{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6JVDPT7UMEVDK7SDV4CQBBPHMN","short_pith_number":"pith:6JVDPT7U","schema_version":"1.0","canonical_sha256":"f26a37cff4612a357e43af050085e763789679e07f23a097f0f2195b50ab9a40","source":{"kind":"arxiv","id":"2311.16503","version":3},"attestation_state":"computed","paper":{"title":"TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jing Liu, Ruihao Gong, Tianlong Chen, Xianglong Liu, Yushi Huang","submitted_at":"2023-11-27T12:59:52Z","abstract_excerpt":"The Diffusion model, a prevalent framework for image generation, encounters significant challenges in terms of broad applicability due to its extended inference times and substantial memory requirements. Efficient Post-training Quantization (PTQ) is pivotal for addressing these issues in traditional models. Different from traditional models, diffusion models heavily depend on the time-step $t$ to achieve satisfactory multi-round denoising. Usually, $t$ from the finite set $\\{1, \\ldots, T\\}$ is encoded to a temporal feature by a few modules totally irrespective of the sampling data. However, ex"},"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":"2311.16503","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T12:59:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c93a75ffd711ecf68894b03657445dbd05097158d320431848daf5275994421c","abstract_canon_sha256":"92b07d79c6897c0ec32a6a209a10c43075d8fe420f41d078a397f4dd1b41e8d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:34.528770Z","signature_b64":"BHXKthkacmR8EkjGR247Qc5wXWdOejqmvYXZv0hFunBKU/BIQyVAZwSnKUYHvun/3lDiI877JOEAieV7Ml5pDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f26a37cff4612a357e43af050085e763789679e07f23a097f0f2195b50ab9a40","last_reissued_at":"2026-07-05T07:54:34.528307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:34.528307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jing Liu, Ruihao Gong, Tianlong Chen, Xianglong Liu, Yushi Huang","submitted_at":"2023-11-27T12:59:52Z","abstract_excerpt":"The Diffusion model, a prevalent framework for image generation, encounters significant challenges in terms of broad applicability due to its extended inference times and substantial memory requirements. Efficient Post-training Quantization (PTQ) is pivotal for addressing these issues in traditional models. Different from traditional models, diffusion models heavily depend on the time-step $t$ to achieve satisfactory multi-round denoising. Usually, $t$ from the finite set $\\{1, \\ldots, T\\}$ is encoded to a temporal feature by a few modules totally irrespective of the sampling data. However, ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16503","kind":"arxiv","version":3},"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/2311.16503/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":"2311.16503","created_at":"2026-07-05T07:54:34.528376+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.16503v3","created_at":"2026-07-05T07:54:34.528376+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16503","created_at":"2026-07-05T07:54:34.528376+00:00"},{"alias_kind":"pith_short_12","alias_value":"6JVDPT7UMEVD","created_at":"2026-07-05T07:54:34.528376+00:00"},{"alias_kind":"pith_short_16","alias_value":"6JVDPT7UMEVDK7SD","created_at":"2026-07-05T07:54:34.528376+00:00"},{"alias_kind":"pith_short_8","alias_value":"6JVDPT7U","created_at":"2026-07-05T07:54:34.528376+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.06661","citing_title":"Efficiency Meets Fidelity: A Novel Quantization Framework for Stable Diffusion","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6JVDPT7UMEVDK7SDV4CQBBPHMN","json":"https://pith.science/pith/6JVDPT7UMEVDK7SDV4CQBBPHMN.json","graph_json":"https://pith.science/api/pith-number/6JVDPT7UMEVDK7SDV4CQBBPHMN/graph.json","events_json":"https://pith.science/api/pith-number/6JVDPT7UMEVDK7SDV4CQBBPHMN/events.json","paper":"https://pith.science/paper/6JVDPT7U"},"agent_actions":{"view_html":"https://pith.science/pith/6JVDPT7UMEVDK7SDV4CQBBPHMN","download_json":"https://pith.science/pith/6JVDPT7UMEVDK7SDV4CQBBPHMN.json","view_paper":"https://pith.science/paper/6JVDPT7U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.16503&json=true","fetch_graph":"https://pith.science/api/pith-number/6JVDPT7UMEVDK7SDV4CQBBPHMN/graph.json","fetch_events":"https://pith.science/api/pith-number/6JVDPT7UMEVDK7SDV4CQBBPHMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6JVDPT7UMEVDK7SDV4CQBBPHMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6JVDPT7UMEVDK7SDV4CQBBPHMN/action/storage_attestation","attest_author":"https://pith.science/pith/6JVDPT7UMEVDK7SDV4CQBBPHMN/action/author_attestation","sign_citation":"https://pith.science/pith/6JVDPT7UMEVDK7SDV4CQBBPHMN/action/citation_signature","submit_replication":"https://pith.science/pith/6JVDPT7UMEVDK7SDV4CQBBPHMN/action/replication_record"}},"created_at":"2026-07-05T07:54:34.528376+00:00","updated_at":"2026-07-05T07:54:34.528376+00:00"}