{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZQBX6DWI6Z65AX5QMKHJZP7WGJ","short_pith_number":"pith:ZQBX6DWI","schema_version":"1.0","canonical_sha256":"cc037f0ec8f67dd05fb0628e9cbff632517935b1c2b2ca77a1b319fb33d52214","source":{"kind":"arxiv","id":"2607.00927","version":1},"attestation_state":"computed","paper":{"title":"Post-Training Pruning for Diffusion Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chengzhi Hu, Jing Zhang, Mengjuan Chen, Qingyi Gu, Xuewen Liu, Zhikai Li","submitted_at":"2026-07-01T13:30:49Z","abstract_excerpt":"Diffusion Transformers (DiTs) have demonstrated impressive performance in image generation but suffer from substantial computational overhead and resource consumption. Post-training pruning offers a promising solution; however, due to DiTs' unique architectural design and parameter distribution, traditional pruning methods are inapplicable, leading to significant performance degradation. Specifically, prior methods developed for LLMs, which derive metrics through a series of approximations, amplify the relative contribution of weights in the saliency metric. In addition, weights in DiTs exhibi"},"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":"2607.00927","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T13:30:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0b178781b881b6f429992d482ee2f23ae6f32ce49c7acf0ff4ad5995bd8b7911","abstract_canon_sha256":"164f45f6c96b7ea1c4c38e951b3f37d03388943d7e9504a3f4725097d1e59ae3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:23.778545Z","signature_b64":"zT6pg1TU632CmhSp5db2e7eugUiyYh4Keb/mBYTmCtzbTJBJCVRrqxPntuia8CBWP55rFs6TYx2Bnhx9TrpBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc037f0ec8f67dd05fb0628e9cbff632517935b1c2b2ca77a1b319fb33d52214","last_reissued_at":"2026-07-02T01:18:23.778157Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:23.778157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Post-Training Pruning for Diffusion Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chengzhi Hu, Jing Zhang, Mengjuan Chen, Qingyi Gu, Xuewen Liu, Zhikai Li","submitted_at":"2026-07-01T13:30:49Z","abstract_excerpt":"Diffusion Transformers (DiTs) have demonstrated impressive performance in image generation but suffer from substantial computational overhead and resource consumption. Post-training pruning offers a promising solution; however, due to DiTs' unique architectural design and parameter distribution, traditional pruning methods are inapplicable, leading to significant performance degradation. Specifically, prior methods developed for LLMs, which derive metrics through a series of approximations, amplify the relative contribution of weights in the saliency metric. In addition, weights in DiTs exhibi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00927","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/2607.00927/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":"2607.00927","created_at":"2026-07-02T01:18:23.778220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00927v1","created_at":"2026-07-02T01:18:23.778220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00927","created_at":"2026-07-02T01:18:23.778220+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQBX6DWI6Z65","created_at":"2026-07-02T01:18:23.778220+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQBX6DWI6Z65AX5Q","created_at":"2026-07-02T01:18:23.778220+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQBX6DWI","created_at":"2026-07-02T01:18:23.778220+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/ZQBX6DWI6Z65AX5QMKHJZP7WGJ","json":"https://pith.science/pith/ZQBX6DWI6Z65AX5QMKHJZP7WGJ.json","graph_json":"https://pith.science/api/pith-number/ZQBX6DWI6Z65AX5QMKHJZP7WGJ/graph.json","events_json":"https://pith.science/api/pith-number/ZQBX6DWI6Z65AX5QMKHJZP7WGJ/events.json","paper":"https://pith.science/paper/ZQBX6DWI"},"agent_actions":{"view_html":"https://pith.science/pith/ZQBX6DWI6Z65AX5QMKHJZP7WGJ","download_json":"https://pith.science/pith/ZQBX6DWI6Z65AX5QMKHJZP7WGJ.json","view_paper":"https://pith.science/paper/ZQBX6DWI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00927&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQBX6DWI6Z65AX5QMKHJZP7WGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQBX6DWI6Z65AX5QMKHJZP7WGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQBX6DWI6Z65AX5QMKHJZP7WGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQBX6DWI6Z65AX5QMKHJZP7WGJ/action/storage_attestation","attest_author":"https://pith.science/pith/ZQBX6DWI6Z65AX5QMKHJZP7WGJ/action/author_attestation","sign_citation":"https://pith.science/pith/ZQBX6DWI6Z65AX5QMKHJZP7WGJ/action/citation_signature","submit_replication":"https://pith.science/pith/ZQBX6DWI6Z65AX5QMKHJZP7WGJ/action/replication_record"}},"created_at":"2026-07-02T01:18:23.778220+00:00","updated_at":"2026-07-02T01:18:23.778220+00:00"}