{"as_of":"2026-08-15T21:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:907577faaa5011f581817b9e25a4d2b091b15ce55d844f9e9ae8709124633ead","coverage":[{"denominator":19,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":19,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:58:13.613771Z","state":"measured"},{"denominator":21,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":21,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T10:47:33.349484Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-02T02:36:27.263655Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"cited_work":{"arxiv_id":"2505.20525","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.20525","snapshot_observed_at":"2026-07-02T02:36:27.263655Z","title":"Multlfg: Training-free multi-lora composi- tion using frequency-domain guidance","venue":null,"work_id":"dc540c71-f4ac-4ba6-bf0e-5582cc906fa6","year":2025},"citing_paper":{"arxiv_id":"2605.08702","last_updated":"2026-05-09T05:32:28Z","snapshot_observed_at":"2026-08-15T05:00:30.894554Z","submitted_at":"2026-05-09T05:32:28Z","title":"Gate-and-Merge: Zero-shot Compositional Personalization of Vision Language Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-12T00:54:41.558704Z"},"links":{"cited_paper":"/paper/2505.20525","citing_paper":"/paper/2605.08702"},"observation_digest":"sha256:e03d40f3d3f3882a450204b48e2da9f0a9c92f26c04c98e390986d5280f827f8","observation_id":"2bdaaea1-8214-4a1d-a092-62c8ff200b4b","resolution":{"observed_at":"2026-05-12T00:56:14.286395Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"cited_work":{"arxiv_id":"2505.20525","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.20525","snapshot_observed_at":"2026-07-02T02:36:27.263655Z","title":"Multlfg: Training-free multi-lora composi- tion using frequency-domain guidance","venue":null,"work_id":"dc540c71-f4ac-4ba6-bf0e-5582cc906fa6","year":2025},"citing_paper":{"arxiv_id":"2606.03792","last_updated":"2026-06-02T15:42:09Z","snapshot_observed_at":"2026-07-06T23:44:00.144689Z","submitted_at":"2026-06-02T15:42:09Z","title":"Training-Free Multi-Concept LoRA Composition with Prompt-Aware Weighting","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-06-28T10:47:33.349484Z"},"links":{"cited_paper":"/paper/2505.20525","citing_paper":"/paper/2606.03792"},"observation_digest":"sha256:614359d5b4e8f49e347b317fbf4b4813e3f25b2db39599ea25a7d872f315ac34","observation_id":"2264771c-32c8-468f-989d-0b5ecb78293b","resolution":{"observed_at":"2026-07-02T02:36:27.265141Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.20525/citation-record","integrity":"/paper/2505.20525/integrity","json":"/paper/2505.20525/citation-record.json","paper":"/paper/2505.20525"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.02429","last_updated":"2024-09-04T04:16:58Z","snapshot_observed_at":"2026-08-14T02:19:49.332861Z","submitted_at":"2024-09-04T04:16:58Z","title":"Training-free Color-Style Disentanglement for Constrained Text-to-Image Synthesis","version":1},"cited_work":{"arxiv_id":"2409.02429","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.02429","snapshot_observed_at":"2026-08-07T13:58:14.205746Z","title":"Training-free Color-Style Disentanglement for Constrained Text-to-Image Synthesis","venue":"cs.CV","work_id":"cda824c6-42b7-4fd2-836e-12f0056dd0a3","year":2024},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:12.796291Z"},"links":{"cited_paper":"/paper/2409.02429","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:ddfac45f070eb0e04796e3572b87b5c4bbedc77045effb7e5d5f177dcb045844","observation_id":"25350f6f-4959-41bc-a2aa-8d5f9186ff70","resolution":{"observed_at":"2026-08-07T13:58:14.265793Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.05268","last_updated":"2024-11-30T11:55:19Z","snapshot_observed_at":"2026-08-13T19:39:02.324453Z","submitted_at":"2024-04-08T07:59:04Z","title":"MC$^2$: Multi-concept Guidance for Customized Multi-concept Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.05268","snapshot_observed_at":"2026-08-07T13:58:12.952590Z","title":"Mc2: Multi-concept guidance for customized multi-concept generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:12.952590Z"},"links":{"cited_paper":"/paper/2404.05268","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:745ec168fd0f07023213f343894eb1e4ec6ab2cafb2c9ba0a73d277520f19bad","observation_id":"6df6151d-d9ec-4657-bde7-f7e86339e980","resolution":{"observed_at":"2026-08-07T13:58:12.952590Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17741","last_updated":"2024-05-28T01:53:26Z","snapshot_observed_at":"2026-08-14T16:12:40.962989Z","submitted_at":"2024-05-28T01:53:26Z","title":"LoRA-Switch: Boosting the Efficiency of Dynamic LLM Adapters via System-Algorithm Co-design","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17741","snapshot_observed_at":"2026-08-07T13:58:13.005495Z","title":"Lora-switch: Boosting the efficiency of dynamic llm adapters via system-algorithm co-design","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:13.005495Z"},"links":{"cited_paper":"/paper/2405.17741","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:6c75f1cebd01be3c0f2703a0b21c499ac38a692a6fef75a40d4d3fa1114dd250","observation_id":"403c2286-9b25-4060-874c-6e42c92841e3","resolution":{"observed_at":"2026-08-07T13:58:13.005495Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.04488","last_updated":"2023-06-20T16:26:38Z","snapshot_observed_at":"2026-08-13T13:25:07.940727Z","submitted_at":"2022-12-08T18:57:02Z","title":"Multi-Concept Customization of Text-to-Image Diffusion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.04488","snapshot_observed_at":"2026-08-07T13:58:13.045285Z","title":"Multi-concept customization of text-to-image diffusion","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:13.045285Z"},"links":{"cited_paper":"/paper/2212.04488","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:d87959a26f14c3db3fc39ae4a5b84fd249c1c873c9153bc40dbf4dda97ab5599","observation_id":"cfe62043-2ed5-4fa3-a387-3ce1089e45c4","resolution":{"observed_at":"2026-08-07T13:58:13.045285Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.01952","last_updated":"2023-07-04T23:04:57Z","snapshot_observed_at":"2026-08-14T22:54:08.184266Z","submitted_at":"2023-07-04T23:04:57Z","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.01952","snapshot_observed_at":"2026-08-07T13:58:13.200551Z","title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:13.200551Z"},"links":{"cited_paper":"/paper/2307.01952","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:b7ea6269aad5e2485afb0631022d764d4893442542259989973a6b4e095782d2","observation_id":"427a9fa3-5894-4ca3-96c6-63001e2cf3dd","resolution":{"observed_at":"2026-08-07T13:58:13.200551Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.13025","last_updated":"2024-12-02T06:40:50Z","snapshot_observed_at":"2026-08-12T22:21:29.853385Z","submitted_at":"2024-10-16T20:33:06Z","title":"LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.13025","snapshot_observed_at":"2026-08-07T13:58:13.248948Z","title":"Lora soups: Merging loras for practical skill composition tasks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:13.248948Z"},"links":{"cited_paper":"/paper/2410.13025","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:d267959c507ac5a16d8294b1844f4e20dbaa6e642431f9ccf4a397c32caece69","observation_id":"3d0f9755-d00e-4f38-b738-e3135b3b0d6d","resolution":{"observed_at":"2026-08-07T13:58:13.248948Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.06125","last_updated":"2022-04-13T01:10:33Z","snapshot_observed_at":"2026-08-15T12:50:58.405488Z","submitted_at":"2022-04-13T01:10:33Z","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.06125","snapshot_observed_at":"2026-08-07T13:58:13.292443Z","title":"Hierarchical text- conditional image generation with clip latents","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:13.292443Z"},"links":{"cited_paper":"/paper/2204.06125","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:080f51554d339f583a1854b491d5b9a9be69a1c82c3421ca78356da05c0883b5","observation_id":"7ba1b1b6-52bf-4c74-a68e-e96f003efc02","resolution":{"observed_at":"2026-08-07T13:58:13.292443Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.13206","last_updated":"2025-04-15T23:39:28Z","snapshot_observed_at":"2026-08-11T14:46:22.504200Z","submitted_at":"2025-04-15T23:39:28Z","title":"DuoLoRA : Cycle-consistent and Rank-disentangled Content-Style Personalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.13206","snapshot_observed_at":"2026-08-07T13:58:13.344216Z","title":"Duolora: Cycle-consistent and rank-disentangled content-style personalization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:13.344216Z"},"links":{"cited_paper":"/paper/2504.13206","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:effc303352e96c9c6cc9bd8ca1288f83f63b3d1ce65cea45871efbc50967343d","observation_id":"6b7385e2-c515-4ab2-9b59-e7e136b17496","resolution":{"observed_at":"2026-08-07T13:58:13.344216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.13628","last_updated":"2024-04-21T11:59:53Z","snapshot_observed_at":"2026-08-13T00:25:17.233474Z","submitted_at":"2024-04-21T11:59:53Z","title":"Mixture of LoRA Experts","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.13628","snapshot_observed_at":"2026-08-07T13:58:13.402299Z","title":"Mixture of lora experts","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:13.402299Z"},"links":{"cited_paper":"/paper/2404.13628","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:1366ebae8b7aed7888c38863d191c24a49ea119b56f947dd98ead0280e50488e","observation_id":"5748e1b2-b35f-49d5-b34c-db97b78c8201","resolution":{"observed_at":"2026-08-07T13:58:13.402299Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.12450","last_updated":"2024-11-19T12:18:16Z","snapshot_observed_at":"2026-08-13T01:14:30.050750Z","submitted_at":"2024-11-19T12:18:16Z","title":"Frequency-Aware Guidance for Blind Image Restoration via Diffusion Models","version":1},"cited_work":{"arxiv_id":"2411.12450","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.12450","snapshot_observed_at":"2026-08-07T13:58:13.739988Z","title":"Frequency-Aware Guidance for Blind Image Restoration via Diffusion Models","venue":"cs.CV","work_id":"147e3fe0-090e-4b7b-972a-59b5f5c2a068","year":2024},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:13.432569Z"},"links":{"cited_paper":"/paper/2411.12450","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:b079250218e53c738bfc86ba7af07d306d2b14bff098e3278c75bb0cda999114","observation_id":"95b990a8-8071-4c28-99c5-ec02f2f805d3","resolution":{"observed_at":"2026-08-07T13:58:13.784254Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.16167","last_updated":"2024-10-22T02:29:22Z","snapshot_observed_at":"2026-08-15T18:48:26.099957Z","submitted_at":"2024-09-24T15:08:41Z","title":"Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.16167","snapshot_observed_at":"2026-08-07T13:58:13.487619Z","title":"Merging loras like playing lego: Pushing the modularity of lora to extremes through rank-wise clustering","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:13.487619Z"},"links":{"cited_paper":"/paper/2409.16167","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:ed638dd6a6404704b09dba422759aaddcc2f58c9d3991a2fa5d4a6ca62b6d5b8","observation_id":"7ccbf94a-4789-4bd1-bd15-7e40408827c1","resolution":{"observed_at":"2026-08-07T13:58:13.487619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16843","last_updated":"2024-11-19T02:52:45Z","snapshot_observed_at":"2026-08-13T04:09:46.973072Z","submitted_at":"2024-02-26T18:59:18Z","title":"Multi-LoRA Composition for Image Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16843","snapshot_observed_at":"2026-08-07T13:58:13.537847Z","title":"Multi-lora composition for image generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:13.537847Z"},"links":{"cited_paper":"/paper/2402.16843","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:0cb1934d28dda0c136d03f776e96295ff44d264f435577605155ef4f85985429","observation_id":"c4334150-4bf1-440d-bd6c-dc0fb0f6a2c4","resolution":{"observed_at":"2026-08-07T13:58:13.537847Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:58:14.335420Z","title":"Wdig: a wavelet domain image generation framework based on frequency domain optimization","venue":null,"work_id":"ec36ae2e-ddf1-4693-8e8b-5a598a7b4c53","year":2023},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:13.578948Z"},"links":{"citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:63fbeae5a9bd1bb33a1c4d4027c159836ba18edcb78695a0cdad90415027131f","observation_id":"06979acf-d391-420a-a868-d0b122542e73","resolution":{"observed_at":"2026-08-07T13:58:14.358325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.04923","last_updated":"2025-02-07T13:41:51Z","snapshot_observed_at":"2026-08-10T06:10:52.406971Z","submitted_at":"2025-02-07T13:41:51Z","title":"Cached Multi-Lora Composition for Multi-Concept Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.04923","snapshot_observed_at":"2026-08-07T13:58:13.613771Z","title":"Cached multi-lora composition for multi-concept image generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:13.613771Z"},"links":{"cited_paper":"/paper/2502.04923","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:1fd8600e592a6d3b8ca3e2f3ba2ce66dcf922838fcd3ed562397b618a0be34ea","observation_id":"88c57f29-b007-426b-8e32-74214e1b7a0f","resolution":{"observed_at":"2026-08-07T13:58:13.613771Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.10002","last_updated":"2025-04-14T09:04:14Z","snapshot_observed_at":"2026-08-15T06:33:18.741489Z","submitted_at":"2025-04-14T09:04:14Z","title":"FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions","version":1},"cited_work":{"arxiv_id":"2504.10002","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.10002","snapshot_observed_at":"2026-08-07T13:58:13.968846Z","title":"FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions","venue":"cs.RO","work_id":"c45e9720-0cff-4963-9943-d1f9c45e6ad0","year":2025},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":1989,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:13.095117Z"},"links":{"cited_paper":"/paper/2504.10002","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:61524175795ce6079ae3977bbe66b250965031360f42308d7a08ee487413f144","observation_id":"289f3308-50bf-4d25-8ee3-0def2b3baacf","resolution":{"observed_at":"2026-08-07T13:58:13.995177Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-08-14T14:11:39.416219Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-07T13:58:12.917042Z","title":"Lorahub: Efficient cross-task generalization via dynamic lora composition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:12.917042Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:85f455ba2e1f1f8df55e1d2cbaca8fde20a41ccb99096ceffc3e0f531d9e5d6e","observation_id":"056ee1f7-abd7-4fa1-be24-5029c697d236","resolution":{"observed_at":"2026-08-07T13:58:12.917042Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.15231","last_updated":"2025-04-15T01:42:54Z","snapshot_observed_at":"2026-08-15T05:04:07.726886Z","submitted_at":"2024-11-21T19:04:02Z","title":"IterIS: Iterative Inference-Solving Alignment for LoRA Merging","version":2},"cited_work":{"arxiv_id":"2411.15231","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.15231","snapshot_observed_at":"2026-08-07T13:58:14.120986Z","title":"IterIS: Iterative Inference-Solving Alignment for LoRA Merging","venue":"cs.LG","work_id":"61468e17-a2c3-482f-a29b-c197b3de0619","year":2024},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:12.870214Z"},"links":{"cited_paper":"/paper/2411.15231","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:4ccdd75e85edea2d6414b5a72e520adf3dfa4cdddf01c52db2b1533dbbbce329","observation_id":"7ca78a43-ba85-44c4-8af8-b0955798fad6","resolution":{"observed_at":"2026-08-07T13:58:14.154516Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.07967","last_updated":"2023-10-16T15:52:20Z","snapshot_observed_at":"2026-08-15T20:40:13.537997Z","submitted_at":"2023-06-13T17:59:32Z","title":"One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.07967","snapshot_observed_at":"2026-08-07T13:58:12.822411Z","title":"One-for-all: Generalized lora for parameter-efficient fine-tuning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:12.822411Z"},"links":{"cited_paper":"/paper/2306.07967","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:b449a70a3fa815924dea49f795e2fbf3ee47ad1f825c1378202b008f6b16783a","observation_id":"f4742288-30c0-4526-a16d-493fae376ceb","resolution":{"observed_at":"2026-08-07T13:58:12.822411Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.18461","last_updated":"2025-03-02T12:44:06Z","snapshot_observed_at":"2026-08-15T20:35:11.014598Z","submitted_at":"2025-02-25T18:59:12Z","title":"K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.18461","snapshot_observed_at":"2026-08-07T13:58:13.135825Z","title":"K-lora: Unlocking training-free fusion of any subject and style loras","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:13.135825Z"},"links":{"cited_paper":"/paper/2502.18461","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:e46359f879dfa0b867c456fe77cb04cc8f12ed93b9169241350908e5133dbfd2","observation_id":"52ef11ea-a4ee-43be-8757-3c9b52c7275d","resolution":{"observed_at":"2026-08-07T13:58:13.135825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T14:12:24.684408Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance"},"reference_resolution":{"displayed":19,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":4,"verified_fuzzy":1},"total_outbound_references":19},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 2 inbound Pith citation observations for arXiv:2505.20525."}