{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L4PYUHEENIIUR4Z7GL5MG7ETRJ","short_pith_number":"pith:L4PYUHEE","schema_version":"1.0","canonical_sha256":"5f1f8a1c846a1148f33f32fac37c938a7079352f051c56f31c0f8d4059d9cae8","source":{"kind":"arxiv","id":"2306.05423","version":2},"attestation_state":"computed","paper":{"title":"ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changyao Tian, Chenxin Tao, Gao Huang, Hao Li, Hongsheng Li, Jifeng Dai, Lewei Lu, Xiaogang Wang, Xizhou Zhu, Ziheng Li","submitted_at":"2023-06-08T17:59:32Z","abstract_excerpt":"Image recognition and generation have long been developed independently of each other. With the recent trend towards general-purpose representation learning, the development of general representations for both recognition and generation tasks is also promoted. However, preliminary attempts mainly focus on generation performance, but are still inferior on recognition tasks. These methods are modeled in the vector-quantized (VQ) space, whereas leading recognition methods use pixels as inputs. Our key insights are twofold: (1) pixels as inputs are crucial for recognition tasks; (2) VQ tokens as r"},"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":"2306.05423","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-08T17:59:32Z","cross_cats_sorted":[],"title_canon_sha256":"edf2e567f2be4e6cd53ff583c1ce9496684b8548f5c8511a2bf6e561aa32fa3c","abstract_canon_sha256":"aff4cd88049d65597c9b92eeebaaadb7de7ff69cacb204a97af2105afe20bc10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:06.281640Z","signature_b64":"I3mFt7TqpqT8h5e1z/uLJnMKoDE0nXNz4d1XPRsZ7SqIpbjBdOdvP7TGPOIlK9Pg7/BS+mrN2z17e1CjOz7WAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f1f8a1c846a1148f33f32fac37c938a7079352f051c56f31c0f8d4059d9cae8","last_reissued_at":"2026-07-05T08:03:06.281134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:06.281134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changyao Tian, Chenxin Tao, Gao Huang, Hao Li, Hongsheng Li, Jifeng Dai, Lewei Lu, Xiaogang Wang, Xizhou Zhu, Ziheng Li","submitted_at":"2023-06-08T17:59:32Z","abstract_excerpt":"Image recognition and generation have long been developed independently of each other. With the recent trend towards general-purpose representation learning, the development of general representations for both recognition and generation tasks is also promoted. However, preliminary attempts mainly focus on generation performance, but are still inferior on recognition tasks. These methods are modeled in the vector-quantized (VQ) space, whereas leading recognition methods use pixels as inputs. Our key insights are twofold: (1) pixels as inputs are crucial for recognition tasks; (2) VQ tokens as r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05423","kind":"arxiv","version":2},"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/2306.05423/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":"2306.05423","created_at":"2026-07-05T08:03:06.281194+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05423v2","created_at":"2026-07-05T08:03:06.281194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05423","created_at":"2026-07-05T08:03:06.281194+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4PYUHEENIIU","created_at":"2026-07-05T08:03:06.281194+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4PYUHEENIIUR4Z7","created_at":"2026-07-05T08:03:06.281194+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4PYUHEE","created_at":"2026-07-05T08:03:06.281194+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25012","citing_title":"Learning from Semantic Dictionaries: Discriminative Codebook Contrastive Learning for Unified Visual Representation and Generation","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L4PYUHEENIIUR4Z7GL5MG7ETRJ","json":"https://pith.science/pith/L4PYUHEENIIUR4Z7GL5MG7ETRJ.json","graph_json":"https://pith.science/api/pith-number/L4PYUHEENIIUR4Z7GL5MG7ETRJ/graph.json","events_json":"https://pith.science/api/pith-number/L4PYUHEENIIUR4Z7GL5MG7ETRJ/events.json","paper":"https://pith.science/paper/L4PYUHEE"},"agent_actions":{"view_html":"https://pith.science/pith/L4PYUHEENIIUR4Z7GL5MG7ETRJ","download_json":"https://pith.science/pith/L4PYUHEENIIUR4Z7GL5MG7ETRJ.json","view_paper":"https://pith.science/paper/L4PYUHEE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05423&json=true","fetch_graph":"https://pith.science/api/pith-number/L4PYUHEENIIUR4Z7GL5MG7ETRJ/graph.json","fetch_events":"https://pith.science/api/pith-number/L4PYUHEENIIUR4Z7GL5MG7ETRJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4PYUHEENIIUR4Z7GL5MG7ETRJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4PYUHEENIIUR4Z7GL5MG7ETRJ/action/storage_attestation","attest_author":"https://pith.science/pith/L4PYUHEENIIUR4Z7GL5MG7ETRJ/action/author_attestation","sign_citation":"https://pith.science/pith/L4PYUHEENIIUR4Z7GL5MG7ETRJ/action/citation_signature","submit_replication":"https://pith.science/pith/L4PYUHEENIIUR4Z7GL5MG7ETRJ/action/replication_record"}},"created_at":"2026-07-05T08:03:06.281194+00:00","updated_at":"2026-07-05T08:03:06.281194+00:00"}