{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7YESDZK7AONVOXK6M6FKTQSPWF","short_pith_number":"pith:7YESDZK7","schema_version":"1.0","canonical_sha256":"fe0921e55f039b575d5e678aa9c24fb171cca7866246f6755dca97c14d096d5b","source":{"kind":"arxiv","id":"2503.17155","version":1},"attestation_state":"computed","paper":{"title":"D2C: Unlocking the Potential of Continuous Autoregressive Image Generation with Discrete Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fandong Meng, Jie Zhou, Jinan Xu, Liqiang Niu, Panpan Wang, Yufeng Chen","submitted_at":"2025-03-21T13:58:49Z","abstract_excerpt":"In the domain of image generation, latent-based generative models occupy a dominant status; however, these models rely heavily on image tokenizer. To meet modeling requirements, autoregressive models possessing the characteristics of scalability and flexibility embrace a discrete-valued tokenizer, but face the challenge of poor image generation quality. In contrast, diffusion models take advantage of the continuous-valued tokenizer to achieve better generation quality but are subject to low efficiency and complexity. The existing hybrid models are mainly to compensate for information loss and "},"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":"2503.17155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T13:58:49Z","cross_cats_sorted":[],"title_canon_sha256":"4d85c0c29efe97a7de01ec6db4912ffb124155ae27e083a947132af9718b7008","abstract_canon_sha256":"6a3918d90698a333b514095c8899e71159202cf32e32213f9dc4e9c5b148aa76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:58.854035Z","signature_b64":"25OMLIATencUQDJW8Z88hv8k+eXwlN3gFDkoUK110HD6yjSTYGUyNlDfe+Ldf6dbwSB3oogS3qY9UUubB+odCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe0921e55f039b575d5e678aa9c24fb171cca7866246f6755dca97c14d096d5b","last_reissued_at":"2026-07-05T10:36:58.853546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:58.853546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"D2C: Unlocking the Potential of Continuous Autoregressive Image Generation with Discrete Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fandong Meng, Jie Zhou, Jinan Xu, Liqiang Niu, Panpan Wang, Yufeng Chen","submitted_at":"2025-03-21T13:58:49Z","abstract_excerpt":"In the domain of image generation, latent-based generative models occupy a dominant status; however, these models rely heavily on image tokenizer. To meet modeling requirements, autoregressive models possessing the characteristics of scalability and flexibility embrace a discrete-valued tokenizer, but face the challenge of poor image generation quality. In contrast, diffusion models take advantage of the continuous-valued tokenizer to achieve better generation quality but are subject to low efficiency and complexity. The existing hybrid models are mainly to compensate for information loss and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17155","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/2503.17155/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":"2503.17155","created_at":"2026-07-05T10:36:58.853604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.17155v1","created_at":"2026-07-05T10:36:58.853604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17155","created_at":"2026-07-05T10:36:58.853604+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YESDZK7AONV","created_at":"2026-07-05T10:36:58.853604+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YESDZK7AONVOXK6","created_at":"2026-07-05T10:36:58.853604+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YESDZK7","created_at":"2026-07-05T10:36:58.853604+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/7YESDZK7AONVOXK6M6FKTQSPWF","json":"https://pith.science/pith/7YESDZK7AONVOXK6M6FKTQSPWF.json","graph_json":"https://pith.science/api/pith-number/7YESDZK7AONVOXK6M6FKTQSPWF/graph.json","events_json":"https://pith.science/api/pith-number/7YESDZK7AONVOXK6M6FKTQSPWF/events.json","paper":"https://pith.science/paper/7YESDZK7"},"agent_actions":{"view_html":"https://pith.science/pith/7YESDZK7AONVOXK6M6FKTQSPWF","download_json":"https://pith.science/pith/7YESDZK7AONVOXK6M6FKTQSPWF.json","view_paper":"https://pith.science/paper/7YESDZK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.17155&json=true","fetch_graph":"https://pith.science/api/pith-number/7YESDZK7AONVOXK6M6FKTQSPWF/graph.json","fetch_events":"https://pith.science/api/pith-number/7YESDZK7AONVOXK6M6FKTQSPWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YESDZK7AONVOXK6M6FKTQSPWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YESDZK7AONVOXK6M6FKTQSPWF/action/storage_attestation","attest_author":"https://pith.science/pith/7YESDZK7AONVOXK6M6FKTQSPWF/action/author_attestation","sign_citation":"https://pith.science/pith/7YESDZK7AONVOXK6M6FKTQSPWF/action/citation_signature","submit_replication":"https://pith.science/pith/7YESDZK7AONVOXK6M6FKTQSPWF/action/replication_record"}},"created_at":"2026-07-05T10:36:58.853604+00:00","updated_at":"2026-07-05T10:36:58.853604+00:00"}