{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YP5JTAECUUK5Q3DKJTQYAW5R6N","short_pith_number":"pith:YP5JTAEC","schema_version":"1.0","canonical_sha256":"c3fa998082a515d86c6a4ce1805bb1f3597a013d91e3ca3a431f35d6211433a5","source":{"kind":"arxiv","id":"2607.00371","version":1},"attestation_state":"computed","paper":{"title":"MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jie Hu, Kun Cheng, Lei Yu, Nannan Wang, Nuoyan Zhou, Xinghao Chen, Zhijun Tu","submitted_at":"2026-07-01T03:11:21Z","abstract_excerpt":"Visual AutoRegressive modeling (VAR) has pioneered a coarse-to-fine multi-scale autoregressive generative paradigm, demonstrating strong capabilities in image generation. However, VAR still suffers from inherent deficiencies in multi-scale representation learning. Specifically, lower scales primarily capture global semantics, while higher scales focus on fine-grained details. Employing a shared architecture across scales induces optimization conflicts. Moreover, due to the causal autoregressive process, inaccurate semantics at early scales can propagate and significantly degrade the final outp"},"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":"2607.00371","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T03:11:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"17b0a40163b6c40568626cbaa7a7dd97522f9bb9b7fa4812d9b6c61b623ef471","abstract_canon_sha256":"f794a67306008adeba59e650238f12452528729aa89efacad26917cd70a4e35e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:41.508923Z","signature_b64":"dE1GRtrFvEhEy/oCmHbQBYttoxVIMKj9RzpeO0nnu1sFqk3AVpj64uOUbiQHH2inKe4nDe2khcoT6USD0Vk1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3fa998082a515d86c6a4ce1805bb1f3597a013d91e3ca3a431f35d6211433a5","last_reissued_at":"2026-07-02T01:17:41.508572Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:41.508572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jie Hu, Kun Cheng, Lei Yu, Nannan Wang, Nuoyan Zhou, Xinghao Chen, Zhijun Tu","submitted_at":"2026-07-01T03:11:21Z","abstract_excerpt":"Visual AutoRegressive modeling (VAR) has pioneered a coarse-to-fine multi-scale autoregressive generative paradigm, demonstrating strong capabilities in image generation. However, VAR still suffers from inherent deficiencies in multi-scale representation learning. Specifically, lower scales primarily capture global semantics, while higher scales focus on fine-grained details. Employing a shared architecture across scales induces optimization conflicts. Moreover, due to the causal autoregressive process, inaccurate semantics at early scales can propagate and significantly degrade the final outp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00371","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/2607.00371/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":"2607.00371","created_at":"2026-07-02T01:17:41.508628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00371v1","created_at":"2026-07-02T01:17:41.508628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00371","created_at":"2026-07-02T01:17:41.508628+00:00"},{"alias_kind":"pith_short_12","alias_value":"YP5JTAECUUK5","created_at":"2026-07-02T01:17:41.508628+00:00"},{"alias_kind":"pith_short_16","alias_value":"YP5JTAECUUK5Q3DK","created_at":"2026-07-02T01:17:41.508628+00:00"},{"alias_kind":"pith_short_8","alias_value":"YP5JTAEC","created_at":"2026-07-02T01:17:41.508628+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/YP5JTAECUUK5Q3DKJTQYAW5R6N","json":"https://pith.science/pith/YP5JTAECUUK5Q3DKJTQYAW5R6N.json","graph_json":"https://pith.science/api/pith-number/YP5JTAECUUK5Q3DKJTQYAW5R6N/graph.json","events_json":"https://pith.science/api/pith-number/YP5JTAECUUK5Q3DKJTQYAW5R6N/events.json","paper":"https://pith.science/paper/YP5JTAEC"},"agent_actions":{"view_html":"https://pith.science/pith/YP5JTAECUUK5Q3DKJTQYAW5R6N","download_json":"https://pith.science/pith/YP5JTAECUUK5Q3DKJTQYAW5R6N.json","view_paper":"https://pith.science/paper/YP5JTAEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00371&json=true","fetch_graph":"https://pith.science/api/pith-number/YP5JTAECUUK5Q3DKJTQYAW5R6N/graph.json","fetch_events":"https://pith.science/api/pith-number/YP5JTAECUUK5Q3DKJTQYAW5R6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YP5JTAECUUK5Q3DKJTQYAW5R6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YP5JTAECUUK5Q3DKJTQYAW5R6N/action/storage_attestation","attest_author":"https://pith.science/pith/YP5JTAECUUK5Q3DKJTQYAW5R6N/action/author_attestation","sign_citation":"https://pith.science/pith/YP5JTAECUUK5Q3DKJTQYAW5R6N/action/citation_signature","submit_replication":"https://pith.science/pith/YP5JTAECUUK5Q3DKJTQYAW5R6N/action/replication_record"}},"created_at":"2026-07-02T01:17:41.508628+00:00","updated_at":"2026-07-02T01:17:41.508628+00:00"}