{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4AKNMW6AJ7ECRXMDK5XZKWFDDL","short_pith_number":"pith:4AKNMW6A","canonical_record":{"source":{"id":"2410.21759","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T05:50:17Z","cross_cats_sorted":[],"title_canon_sha256":"4a3d2a37637e4245ba42f626e3d8aa330ad09a62485764cd1f6b29fe12b6334b","abstract_canon_sha256":"58099b683ac2ecc467a91eea35875fb598cb827153ffc86741dd7c807bff27b0"},"schema_version":"1.0"},"canonical_sha256":"e014d65bc04fc828dd83576f9558a31afd11e99d4f6c22f7207503dcd303b8e9","source":{"kind":"arxiv","id":"2410.21759","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21759","created_at":"2026-07-05T11:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21759v3","created_at":"2026-07-05T11:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21759","created_at":"2026-07-05T11:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"4AKNMW6AJ7EC","created_at":"2026-07-05T11:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"4AKNMW6AJ7ECRXMD","created_at":"2026-07-05T11:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"4AKNMW6A","created_at":"2026-07-05T11:04:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4AKNMW6AJ7ECRXMDK5XZKWFDDL","target":"record","payload":{"canonical_record":{"source":{"id":"2410.21759","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T05:50:17Z","cross_cats_sorted":[],"title_canon_sha256":"4a3d2a37637e4245ba42f626e3d8aa330ad09a62485764cd1f6b29fe12b6334b","abstract_canon_sha256":"58099b683ac2ecc467a91eea35875fb598cb827153ffc86741dd7c807bff27b0"},"schema_version":"1.0"},"canonical_sha256":"e014d65bc04fc828dd83576f9558a31afd11e99d4f6c22f7207503dcd303b8e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:41.375335Z","signature_b64":"RIZRZYWHyuOpwbocJIgvsGH99TihvoBiJzOPdwALFSoqphmZ1SZI423HSXj9vw/VUCrn2o5F4GVkEe1jvju2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e014d65bc04fc828dd83576f9558a31afd11e99d4f6c22f7207503dcd303b8e9","last_reissued_at":"2026-07-05T11:04:41.374735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:41.374735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.21759","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:04:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6gNbVQ/jOz7o407rJDgLfCS14sRJNna0zjspD6ebPOTYENzd5ceC6wo2fpJwdQxx677cG3OotX4I3TxaU8fUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:38:00.866210Z"},"content_sha256":"bfdeef563005536787f02f340265888529630eb680813172b758fd036d5a88a0","schema_version":"1.0","event_id":"sha256:bfdeef563005536787f02f340265888529630eb680813172b758fd036d5a88a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4AKNMW6AJ7ECRXMDK5XZKWFDDL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Guo, Luca Benini, Shu-Tao Xia, Tao Dai, Yawei Li","submitted_at":"2024-10-29T05:50:17Z","abstract_excerpt":"Fine-tuning pre-trained diffusion models under limited budgets has gained great success. In particular, the recent advances that directly fine-tune the quantized weights using Low-rank Adaptation (LoRA) further reduces training costs. Despite these progress, we point out that existing adaptation recipes are not inference-efficient. Specifically, additional post-training quantization (PTQ) on tuned weights is needed during deployment, which results in noticeable performance drop when the bit-width is low. Based on this observation, we introduce IntLoRA, which adapts quantized diffusion models w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21759","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/2410.21759/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":"2026-07-05T11:04:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LyO6tpp0+6lYOpcprnp6r6idrjst1tMQmr+bo5NjOLh009p6XWs4WYN/5kmG2R+Maax7u6pxqWHnRYlLHa6ODA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:38:00.866839Z"},"content_sha256":"8efe9bca6128f7521ed1883d83b4ac8a3774ea2a4e3b2c00a62f38f0754bd47c","schema_version":"1.0","event_id":"sha256:8efe9bca6128f7521ed1883d83b4ac8a3774ea2a4e3b2c00a62f38f0754bd47c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4AKNMW6AJ7ECRXMDK5XZKWFDDL/bundle.json","state_url":"https://pith.science/pith/4AKNMW6AJ7ECRXMDK5XZKWFDDL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4AKNMW6AJ7ECRXMDK5XZKWFDDL/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":"2026-08-21T21:38:00Z","links":{"resolver":"https://pith.science/pith/4AKNMW6AJ7ECRXMDK5XZKWFDDL","bundle":"https://pith.science/pith/4AKNMW6AJ7ECRXMDK5XZKWFDDL/bundle.json","state":"https://pith.science/pith/4AKNMW6AJ7ECRXMDK5XZKWFDDL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4AKNMW6AJ7ECRXMDK5XZKWFDDL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4AKNMW6AJ7ECRXMDK5XZKWFDDL","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":"58099b683ac2ecc467a91eea35875fb598cb827153ffc86741dd7c807bff27b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T05:50:17Z","title_canon_sha256":"4a3d2a37637e4245ba42f626e3d8aa330ad09a62485764cd1f6b29fe12b6334b"},"schema_version":"1.0","source":{"id":"2410.21759","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21759","created_at":"2026-07-05T11:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21759v3","created_at":"2026-07-05T11:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21759","created_at":"2026-07-05T11:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"4AKNMW6AJ7EC","created_at":"2026-07-05T11:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"4AKNMW6AJ7ECRXMD","created_at":"2026-07-05T11:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"4AKNMW6A","created_at":"2026-07-05T11:04:41Z"}],"graph_snapshots":[{"event_id":"sha256:8efe9bca6128f7521ed1883d83b4ac8a3774ea2a4e3b2c00a62f38f0754bd47c","target":"graph","created_at":"2026-07-05T11:04:41Z","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/2410.21759/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning pre-trained diffusion models under limited budgets has gained great success. In particular, the recent advances that directly fine-tune the quantized weights using Low-rank Adaptation (LoRA) further reduces training costs. Despite these progress, we point out that existing adaptation recipes are not inference-efficient. Specifically, additional post-training quantization (PTQ) on tuned weights is needed during deployment, which results in noticeable performance drop when the bit-width is low. Based on this observation, we introduce IntLoRA, which adapts quantized diffusion models w","authors_text":"Hang Guo, Luca Benini, Shu-Tao Xia, Tao Dai, Yawei Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T05:50:17Z","title":"IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21759","kind":"arxiv","version":3},"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:bfdeef563005536787f02f340265888529630eb680813172b758fd036d5a88a0","target":"record","created_at":"2026-07-05T11:04:41Z","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":"58099b683ac2ecc467a91eea35875fb598cb827153ffc86741dd7c807bff27b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T05:50:17Z","title_canon_sha256":"4a3d2a37637e4245ba42f626e3d8aa330ad09a62485764cd1f6b29fe12b6334b"},"schema_version":"1.0","source":{"id":"2410.21759","kind":"arxiv","version":3}},"canonical_sha256":"e014d65bc04fc828dd83576f9558a31afd11e99d4f6c22f7207503dcd303b8e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e014d65bc04fc828dd83576f9558a31afd11e99d4f6c22f7207503dcd303b8e9","first_computed_at":"2026-07-05T11:04:41.374735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:41.374735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RIZRZYWHyuOpwbocJIgvsGH99TihvoBiJzOPdwALFSoqphmZ1SZI423HSXj9vw/VUCrn2o5F4GVkEe1jvju2Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:41.375335Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.21759","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfdeef563005536787f02f340265888529630eb680813172b758fd036d5a88a0","sha256:8efe9bca6128f7521ed1883d83b4ac8a3774ea2a4e3b2c00a62f38f0754bd47c"],"state_sha256":"e5b5d6a85ddc6f6d0dc1ecf39b6b66146513b27ea1b69a487a187adec0bffaf4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sO6mlWt7+uloZwwhSZkjAwXFWnLld66Dksi66fXhtfCBfiR5l7N38Z7oglHr2L0uOLyn3jQqpDt3BmWhp/exCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T21:38:00.872249Z","bundle_sha256":"3a0dcf827bfd1fe716cd10d1f7db2216ac96b00786dcecbae3b570f95e7f6c80"}}