{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RQKNQBD2QRGUWWVTGOIDBL5CAE","short_pith_number":"pith:RQKNQBD2","schema_version":"1.0","canonical_sha256":"8c14d8047a844d4b5ab3339030afa2010bfc7ab615517bcf519885234e386c54","source":{"kind":"arxiv","id":"2405.14854","version":2},"attestation_state":"computed","paper":{"title":"TerDiT: Ternary Diffusion Models with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aojun Zhou, Hongsheng Li, Junchi Yan, Peng Gao, Qi Liu, Renrui Zhang, Xudong Lu, Xue Yang, Yuhui Xu, Ziyi Lin","submitted_at":"2024-05-23T17:57:24Z","abstract_excerpt":"Recent developments in large-scale pre-trained text-to-image diffusion models have significantly improved the generation of high-fidelity images, particularly with the emergence of diffusion transformer models (DiTs). Among diffusion models, diffusion transformers have demonstrated superior image-generation capabilities, boosting lower FID scores and higher scalability. However, deploying large-scale DiT models can be expensive due to their excessive parameter numbers. Although existing research has explored efficient deployment techniques for diffusion models, such as model quantization, ther"},"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":"2405.14854","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T17:57:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"183d5a38d1fb582970ae1c7ec17606d31445f0245361efd627b95822ac8d5e97","abstract_canon_sha256":"4695065d6871c3576b2efd45548427d275339b231c9058ce2892acf8dfdedfbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:08.376277Z","signature_b64":"9wi2umeQc5JeIAH7D/6Y1gGNLuY0AnJFR6Cdm1OQICB+nIAEF0GcLIhhI6SUTPjx1dclpzJ+H5kUp+LuB9MWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c14d8047a844d4b5ab3339030afa2010bfc7ab615517bcf519885234e386c54","last_reissued_at":"2026-07-05T10:45:08.375759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:08.375759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TerDiT: Ternary Diffusion Models with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aojun Zhou, Hongsheng Li, Junchi Yan, Peng Gao, Qi Liu, Renrui Zhang, Xudong Lu, Xue Yang, Yuhui Xu, Ziyi Lin","submitted_at":"2024-05-23T17:57:24Z","abstract_excerpt":"Recent developments in large-scale pre-trained text-to-image diffusion models have significantly improved the generation of high-fidelity images, particularly with the emergence of diffusion transformer models (DiTs). Among diffusion models, diffusion transformers have demonstrated superior image-generation capabilities, boosting lower FID scores and higher scalability. However, deploying large-scale DiT models can be expensive due to their excessive parameter numbers. Although existing research has explored efficient deployment techniques for diffusion models, such as model quantization, ther"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14854","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/2405.14854/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":"2405.14854","created_at":"2026-07-05T10:45:08.375819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14854v2","created_at":"2026-07-05T10:45:08.375819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14854","created_at":"2026-07-05T10:45:08.375819+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQKNQBD2QRGU","created_at":"2026-07-05T10:45:08.375819+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQKNQBD2QRGUWWVT","created_at":"2026-07-05T10:45:08.375819+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQKNQBD2","created_at":"2026-07-05T10:45:08.375819+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":255,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23582","citing_title":"RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":255,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RQKNQBD2QRGUWWVTGOIDBL5CAE","json":"https://pith.science/pith/RQKNQBD2QRGUWWVTGOIDBL5CAE.json","graph_json":"https://pith.science/api/pith-number/RQKNQBD2QRGUWWVTGOIDBL5CAE/graph.json","events_json":"https://pith.science/api/pith-number/RQKNQBD2QRGUWWVTGOIDBL5CAE/events.json","paper":"https://pith.science/paper/RQKNQBD2"},"agent_actions":{"view_html":"https://pith.science/pith/RQKNQBD2QRGUWWVTGOIDBL5CAE","download_json":"https://pith.science/pith/RQKNQBD2QRGUWWVTGOIDBL5CAE.json","view_paper":"https://pith.science/paper/RQKNQBD2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14854&json=true","fetch_graph":"https://pith.science/api/pith-number/RQKNQBD2QRGUWWVTGOIDBL5CAE/graph.json","fetch_events":"https://pith.science/api/pith-number/RQKNQBD2QRGUWWVTGOIDBL5CAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQKNQBD2QRGUWWVTGOIDBL5CAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQKNQBD2QRGUWWVTGOIDBL5CAE/action/storage_attestation","attest_author":"https://pith.science/pith/RQKNQBD2QRGUWWVTGOIDBL5CAE/action/author_attestation","sign_citation":"https://pith.science/pith/RQKNQBD2QRGUWWVTGOIDBL5CAE/action/citation_signature","submit_replication":"https://pith.science/pith/RQKNQBD2QRGUWWVTGOIDBL5CAE/action/replication_record"}},"created_at":"2026-07-05T10:45:08.375819+00:00","updated_at":"2026-07-05T10:45:08.375819+00:00"}