{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YTJM6UU3GXPS5F7VEGW4PM64CM","short_pith_number":"pith:YTJM6UU3","schema_version":"1.0","canonical_sha256":"c4d2cf529b35df2e97f521adc7b3dc132c6fbfee975d3f45c08f1e6016375bcd","source":{"kind":"arxiv","id":"2607.10535","version":1},"attestation_state":"computed","paper":{"title":"Improving Sample Diversity in Autoregressive Text-to-Image Generation via Cluster Truncation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Phillip Howard, Runyan Tan, Shuang Wu, Trang Nguyen","submitted_at":"2026-07-12T02:14:16Z","abstract_excerpt":"While diffusion models achieve state-of-the-art image quality for text-to-image (T2I) generation, recent work has demonstrated that they suffer from sample diversity collapse. In this work, we investigate whether autoregressive (AR) image generation models can push the Pareto frontier between image quality and sample diversity. With recent advances in quality and efficiency, AR models have emerged as a viable alternative to diffusion-based image generation. Beyond enabling new use cases such as interleaved image-text generation, their sequential generation process makes them compatible with a "},"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":"2607.10535","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-12T02:14:16Z","cross_cats_sorted":[],"title_canon_sha256":"5b9a585c6dda4e1356d6ce08205ba9bb52091602ac9c1424bf79217ccf5e3085","abstract_canon_sha256":"b6028ad034a0b0fc9eefd61bf8a38a2e1682b6f67a6c23f4e46a57fa9a13a7a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:20.095515Z","signature_b64":"lsr2rXC81hQJsEh/x4xoj/kEb3mXm45um3Io31w+V9e1dAiwc49u2T0hWdznS0eRNDWq4szs32Me6YrM5znvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4d2cf529b35df2e97f521adc7b3dc132c6fbfee975d3f45c08f1e6016375bcd","last_reissued_at":"2026-07-14T01:21:20.094700Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:20.094700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Sample Diversity in Autoregressive Text-to-Image Generation via Cluster Truncation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Phillip Howard, Runyan Tan, Shuang Wu, Trang Nguyen","submitted_at":"2026-07-12T02:14:16Z","abstract_excerpt":"While diffusion models achieve state-of-the-art image quality for text-to-image (T2I) generation, recent work has demonstrated that they suffer from sample diversity collapse. In this work, we investigate whether autoregressive (AR) image generation models can push the Pareto frontier between image quality and sample diversity. With recent advances in quality and efficiency, AR models have emerged as a viable alternative to diffusion-based image generation. Beyond enabling new use cases such as interleaved image-text generation, their sequential generation process makes them compatible with a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10535","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/2607.10535/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":"2607.10535","created_at":"2026-07-14T01:21:20.095108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10535v1","created_at":"2026-07-14T01:21:20.095108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10535","created_at":"2026-07-14T01:21:20.095108+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTJM6UU3GXPS","created_at":"2026-07-14T01:21:20.095108+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTJM6UU3GXPS5F7V","created_at":"2026-07-14T01:21:20.095108+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTJM6UU3","created_at":"2026-07-14T01:21:20.095108+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/YTJM6UU3GXPS5F7VEGW4PM64CM","json":"https://pith.science/pith/YTJM6UU3GXPS5F7VEGW4PM64CM.json","graph_json":"https://pith.science/api/pith-number/YTJM6UU3GXPS5F7VEGW4PM64CM/graph.json","events_json":"https://pith.science/api/pith-number/YTJM6UU3GXPS5F7VEGW4PM64CM/events.json","paper":"https://pith.science/paper/YTJM6UU3"},"agent_actions":{"view_html":"https://pith.science/pith/YTJM6UU3GXPS5F7VEGW4PM64CM","download_json":"https://pith.science/pith/YTJM6UU3GXPS5F7VEGW4PM64CM.json","view_paper":"https://pith.science/paper/YTJM6UU3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10535&json=true","fetch_graph":"https://pith.science/api/pith-number/YTJM6UU3GXPS5F7VEGW4PM64CM/graph.json","fetch_events":"https://pith.science/api/pith-number/YTJM6UU3GXPS5F7VEGW4PM64CM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTJM6UU3GXPS5F7VEGW4PM64CM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTJM6UU3GXPS5F7VEGW4PM64CM/action/storage_attestation","attest_author":"https://pith.science/pith/YTJM6UU3GXPS5F7VEGW4PM64CM/action/author_attestation","sign_citation":"https://pith.science/pith/YTJM6UU3GXPS5F7VEGW4PM64CM/action/citation_signature","submit_replication":"https://pith.science/pith/YTJM6UU3GXPS5F7VEGW4PM64CM/action/replication_record"}},"created_at":"2026-07-14T01:21:20.095108+00:00","updated_at":"2026-07-14T01:21:20.095108+00:00"}