{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UPHSYJ3NLHP4QW2YJLDP5ZQ5LS","short_pith_number":"pith:UPHSYJ3N","schema_version":"1.0","canonical_sha256":"a3cf2c276d59dfc85b584ac6fee61d5caecde4676f6e158d21c2b9c53f1013ef","source":{"kind":"arxiv","id":"2606.11096","version":1},"attestation_state":"computed","paper":{"title":"IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo He, Junke Wang, Lingyu Kong, Yitong Chen, Yixuan Ren, Yu-Gang Jiang, Zijie Diao, Zuxuan Wu","submitted_at":"2026-06-09T16:53:30Z","abstract_excerpt":"Built on pretrained vision foundation models (VFMs), representation autoencoders (RAEs) have recently emerged as a promising approach for constructing semantically rich latent spaces for image generation. However, their reconstruction quality often remains suboptimal, largely because deep VFM representations do not preserve sufficient fine-grained visual detail. This limitation becomes even more severe after discretization, where missing low-level information is difficult to recover. In fact, we observe that shallow VFM features retain considerably richer local appearance and structural detail"},"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":"2606.11096","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-09T16:53:30Z","cross_cats_sorted":[],"title_canon_sha256":"434c8962039d52e1c8dfdda81fc89ee2b82fc43489448df6592f0266610850f0","abstract_canon_sha256":"60d810a339d2d08d9c82eefa38904d33016a2c9136c146c6263f1408452677c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:11:10.129054Z","signature_b64":"hvENFCqnedm6YxHHdr6F3VPqyrbvgt55O9OVuhynIoAWBEkSVhOMTYKgvnhF+j1FklN2T2HpxMMao6RIXXE+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3cf2c276d59dfc85b584ac6fee61d5caecde4676f6e158d21c2b9c53f1013ef","last_reissued_at":"2026-06-10T01:11:10.128123Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:11:10.128123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo He, Junke Wang, Lingyu Kong, Yitong Chen, Yixuan Ren, Yu-Gang Jiang, Zijie Diao, Zuxuan Wu","submitted_at":"2026-06-09T16:53:30Z","abstract_excerpt":"Built on pretrained vision foundation models (VFMs), representation autoencoders (RAEs) have recently emerged as a promising approach for constructing semantically rich latent spaces for image generation. However, their reconstruction quality often remains suboptimal, largely because deep VFM representations do not preserve sufficient fine-grained visual detail. This limitation becomes even more severe after discretization, where missing low-level information is difficult to recover. In fact, we observe that shallow VFM features retain considerably richer local appearance and structural detail"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11096","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/2606.11096/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":"2606.11096","created_at":"2026-06-10T01:11:10.128287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11096v1","created_at":"2026-06-10T01:11:10.128287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11096","created_at":"2026-06-10T01:11:10.128287+00:00"},{"alias_kind":"pith_short_12","alias_value":"UPHSYJ3NLHP4","created_at":"2026-06-10T01:11:10.128287+00:00"},{"alias_kind":"pith_short_16","alias_value":"UPHSYJ3NLHP4QW2Y","created_at":"2026-06-10T01:11:10.128287+00:00"},{"alias_kind":"pith_short_8","alias_value":"UPHSYJ3N","created_at":"2026-06-10T01:11:10.128287+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/UPHSYJ3NLHP4QW2YJLDP5ZQ5LS","json":"https://pith.science/pith/UPHSYJ3NLHP4QW2YJLDP5ZQ5LS.json","graph_json":"https://pith.science/api/pith-number/UPHSYJ3NLHP4QW2YJLDP5ZQ5LS/graph.json","events_json":"https://pith.science/api/pith-number/UPHSYJ3NLHP4QW2YJLDP5ZQ5LS/events.json","paper":"https://pith.science/paper/UPHSYJ3N"},"agent_actions":{"view_html":"https://pith.science/pith/UPHSYJ3NLHP4QW2YJLDP5ZQ5LS","download_json":"https://pith.science/pith/UPHSYJ3NLHP4QW2YJLDP5ZQ5LS.json","view_paper":"https://pith.science/paper/UPHSYJ3N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11096&json=true","fetch_graph":"https://pith.science/api/pith-number/UPHSYJ3NLHP4QW2YJLDP5ZQ5LS/graph.json","fetch_events":"https://pith.science/api/pith-number/UPHSYJ3NLHP4QW2YJLDP5ZQ5LS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UPHSYJ3NLHP4QW2YJLDP5ZQ5LS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UPHSYJ3NLHP4QW2YJLDP5ZQ5LS/action/storage_attestation","attest_author":"https://pith.science/pith/UPHSYJ3NLHP4QW2YJLDP5ZQ5LS/action/author_attestation","sign_citation":"https://pith.science/pith/UPHSYJ3NLHP4QW2YJLDP5ZQ5LS/action/citation_signature","submit_replication":"https://pith.science/pith/UPHSYJ3NLHP4QW2YJLDP5ZQ5LS/action/replication_record"}},"created_at":"2026-06-10T01:11:10.128287+00:00","updated_at":"2026-06-10T01:11:10.128287+00:00"}