{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:O37JTEOEJYZQVDW25N7VUXU3AQ","short_pith_number":"pith:O37JTEOE","canonical_record":{"source":{"id":"2405.21050","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T17:43:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6acef06025e6beced06eabca0e5b9ce0ef61db056fb244d32aa03d6a5e0db6dd","abstract_canon_sha256":"b1682337f79d922c4826d5dd0080bd38a31149bb3f13a3e2711124f29b05ce10"},"schema_version":"1.0"},"canonical_sha256":"76fe9991c44e330a8edaeb7f5a5e9b04072761ca21b3814bcb4015498cb8c9cf","source":{"kind":"arxiv","id":"2405.21050","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.21050","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"arxiv_version","alias_value":"2405.21050v1","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.21050","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"pith_short_12","alias_value":"O37JTEOEJYZQ","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"pith_short_16","alias_value":"O37JTEOEJYZQVDW2","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"pith_short_8","alias_value":"O37JTEOE","created_at":"2026-07-05T08:25:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:O37JTEOEJYZQVDW25N7VUXU3AQ","target":"record","payload":{"canonical_record":{"source":{"id":"2405.21050","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T17:43:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6acef06025e6beced06eabca0e5b9ce0ef61db056fb244d32aa03d6a5e0db6dd","abstract_canon_sha256":"b1682337f79d922c4826d5dd0080bd38a31149bb3f13a3e2711124f29b05ce10"},"schema_version":"1.0"},"canonical_sha256":"76fe9991c44e330a8edaeb7f5a5e9b04072761ca21b3814bcb4015498cb8c9cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:45.393952Z","signature_b64":"56GCx3Yu4E41j6rhF9CLsOqRXsf+yCdljKzZwz3B6YXJW1ygy4vU935JY1azNDj4nMNKAf6gbJny1YgI9wBHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76fe9991c44e330a8edaeb7f5a5e9b04072761ca21b3814bcb4015498cb8c9cf","last_reissued_at":"2026-07-05T08:25:45.393491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:45.393491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.21050","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:25:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/yk40/1QqXOOw99AXjYpBz4fuon2d6+ubIh+zIgygAOD+a4p/QwXbhMbekhkz6N0zAtjDObf+iY0YBGSHyoSAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T17:41:03.416170Z"},"content_sha256":"a78987031217123f8df6e0f9a0466c92c754643e77da9c5bbedd7bcd83725f3a","schema_version":"1.0","event_id":"sha256:a78987031217123f8df6e0f9a0466c92c754643e77da9c5bbedd7bcd83725f3a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:O37JTEOEJYZQVDW25N7VUXU3AQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Akash Srivastava, Dimitris N. Metaxas, Felix Juefei-Xu, Hao Wang, Junzhou Huang, Ligong Han, Molei Tao, Song Wen, Xinxi Zhang","submitted_at":"2024-05-31T17:43:35Z","abstract_excerpt":"Adapting large-scale pre-trained generative models in a parameter-efficient manner is gaining traction. Traditional methods like low rank adaptation achieve parameter efficiency by imposing constraints but may not be optimal for tasks requiring high representation capacity. We propose a novel spectrum-aware adaptation framework for generative models. Our method adjusts both singular values and their basis vectors of pretrained weights. Using the Kronecker product and efficient Stiefel optimizers, we achieve parameter-efficient adaptation of orthogonal matrices. We introduce Spectral Orthogonal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.21050","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/2405.21050/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":"2026-07-05T08:25:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DV8iNNB2Rt0cwDtOYUXg8zD7+lAylBVG1y18n60SN1TYOUb6Hc+wXQrpv6TSuzMDtH3i5xrfyqPG3cJ2y2w+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T17:41:03.416884Z"},"content_sha256":"4cc67b2d1a4902a4fef15f0a6be6c885429c337a7d615a378ea9328cb666efb8","schema_version":"1.0","event_id":"sha256:4cc67b2d1a4902a4fef15f0a6be6c885429c337a7d615a378ea9328cb666efb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O37JTEOEJYZQVDW25N7VUXU3AQ/bundle.json","state_url":"https://pith.science/pith/O37JTEOEJYZQVDW25N7VUXU3AQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O37JTEOEJYZQVDW25N7VUXU3AQ/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":"2026-08-17T17:41:03Z","links":{"resolver":"https://pith.science/pith/O37JTEOEJYZQVDW25N7VUXU3AQ","bundle":"https://pith.science/pith/O37JTEOEJYZQVDW25N7VUXU3AQ/bundle.json","state":"https://pith.science/pith/O37JTEOEJYZQVDW25N7VUXU3AQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O37JTEOEJYZQVDW25N7VUXU3AQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O37JTEOEJYZQVDW25N7VUXU3AQ","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":"b1682337f79d922c4826d5dd0080bd38a31149bb3f13a3e2711124f29b05ce10","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T17:43:35Z","title_canon_sha256":"6acef06025e6beced06eabca0e5b9ce0ef61db056fb244d32aa03d6a5e0db6dd"},"schema_version":"1.0","source":{"id":"2405.21050","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.21050","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"arxiv_version","alias_value":"2405.21050v1","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.21050","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"pith_short_12","alias_value":"O37JTEOEJYZQ","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"pith_short_16","alias_value":"O37JTEOEJYZQVDW2","created_at":"2026-07-05T08:25:45Z"},{"alias_kind":"pith_short_8","alias_value":"O37JTEOE","created_at":"2026-07-05T08:25:45Z"}],"graph_snapshots":[{"event_id":"sha256:4cc67b2d1a4902a4fef15f0a6be6c885429c337a7d615a378ea9328cb666efb8","target":"graph","created_at":"2026-07-05T08:25:45Z","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/2405.21050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adapting large-scale pre-trained generative models in a parameter-efficient manner is gaining traction. Traditional methods like low rank adaptation achieve parameter efficiency by imposing constraints but may not be optimal for tasks requiring high representation capacity. We propose a novel spectrum-aware adaptation framework for generative models. Our method adjusts both singular values and their basis vectors of pretrained weights. Using the Kronecker product and efficient Stiefel optimizers, we achieve parameter-efficient adaptation of orthogonal matrices. We introduce Spectral Orthogonal","authors_text":"Akash Srivastava, Dimitris N. Metaxas, Felix Juefei-Xu, Hao Wang, Junzhou Huang, Ligong Han, Molei Tao, Song Wen, Xinxi Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T17:43:35Z","title":"Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.21050","kind":"arxiv","version":1},"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:a78987031217123f8df6e0f9a0466c92c754643e77da9c5bbedd7bcd83725f3a","target":"record","created_at":"2026-07-05T08:25:45Z","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":"b1682337f79d922c4826d5dd0080bd38a31149bb3f13a3e2711124f29b05ce10","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T17:43:35Z","title_canon_sha256":"6acef06025e6beced06eabca0e5b9ce0ef61db056fb244d32aa03d6a5e0db6dd"},"schema_version":"1.0","source":{"id":"2405.21050","kind":"arxiv","version":1}},"canonical_sha256":"76fe9991c44e330a8edaeb7f5a5e9b04072761ca21b3814bcb4015498cb8c9cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76fe9991c44e330a8edaeb7f5a5e9b04072761ca21b3814bcb4015498cb8c9cf","first_computed_at":"2026-07-05T08:25:45.393491Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:45.393491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"56GCx3Yu4E41j6rhF9CLsOqRXsf+yCdljKzZwz3B6YXJW1ygy4vU935JY1azNDj4nMNKAf6gbJny1YgI9wBHBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:45.393952Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.21050","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a78987031217123f8df6e0f9a0466c92c754643e77da9c5bbedd7bcd83725f3a","sha256:4cc67b2d1a4902a4fef15f0a6be6c885429c337a7d615a378ea9328cb666efb8"],"state_sha256":"18ea582fba948d70bac61abc98893f0f1e569b3a6ce0edc9e682a4f48ef445c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IFJ7n1a8SZh5zRL908DzjiNjXOGKF+u69HhGXOn2WXojG03HFrxR1kVF270F04JrRF0aNRNWZL2+yZIeZ0NBBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T17:41:03.421715Z","bundle_sha256":"ad5364e9dd1b6061c93293ce031966489498da07d2f35bf6e132d6d8b176327a"}}