{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NOUPZU5SXMXEBUYFHFM3GSICAH","short_pith_number":"pith:NOUPZU5S","schema_version":"1.0","canonical_sha256":"6ba8fcd3b2bb2e40d3053959b3490201e470763750986b38a8d423c298a09ebb","source":{"kind":"arxiv","id":"2605.21981","version":1},"attestation_state":"computed","paper":{"title":"RiT: Vanilla Diffusion Transformers Suffice in Representation Space","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aishwarya Agrawal, Le Zhang, Ning Mang","submitted_at":"2026-05-21T04:21:43Z","abstract_excerpt":"Flow matching with $x$-prediction -- regressing the clean data point rather than the ambient velocity -- is known to exploit low-dimensional manifold structure effectively in pixel space \\cite{li2025back}. We ask whether a pretrained representation space, while containing a low-dimensional data manifold of comparable intrinsic dimensionality, offers a distribution more favorable for flow-matching learning. Comparing pixel, SD-VAE, and DINOv2 features along four geometric axes, we find that pixel and DINOv2 share nearly identical intrinsic dimensionalities (both $\\hat{d}\\!\\approx\\!33$) yet DINO"},"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":"2605.21981","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T04:21:43Z","cross_cats_sorted":[],"title_canon_sha256":"3b41e992a5a9a237135ff7b4ef024324867e5979f556e07f9d8fb661d6f5e9ad","abstract_canon_sha256":"24a7359832290f2ff5c49a9aae9f8eaeaf27c01e1cbe8686bfc952e4d70c779d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:18.507396Z","signature_b64":"rI/tkC/gMl44q8DTRAZPoJIooB3bcv+M/OTIuAGohSYr4frl+8dYZukwZOwjQMHN5Q27XZHqaQc/ik8zokfMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ba8fcd3b2bb2e40d3053959b3490201e470763750986b38a8d423c298a09ebb","last_reissued_at":"2026-05-22T01:04:18.506718Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:18.506718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RiT: Vanilla Diffusion Transformers Suffice in Representation Space","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aishwarya Agrawal, Le Zhang, Ning Mang","submitted_at":"2026-05-21T04:21:43Z","abstract_excerpt":"Flow matching with $x$-prediction -- regressing the clean data point rather than the ambient velocity -- is known to exploit low-dimensional manifold structure effectively in pixel space \\cite{li2025back}. We ask whether a pretrained representation space, while containing a low-dimensional data manifold of comparable intrinsic dimensionality, offers a distribution more favorable for flow-matching learning. Comparing pixel, SD-VAE, and DINOv2 features along four geometric axes, we find that pixel and DINOv2 share nearly identical intrinsic dimensionalities (both $\\hat{d}\\!\\approx\\!33$) yet DINO"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21981","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/2605.21981/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":"2605.21981","created_at":"2026-05-22T01:04:18.506845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21981v1","created_at":"2026-05-22T01:04:18.506845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21981","created_at":"2026-05-22T01:04:18.506845+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOUPZU5SXMXE","created_at":"2026-05-22T01:04:18.506845+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOUPZU5SXMXEBUYF","created_at":"2026-05-22T01:04:18.506845+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOUPZU5S","created_at":"2026-05-22T01:04:18.506845+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/NOUPZU5SXMXEBUYFHFM3GSICAH","json":"https://pith.science/pith/NOUPZU5SXMXEBUYFHFM3GSICAH.json","graph_json":"https://pith.science/api/pith-number/NOUPZU5SXMXEBUYFHFM3GSICAH/graph.json","events_json":"https://pith.science/api/pith-number/NOUPZU5SXMXEBUYFHFM3GSICAH/events.json","paper":"https://pith.science/paper/NOUPZU5S"},"agent_actions":{"view_html":"https://pith.science/pith/NOUPZU5SXMXEBUYFHFM3GSICAH","download_json":"https://pith.science/pith/NOUPZU5SXMXEBUYFHFM3GSICAH.json","view_paper":"https://pith.science/paper/NOUPZU5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21981&json=true","fetch_graph":"https://pith.science/api/pith-number/NOUPZU5SXMXEBUYFHFM3GSICAH/graph.json","fetch_events":"https://pith.science/api/pith-number/NOUPZU5SXMXEBUYFHFM3GSICAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOUPZU5SXMXEBUYFHFM3GSICAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOUPZU5SXMXEBUYFHFM3GSICAH/action/storage_attestation","attest_author":"https://pith.science/pith/NOUPZU5SXMXEBUYFHFM3GSICAH/action/author_attestation","sign_citation":"https://pith.science/pith/NOUPZU5SXMXEBUYFHFM3GSICAH/action/citation_signature","submit_replication":"https://pith.science/pith/NOUPZU5SXMXEBUYFHFM3GSICAH/action/replication_record"}},"created_at":"2026-05-22T01:04:18.506845+00:00","updated_at":"2026-05-22T01:04:18.506845+00:00"}