{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AAC2OAG6475S6UQUQVTDIFU4IT","short_pith_number":"pith:AAC2OAG6","schema_version":"1.0","canonical_sha256":"0005a700dee7fb2f5214856634169c44faef0adbbdf4ef13cdbd0055f6736d3b","source":{"kind":"arxiv","id":"2504.09606","version":1},"attestation_state":"computed","paper":{"title":"Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaojian Li, Haoran You, Lexington Whalen, Sixu Li, Yingyan (Celine) Lin, Zhenbang Du","submitted_at":"2025-04-13T14:53:18Z","abstract_excerpt":"Training diffusion models (DMs) requires substantial computational resources due to multiple forward and backward passes across numerous timesteps, motivating research into efficient training techniques. In this paper, we propose EB-Diff-Train, a new efficient DM training approach that is orthogonal to other methods of accelerating DM training, by investigating and leveraging Early-Bird (EB) tickets -- sparse subnetworks that manifest early in the training process and maintain high generation quality.\n  We first investigate the existence of traditional EB tickets in DMs, enabling competitive g"},"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":"2504.09606","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-13T14:53:18Z","cross_cats_sorted":[],"title_canon_sha256":"056be0fcb5b51412d28ec9a2981f1c95de1619901d320935339f951b4b2e0c5e","abstract_canon_sha256":"34726fb3b6450f1d9e55750c9bcf9d0b27d4ac66b02ff237827b1e348727a8fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:39.901801Z","signature_b64":"zSwtCvAT+df1Dre3f5IZ15gw00qJ4ZN3OkZyuph0lIu4IANOjQcp8yLx5wMYveiyU3nJ/qO723mzpAFrPaWfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0005a700dee7fb2f5214856634169c44faef0adbbdf4ef13cdbd0055f6736d3b","last_reissued_at":"2026-07-05T10:48:39.901321Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:39.901321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaojian Li, Haoran You, Lexington Whalen, Sixu Li, Yingyan (Celine) Lin, Zhenbang Du","submitted_at":"2025-04-13T14:53:18Z","abstract_excerpt":"Training diffusion models (DMs) requires substantial computational resources due to multiple forward and backward passes across numerous timesteps, motivating research into efficient training techniques. In this paper, we propose EB-Diff-Train, a new efficient DM training approach that is orthogonal to other methods of accelerating DM training, by investigating and leveraging Early-Bird (EB) tickets -- sparse subnetworks that manifest early in the training process and maintain high generation quality.\n  We first investigate the existence of traditional EB tickets in DMs, enabling competitive g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09606","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/2504.09606/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":"2504.09606","created_at":"2026-07-05T10:48:39.901380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.09606v1","created_at":"2026-07-05T10:48:39.901380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09606","created_at":"2026-07-05T10:48:39.901380+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAC2OAG6475S","created_at":"2026-07-05T10:48:39.901380+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAC2OAG6475S6UQU","created_at":"2026-07-05T10:48:39.901380+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAC2OAG6","created_at":"2026-07-05T10:48:39.901380+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03057","citing_title":"TASQ: Temporal-Adaptive Bit Sparsification Quantization for Diffusion Models","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AAC2OAG6475S6UQUQVTDIFU4IT","json":"https://pith.science/pith/AAC2OAG6475S6UQUQVTDIFU4IT.json","graph_json":"https://pith.science/api/pith-number/AAC2OAG6475S6UQUQVTDIFU4IT/graph.json","events_json":"https://pith.science/api/pith-number/AAC2OAG6475S6UQUQVTDIFU4IT/events.json","paper":"https://pith.science/paper/AAC2OAG6"},"agent_actions":{"view_html":"https://pith.science/pith/AAC2OAG6475S6UQUQVTDIFU4IT","download_json":"https://pith.science/pith/AAC2OAG6475S6UQUQVTDIFU4IT.json","view_paper":"https://pith.science/paper/AAC2OAG6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.09606&json=true","fetch_graph":"https://pith.science/api/pith-number/AAC2OAG6475S6UQUQVTDIFU4IT/graph.json","fetch_events":"https://pith.science/api/pith-number/AAC2OAG6475S6UQUQVTDIFU4IT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAC2OAG6475S6UQUQVTDIFU4IT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAC2OAG6475S6UQUQVTDIFU4IT/action/storage_attestation","attest_author":"https://pith.science/pith/AAC2OAG6475S6UQUQVTDIFU4IT/action/author_attestation","sign_citation":"https://pith.science/pith/AAC2OAG6475S6UQUQVTDIFU4IT/action/citation_signature","submit_replication":"https://pith.science/pith/AAC2OAG6475S6UQUQVTDIFU4IT/action/replication_record"}},"created_at":"2026-07-05T10:48:39.901380+00:00","updated_at":"2026-07-05T10:48:39.901380+00:00"}