{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QZL7APBBTAGODR4O5J22CXU5F6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"16584520de0dc4ab2f2b6a533443558a56c0dd0187404b57e439cc2fc8b5dbfb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-07T19:11:22Z","title_canon_sha256":"9e9aec20a2fa9e72f223d6589aabf45224db45206dd389a1afb810d69cc788d6"},"schema_version":"1.0","source":{"id":"2606.08788","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08788","created_at":"2026-06-09T02:07:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08788v1","created_at":"2026-06-09T02:07:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08788","created_at":"2026-06-09T02:07:39Z"},{"alias_kind":"pith_short_12","alias_value":"QZL7APBBTAGO","created_at":"2026-06-09T02:07:39Z"},{"alias_kind":"pith_short_16","alias_value":"QZL7APBBTAGODR4O","created_at":"2026-06-09T02:07:39Z"},{"alias_kind":"pith_short_8","alias_value":"QZL7APBB","created_at":"2026-06-09T02:07:39Z"}],"graph_snapshots":[{"event_id":"sha256:ac8bad793689ba88b2aeed0ae0b262ef50363ccfc2152a1b71a9078971bb5d8a","target":"graph","created_at":"2026-06-09T02:07:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.08788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Representation alignment with pretrained vision models has recently shown strong potential for accelerating diffusion transformer training. By aligning intermediate diffusion features with clean-image representations from self-supervised vision encoders, existing methods improve convergence and generation quality. However, such alignment also introduces a non-trivial constraint: diffusion models operate on noisy inputs whose usable information varies across timesteps, while the reference features are extracted from clean images. In this paper, we revisit this mismatch from a token-level perspe","authors_text":"Changqian Yu, Cheng Da, Huan Yang, Kun Gai, Lianyu Pang, Song Guo, Tianlin Pan, Wenhan Luo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-07T19:11:22Z","title":"MaskAlign: Token-Subset Representation Alignment for Efficient Diffusion Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08788","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4db79ca54fb5f74328ddbfaca727c760322e200747fadf97d86272918aa9a897","target":"record","created_at":"2026-06-09T02:07:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"16584520de0dc4ab2f2b6a533443558a56c0dd0187404b57e439cc2fc8b5dbfb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-07T19:11:22Z","title_canon_sha256":"9e9aec20a2fa9e72f223d6589aabf45224db45206dd389a1afb810d69cc788d6"},"schema_version":"1.0","source":{"id":"2606.08788","kind":"arxiv","version":1}},"canonical_sha256":"8657f03c21980ce1c78eea75a15e9d2f97e81d9632800884978f3d198a2ece98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8657f03c21980ce1c78eea75a15e9d2f97e81d9632800884978f3d198a2ece98","first_computed_at":"2026-06-09T02:07:39.426589Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:07:39.426589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Aw54ZvfzsEnnA98NasCgy3KB7V8aD+jZICHhE5l9isORKQ6oRcOTD5OUadUHRuZR8DqCMH7MelYysYACatqdDg==","signature_status":"signed_v1","signed_at":"2026-06-09T02:07:39.427441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08788","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4db79ca54fb5f74328ddbfaca727c760322e200747fadf97d86272918aa9a897","sha256:ac8bad793689ba88b2aeed0ae0b262ef50363ccfc2152a1b71a9078971bb5d8a"],"state_sha256":"b248d2b7a76532a3fbe92e1eb1b0159592f4a1b186772e2886d55d46b627bb49"}