{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3HE47GK55SEXOUKFRQT5D53FHA","short_pith_number":"pith:3HE47GK5","canonical_record":{"source":{"id":"2501.18427","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-30T15:31:48Z","cross_cats_sorted":[],"title_canon_sha256":"845838c65c0172ce2eac4b748e23678622d659bb2caaf35f887c9c0c90f5c16c","abstract_canon_sha256":"791871af1d6b2cfbd7ef251f7ec17d0d33a7bed7e9efb3f5864a9fb436a449d2"},"schema_version":"1.0"},"canonical_sha256":"d9c9cf995dec897751458c27d1f765381b103472802ad584455c6e5f211eea0d","source":{"kind":"arxiv","id":"2501.18427","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18427","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18427v4","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18427","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"3HE47GK55SEX","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"3HE47GK55SEXOUKF","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"3HE47GK5","created_at":"2026-07-05T11:04:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3HE47GK55SEXOUKFRQT5D53FHA","target":"record","payload":{"canonical_record":{"source":{"id":"2501.18427","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-30T15:31:48Z","cross_cats_sorted":[],"title_canon_sha256":"845838c65c0172ce2eac4b748e23678622d659bb2caaf35f887c9c0c90f5c16c","abstract_canon_sha256":"791871af1d6b2cfbd7ef251f7ec17d0d33a7bed7e9efb3f5864a9fb436a449d2"},"schema_version":"1.0"},"canonical_sha256":"d9c9cf995dec897751458c27d1f765381b103472802ad584455c6e5f211eea0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:44.685910Z","signature_b64":"MkWP8wGQjAl04U98aFySFFznQPI3DmMZTMbzeCE//k1LMK75DdVDqz3/ikZr6Icv4NYQDr3JY3+POGwaqddJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9c9cf995dec897751458c27d1f765381b103472802ad584455c6e5f211eea0d","last_reissued_at":"2026-07-05T11:04:44.685363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:44.685363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.18427","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4+QQLhcnW8MhM5jlM0347bQ+Pn3RMkazJ4Gr0j1qyibN7BgfHx4bq5nVbjNZ98sUBmKORPsZgxC/lTuGjDPGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:27:31.626627Z"},"content_sha256":"905b26024a566a22e0a3403768dd332da5b0002795f49bbe91118b0df9dc10ac","schema_version":"1.0","event_id":"sha256:905b26024a566a22e0a3403768dd332da5b0002795f49bbe91118b0df9dc10ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3HE47GK55SEXOUKFRQT5D53FHA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingchen Liu, Chengyue Wu, Daquan Zhou, Enze Xie, Han Cai, Jincheng Yu, Junsong Chen, Junyu Chen, Ligeng Zhu, Muyang Li, Song Han, Yujun Lin, Yuyang Zhao, Zhekai Zhang","submitted_at":"2025-01-30T15:31:48Z","abstract_excerpt":"This paper presents SANA-1.5, a linear Diffusion Transformer for efficient scaling in text-to-image generation. Building upon SANA-1.0, we introduce three key innovations: (1) Efficient Training Scaling: A depth-growth paradigm that enables scaling from 1.6B to 4.8B parameters with significantly reduced computational resources, combined with a memory-efficient 8-bit optimizer. (2) Model Depth Pruning: A block importance analysis technique for efficient model compression to arbitrary sizes with minimal quality loss. (3) Inference-time Scaling: A repeated sampling strategy that trades computatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18427","kind":"arxiv","version":4},"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/2501.18427/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8A+7zpKspXvCPHZeMjfZvS9WWlyILDpd+0LSOgr+OLhyyokj6ZaaSMnxlS+ffkYhJ44/n8NCEt3QvfxTn4KyBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:27:31.626996Z"},"content_sha256":"bc893791db4135e10734704d3b83ffd23c8497c63054d170168282c950b5ef9c","schema_version":"1.0","event_id":"sha256:bc893791db4135e10734704d3b83ffd23c8497c63054d170168282c950b5ef9c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3HE47GK55SEXOUKFRQT5D53FHA/bundle.json","state_url":"https://pith.science/pith/3HE47GK55SEXOUKFRQT5D53FHA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3HE47GK55SEXOUKFRQT5D53FHA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T10:27:31Z","links":{"resolver":"https://pith.science/pith/3HE47GK55SEXOUKFRQT5D53FHA","bundle":"https://pith.science/pith/3HE47GK55SEXOUKFRQT5D53FHA/bundle.json","state":"https://pith.science/pith/3HE47GK55SEXOUKFRQT5D53FHA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3HE47GK55SEXOUKFRQT5D53FHA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3HE47GK55SEXOUKFRQT5D53FHA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"791871af1d6b2cfbd7ef251f7ec17d0d33a7bed7e9efb3f5864a9fb436a449d2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-30T15:31:48Z","title_canon_sha256":"845838c65c0172ce2eac4b748e23678622d659bb2caaf35f887c9c0c90f5c16c"},"schema_version":"1.0","source":{"id":"2501.18427","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18427","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18427v4","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18427","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"3HE47GK55SEX","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"3HE47GK55SEXOUKF","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"3HE47GK5","created_at":"2026-07-05T11:04:44Z"}],"graph_snapshots":[{"event_id":"sha256:bc893791db4135e10734704d3b83ffd23c8497c63054d170168282c950b5ef9c","target":"graph","created_at":"2026-07-05T11:04:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.18427/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents SANA-1.5, a linear Diffusion Transformer for efficient scaling in text-to-image generation. Building upon SANA-1.0, we introduce three key innovations: (1) Efficient Training Scaling: A depth-growth paradigm that enables scaling from 1.6B to 4.8B parameters with significantly reduced computational resources, combined with a memory-efficient 8-bit optimizer. (2) Model Depth Pruning: A block importance analysis technique for efficient model compression to arbitrary sizes with minimal quality loss. (3) Inference-time Scaling: A repeated sampling strategy that trades computatio","authors_text":"Bingchen Liu, Chengyue Wu, Daquan Zhou, Enze Xie, Han Cai, Jincheng Yu, Junsong Chen, Junyu Chen, Ligeng Zhu, Muyang Li, Song Han, Yujun Lin, Yuyang Zhao, Zhekai Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-30T15:31:48Z","title":"SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18427","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:905b26024a566a22e0a3403768dd332da5b0002795f49bbe91118b0df9dc10ac","target":"record","created_at":"2026-07-05T11:04:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"791871af1d6b2cfbd7ef251f7ec17d0d33a7bed7e9efb3f5864a9fb436a449d2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-30T15:31:48Z","title_canon_sha256":"845838c65c0172ce2eac4b748e23678622d659bb2caaf35f887c9c0c90f5c16c"},"schema_version":"1.0","source":{"id":"2501.18427","kind":"arxiv","version":4}},"canonical_sha256":"d9c9cf995dec897751458c27d1f765381b103472802ad584455c6e5f211eea0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9c9cf995dec897751458c27d1f765381b103472802ad584455c6e5f211eea0d","first_computed_at":"2026-07-05T11:04:44.685363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:44.685363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MkWP8wGQjAl04U98aFySFFznQPI3DmMZTMbzeCE//k1LMK75DdVDqz3/ikZr6Icv4NYQDr3JY3+POGwaqddJBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:44.685910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18427","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:905b26024a566a22e0a3403768dd332da5b0002795f49bbe91118b0df9dc10ac","sha256:bc893791db4135e10734704d3b83ffd23c8497c63054d170168282c950b5ef9c"],"state_sha256":"1ac21f3a880b731073235b72e6763ae3b32858142b665ed075bdce8769862f61"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v7CmkHKglW/lx64+pRI7YfZjUF6KBOBPE/SZ545o6zoLLB7NTBbxYJVeZJCQr0t40FMjyEjJ5eoR6MH9SXESBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:27:31.628887Z","bundle_sha256":"e4c806cb25274e4456156179db41b6c0b1117954c09e4bf436842ed7ae587911"}}