{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OGCDGPMRSND2IDXQ6WA35CFO7N","short_pith_number":"pith:OGCDGPMR","schema_version":"1.0","canonical_sha256":"7184333d919347a40ef0f581be88aefb6accb1371a89ac49c0cc0963a42c6172","source":{"kind":"arxiv","id":"2606.06813","version":1},"attestation_state":"computed","paper":{"title":"Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dahee Kwon, Haeun Lee, Jaesik Choi","submitted_at":"2026-06-05T01:27:44Z","abstract_excerpt":"Recent text-to-image models built on large-scale Transformer backbones and flow-based objectives deliver strong text-image alignment and high visual quality, yet often produce overly similar samples under a fixed prompt. Existing diversity-enhancement methods alleviate this issue, but typically require expensive sampling or auxiliary optimization, incurring non-trivial overhead. To investigate the root cause of this homogeneity, we examine intermediate Transformer features and observe that the zero-frequency spatial average (DC) component rapidly converges across seeds early in generation, cau"},"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":"2606.06813","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T01:27:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"650511378a8e762cc6ce706462b6c417dc3e69227468b5a152450ed7de29e38f","abstract_canon_sha256":"1f769fe0d6fb0e9454e80a8aba02dcb4c40f48c7a7f7f67350d393d8948cdcdb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:29.482245Z","signature_b64":"VafVFzwW5DXobEbS8azFDEWXjGUPHHC4ss0XLQFhQsVtiywNJk4FhDlwb4H9qu0vfKsihT1WxQ8W+5dDkXrHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7184333d919347a40ef0f581be88aefb6accb1371a89ac49c0cc0963a42c6172","last_reissued_at":"2026-06-08T01:04:29.481552Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:29.481552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dahee Kwon, Haeun Lee, Jaesik Choi","submitted_at":"2026-06-05T01:27:44Z","abstract_excerpt":"Recent text-to-image models built on large-scale Transformer backbones and flow-based objectives deliver strong text-image alignment and high visual quality, yet often produce overly similar samples under a fixed prompt. Existing diversity-enhancement methods alleviate this issue, but typically require expensive sampling or auxiliary optimization, incurring non-trivial overhead. To investigate the root cause of this homogeneity, we examine intermediate Transformer features and observe that the zero-frequency spatial average (DC) component rapidly converges across seeds early in generation, cau"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06813","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/2606.06813/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":"2606.06813","created_at":"2026-06-08T01:04:29.481646+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06813v1","created_at":"2026-06-08T01:04:29.481646+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06813","created_at":"2026-06-08T01:04:29.481646+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGCDGPMRSND2","created_at":"2026-06-08T01:04:29.481646+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGCDGPMRSND2IDXQ","created_at":"2026-06-08T01:04:29.481646+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGCDGPMR","created_at":"2026-06-08T01:04:29.481646+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/OGCDGPMRSND2IDXQ6WA35CFO7N","json":"https://pith.science/pith/OGCDGPMRSND2IDXQ6WA35CFO7N.json","graph_json":"https://pith.science/api/pith-number/OGCDGPMRSND2IDXQ6WA35CFO7N/graph.json","events_json":"https://pith.science/api/pith-number/OGCDGPMRSND2IDXQ6WA35CFO7N/events.json","paper":"https://pith.science/paper/OGCDGPMR"},"agent_actions":{"view_html":"https://pith.science/pith/OGCDGPMRSND2IDXQ6WA35CFO7N","download_json":"https://pith.science/pith/OGCDGPMRSND2IDXQ6WA35CFO7N.json","view_paper":"https://pith.science/paper/OGCDGPMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06813&json=true","fetch_graph":"https://pith.science/api/pith-number/OGCDGPMRSND2IDXQ6WA35CFO7N/graph.json","fetch_events":"https://pith.science/api/pith-number/OGCDGPMRSND2IDXQ6WA35CFO7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGCDGPMRSND2IDXQ6WA35CFO7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGCDGPMRSND2IDXQ6WA35CFO7N/action/storage_attestation","attest_author":"https://pith.science/pith/OGCDGPMRSND2IDXQ6WA35CFO7N/action/author_attestation","sign_citation":"https://pith.science/pith/OGCDGPMRSND2IDXQ6WA35CFO7N/action/citation_signature","submit_replication":"https://pith.science/pith/OGCDGPMRSND2IDXQ6WA35CFO7N/action/replication_record"}},"created_at":"2026-06-08T01:04:29.481646+00:00","updated_at":"2026-06-08T01:04:29.481646+00:00"}