{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IC2F5YFNXK4X3FHKV24VFSNURV","short_pith_number":"pith:IC2F5YFN","canonical_record":{"source":{"id":"2506.04244","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-29T20:37:04Z","cross_cats_sorted":[],"title_canon_sha256":"e0f96ec274542ff1aad74ccb5ae5b9e5ae93eec7b83926cfcd3d71d159f2bf11","abstract_canon_sha256":"12dc1f146d8a32336a666dbbf03a98aac49099bbd3da94ed70106498d1ba0cb4"},"schema_version":"1.0"},"canonical_sha256":"40b45ee0adbab97d94eaaeb952c9b48d6bfb074aef890ff3475ce6e10b30650b","source":{"kind":"arxiv","id":"2506.04244","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04244","created_at":"2026-07-05T11:16:10Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04244v1","created_at":"2026-07-05T11:16:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04244","created_at":"2026-07-05T11:16:10Z"},{"alias_kind":"pith_short_12","alias_value":"IC2F5YFNXK4X","created_at":"2026-07-05T11:16:10Z"},{"alias_kind":"pith_short_16","alias_value":"IC2F5YFNXK4X3FHK","created_at":"2026-07-05T11:16:10Z"},{"alias_kind":"pith_short_8","alias_value":"IC2F5YFN","created_at":"2026-07-05T11:16:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IC2F5YFNXK4X3FHKV24VFSNURV","target":"record","payload":{"canonical_record":{"source":{"id":"2506.04244","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-29T20:37:04Z","cross_cats_sorted":[],"title_canon_sha256":"e0f96ec274542ff1aad74ccb5ae5b9e5ae93eec7b83926cfcd3d71d159f2bf11","abstract_canon_sha256":"12dc1f146d8a32336a666dbbf03a98aac49099bbd3da94ed70106498d1ba0cb4"},"schema_version":"1.0"},"canonical_sha256":"40b45ee0adbab97d94eaaeb952c9b48d6bfb074aef890ff3475ce6e10b30650b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:10.982155Z","signature_b64":"QxRtThFZOCjLLeUrHu9hLxhznElJOy4v/VfZdvvrnzbTS2HmRE64Bw/3i7DDFUAiio6CmNj26ODB1O3g9fTaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40b45ee0adbab97d94eaaeb952c9b48d6bfb074aef890ff3475ce6e10b30650b","last_reissued_at":"2026-07-05T11:16:10.981585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:10.981585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.04244","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":"2026-07-05T11:16:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2cPHLBYagIvj0/xT2/n9VV9KSBpbV7u55pYofTkxZghxrEb4Cqg1l/xdEi0iLwiOS+TxQzilmJveOkfqqGEhBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:43:21.658809Z"},"content_sha256":"fea6c6f85925f18bd56f13d995c2412e9a1369fedd458276c147430d91a8ffd7","schema_version":"1.0","event_id":"sha256:fea6c6f85925f18bd56f13d995c2412e9a1369fedd458276c147430d91a8ffd7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IC2F5YFNXK4X3FHKV24VFSNURV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Debasmit Das, Farzad Farhadzadeh, Fatih Porikli, Shubhankar Borse","submitted_at":"2025-05-29T20:37:04Z","abstract_excerpt":"We introduce ProLoRA, enabling zero-shot adaptation of parameter-efficient fine-tuning in text-to-image diffusion models. ProLoRA transfers pre-trained low-rank adjustments (e.g., LoRA) from a source to a target model without additional training data. This overcomes the limitations of traditional methods that require retraining when switching base models, often challenging due to data constraints. ProLoRA achieves this via projection of source adjustments into the target model's weight space, leveraging subspace and null space similarities and selectively targeting aligned layers. Evaluations "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04244","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/2506.04244/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":"2026-07-05T11:16:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/3BOFY6UTNOS1qelKChhj74yHGD26XsupS8Gw/TKAamYYqqDeft6q2FJvuZq/PBqJlwL6XI8QIkzEcXEQYI3Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:43:21.659166Z"},"content_sha256":"2e623150f8c815e20ce0c4cb1a42b62b5b07045b4da730a099dfe5db920682c6","schema_version":"1.0","event_id":"sha256:2e623150f8c815e20ce0c4cb1a42b62b5b07045b4da730a099dfe5db920682c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IC2F5YFNXK4X3FHKV24VFSNURV/bundle.json","state_url":"https://pith.science/pith/IC2F5YFNXK4X3FHKV24VFSNURV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IC2F5YFNXK4X3FHKV24VFSNURV/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":"2026-07-07T14:43:21Z","links":{"resolver":"https://pith.science/pith/IC2F5YFNXK4X3FHKV24VFSNURV","bundle":"https://pith.science/pith/IC2F5YFNXK4X3FHKV24VFSNURV/bundle.json","state":"https://pith.science/pith/IC2F5YFNXK4X3FHKV24VFSNURV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IC2F5YFNXK4X3FHKV24VFSNURV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IC2F5YFNXK4X3FHKV24VFSNURV","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":"12dc1f146d8a32336a666dbbf03a98aac49099bbd3da94ed70106498d1ba0cb4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-29T20:37:04Z","title_canon_sha256":"e0f96ec274542ff1aad74ccb5ae5b9e5ae93eec7b83926cfcd3d71d159f2bf11"},"schema_version":"1.0","source":{"id":"2506.04244","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04244","created_at":"2026-07-05T11:16:10Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04244v1","created_at":"2026-07-05T11:16:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04244","created_at":"2026-07-05T11:16:10Z"},{"alias_kind":"pith_short_12","alias_value":"IC2F5YFNXK4X","created_at":"2026-07-05T11:16:10Z"},{"alias_kind":"pith_short_16","alias_value":"IC2F5YFNXK4X3FHK","created_at":"2026-07-05T11:16:10Z"},{"alias_kind":"pith_short_8","alias_value":"IC2F5YFN","created_at":"2026-07-05T11:16:10Z"}],"graph_snapshots":[{"event_id":"sha256:2e623150f8c815e20ce0c4cb1a42b62b5b07045b4da730a099dfe5db920682c6","target":"graph","created_at":"2026-07-05T11:16:10Z","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/2506.04244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce ProLoRA, enabling zero-shot adaptation of parameter-efficient fine-tuning in text-to-image diffusion models. ProLoRA transfers pre-trained low-rank adjustments (e.g., LoRA) from a source to a target model without additional training data. This overcomes the limitations of traditional methods that require retraining when switching base models, often challenging due to data constraints. ProLoRA achieves this via projection of source adjustments into the target model's weight space, leveraging subspace and null space similarities and selectively targeting aligned layers. Evaluations ","authors_text":"Debasmit Das, Farzad Farhadzadeh, Fatih Porikli, Shubhankar Borse","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-29T20:37:04Z","title":"Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04244","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:fea6c6f85925f18bd56f13d995c2412e9a1369fedd458276c147430d91a8ffd7","target":"record","created_at":"2026-07-05T11:16:10Z","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":"12dc1f146d8a32336a666dbbf03a98aac49099bbd3da94ed70106498d1ba0cb4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-29T20:37:04Z","title_canon_sha256":"e0f96ec274542ff1aad74ccb5ae5b9e5ae93eec7b83926cfcd3d71d159f2bf11"},"schema_version":"1.0","source":{"id":"2506.04244","kind":"arxiv","version":1}},"canonical_sha256":"40b45ee0adbab97d94eaaeb952c9b48d6bfb074aef890ff3475ce6e10b30650b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40b45ee0adbab97d94eaaeb952c9b48d6bfb074aef890ff3475ce6e10b30650b","first_computed_at":"2026-07-05T11:16:10.981585Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:10.981585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QxRtThFZOCjLLeUrHu9hLxhznElJOy4v/VfZdvvrnzbTS2HmRE64Bw/3i7DDFUAiio6CmNj26ODB1O3g9fTaDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:10.982155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04244","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fea6c6f85925f18bd56f13d995c2412e9a1369fedd458276c147430d91a8ffd7","sha256:2e623150f8c815e20ce0c4cb1a42b62b5b07045b4da730a099dfe5db920682c6"],"state_sha256":"e83194f3f91fd07afa8f9312fa04708e066f6d7481bb7d89381e8b194db2212d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ougEUAnYFGdZB1JCA+AET4dRRupVs7tVQBb0cWdgtm/NSfN8w+wx0RxQiJlkfqN29upkG/1fPY2nzWXM8MLsCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:43:21.661084Z","bundle_sha256":"f4ac1904fcafe6cacf4ad0a9b6bcb887a4a08013e6f52bfab925db7033f38aac"}}