{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X45YCDLRJYIVUR76UUKDHV3CM6","short_pith_number":"pith:X45YCDLR","schema_version":"1.0","canonical_sha256":"bf3b810d714e115a47fea51433d762678e8674901d67465865f72a560fed827c","source":{"kind":"arxiv","id":"2511.19778","version":2},"attestation_state":"computed","paper":{"title":"Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitris Samaras, Haoyu Wu, Hieu Le, Jingyi Xu, Qiaomu Miao","submitted_at":"2025-11-24T23:10:15Z","abstract_excerpt":"Rotary positional embeddings (RoPE) are widely used in diffusion transformers (DiTs) to encode spatial relationships, yet their behavior with mixed-resolution tokens remains underexplored. A natural approach is to rescale token positions from different resolutions into a unified coordinate system before attention, but we show this fails. Our analysis shows that with RoPE, the attention similarity score is a highly structured and periodic function of token distance, so rescaling distances across resolutions moves token pairs to different regions of this periodic function, leading to incorrect 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":"2511.19778","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T23:10:15Z","cross_cats_sorted":[],"title_canon_sha256":"72db8fa95bad4f61322432ff2e9affe2e422ddd91d92ec1418d8fc259fc8839d","abstract_canon_sha256":"585b7c62998a1380f21175a6e47ad60a50ed162c5fcd6b7292b296d111eb4ccf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:11.970765Z","signature_b64":"xPqUReBEhV07yNXEON4+Gm17cheN9SN2a+RvR+FYudGM4uSBPnGlcoisjd1ocFs1LtmVJq2cHd6D7roXJvtqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf3b810d714e115a47fea51433d762678e8674901d67465865f72a560fed827c","last_reissued_at":"2026-07-01T01:17:11.970265Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:11.970265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitris Samaras, Haoyu Wu, Hieu Le, Jingyi Xu, Qiaomu Miao","submitted_at":"2025-11-24T23:10:15Z","abstract_excerpt":"Rotary positional embeddings (RoPE) are widely used in diffusion transformers (DiTs) to encode spatial relationships, yet their behavior with mixed-resolution tokens remains underexplored. A natural approach is to rescale token positions from different resolutions into a unified coordinate system before attention, but we show this fails. Our analysis shows that with RoPE, the attention similarity score is a highly structured and periodic function of token distance, so rescaling distances across resolutions moves token pairs to different regions of this periodic function, leading to incorrect a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.19778","kind":"arxiv","version":2},"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/2511.19778/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":"2511.19778","created_at":"2026-07-01T01:17:11.970330+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.19778v2","created_at":"2026-07-01T01:17:11.970330+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.19778","created_at":"2026-07-01T01:17:11.970330+00:00"},{"alias_kind":"pith_short_12","alias_value":"X45YCDLRJYIV","created_at":"2026-07-01T01:17:11.970330+00:00"},{"alias_kind":"pith_short_16","alias_value":"X45YCDLRJYIVUR76","created_at":"2026-07-01T01:17:11.970330+00:00"},{"alias_kind":"pith_short_8","alias_value":"X45YCDLR","created_at":"2026-07-01T01:17:11.970330+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/X45YCDLRJYIVUR76UUKDHV3CM6","json":"https://pith.science/pith/X45YCDLRJYIVUR76UUKDHV3CM6.json","graph_json":"https://pith.science/api/pith-number/X45YCDLRJYIVUR76UUKDHV3CM6/graph.json","events_json":"https://pith.science/api/pith-number/X45YCDLRJYIVUR76UUKDHV3CM6/events.json","paper":"https://pith.science/paper/X45YCDLR"},"agent_actions":{"view_html":"https://pith.science/pith/X45YCDLRJYIVUR76UUKDHV3CM6","download_json":"https://pith.science/pith/X45YCDLRJYIVUR76UUKDHV3CM6.json","view_paper":"https://pith.science/paper/X45YCDLR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.19778&json=true","fetch_graph":"https://pith.science/api/pith-number/X45YCDLRJYIVUR76UUKDHV3CM6/graph.json","fetch_events":"https://pith.science/api/pith-number/X45YCDLRJYIVUR76UUKDHV3CM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X45YCDLRJYIVUR76UUKDHV3CM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X45YCDLRJYIVUR76UUKDHV3CM6/action/storage_attestation","attest_author":"https://pith.science/pith/X45YCDLRJYIVUR76UUKDHV3CM6/action/author_attestation","sign_citation":"https://pith.science/pith/X45YCDLRJYIVUR76UUKDHV3CM6/action/citation_signature","submit_replication":"https://pith.science/pith/X45YCDLRJYIVUR76UUKDHV3CM6/action/replication_record"}},"created_at":"2026-07-01T01:17:11.970330+00:00","updated_at":"2026-07-01T01:17:11.970330+00:00"}