instance Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jaesik Park, Jonghyun Choi, Kyungsu Kim, Sanghyun Jo, Wooyeol Lee, Ziseok Lee","submitted_at":"2025-05-27T09:23:10Z","abstract_excerpt":"Recent open-weight text-to-image (T2I) diffusion models still struggle with multi-instance prompts, often omitting or merging instances and mixing semantics among similar objects. We trace these failures to early denoising steps, before instance boundaries are reliably stabilized. Existing training-free guidance is largely driven by cross-attention or other token-conditioned semantic signals. Such guidance can separate concepts at the token level, but largely assumes that distinct instance regions have already emerged. In early denoising steps, it cannot reliably carve out these regions, so co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20935","kind":"arxiv","version":3},"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/2505.20935/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.20935","created_at":"2026-06-30T01:16:23.477232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20935v3","created_at":"2026-06-30T01:16:23.477232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20935","created_at":"2026-06-30T01:16:23.477232+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOUUIX2SBJIP","created_at":"2026-06-30T01:16:23.477232+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOUUIX2SBJIPH5RM","created_at":"2026-06-30T01:16:23.477232+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOUUIX2S","created_at":"2026-06-30T01:16:23.477232+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QOUUIX2SBJIPH5RMKJJTS3R3P3","json":"https://pith.science/pith/QOUUIX2SBJIPH5RMKJJTS3R3P3.json","graph_json":"https://pith.science/api/pith-number/QOUUIX2SBJIPH5RMKJJTS3R3P3/graph.json","events_json":"https://pith.science/api/pith-number/QOUUIX2SBJIPH5RMKJJTS3R3P3/events.json","paper":"https://pith.science/paper/QOUUIX2S"},"agent_actions":{"view_html":"https://pith.science/pith/QOUUIX2SBJIPH5RMKJJTS3R3P3","download_json":"https://pith.science/pith/QOUUIX2SBJIPH5RMKJJTS3R3P3.json","view_paper":"https://pith.science/paper/QOUUIX2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20935&json=true","fetch_graph":"https://pith.science/api/pith-number/QOUUIX2SBJIPH5RMKJJTS3R3P3/graph.json","fetch_events":"https://pith.science/api/pith-number/QOUUIX2SBJIPH5RMKJJTS3R3P3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOUUIX2SBJIPH5RMKJJTS3R3P3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOUUIX2SBJIPH5RMKJJTS3R3P3/action/storage_attestation","attest_author":"https://pith.science/pith/QOUUIX2SBJIPH5RMKJJTS3R3P3/action/author_attestation","sign_citation":"https://pith.science/pith/QOUUIX2SBJIPH5RMKJJTS3R3P3/action/citation_signature","submit_replication":"https://pith.science/pith/QOUUIX2SBJIPH5RMKJJTS3R3P3/action/replication_record"}},"created_at":"2026-06-30T01:16:23.477232+00:00","updated_at":"2026-06-30T01:16:23.477232+00:00"}