{"as_of":"2026-08-18T08:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e370b38e07c06fe210e2545c5573a8956926e2a51062240a78fd3bbb78d4a44c","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T16:35:25.128475Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T16:52:56.657593Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.13107","snapshot_observed_at":"2026-08-04T16:52:56.657593Z","title":"arXiv preprint arXiv:2507.13107v1 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.11247","last_updated":"2025-09-14T12:46:39Z","snapshot_observed_at":"2026-08-09T11:17:00.564561Z","submitted_at":"2025-09-14T12:46:39Z","title":"Contextualized Multimodal Lifelong Person Re-Identification in Hybrid Clothing States","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T16:52:56.657593Z"},"links":{"cited_paper":"/paper/2507.13107","citing_paper":"/paper/2509.11247"},"observation_digest":"sha256:cc907779162df7cd89c7d615f2a1a80dfcf0d571a683396cc2665f552bf8279c","observation_id":"1574b754-e60f-46d0-87f4-e33f27a47af2","resolution":{"observed_at":"2026-08-04T16:52:56.657593Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2507.13107/citation-record","integrity":"/paper/2507.13107/integrity","json":"/paper/2507.13107/citation-record.json","paper":"/paper/2507.13107"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:22.001139Z","title":"High- resolution image synthesis with latent diffusion models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:22.001139Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:1ed5bb594f43eedea30ac6f16e1f15498991aa5a81c31bd39e5590e7c7d8eb22","observation_id":"0a73e100-b026-4e2b-bb8b-f0082aabeff5","resolution":{"observed_at":"2026-08-06T16:35:22.001139Z","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":"2026-08-06T16:35:22.078435Z","title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:22.078435Z"},"links":{"cited_paper":"/paper/2307.01952","citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:af450f5b3bb63c1c5d1e98eb7f2869725b30256b1f43c69a6a41580104443895","observation_id":"312d7b08-758c-451a-ab37-50f41f3412a2","resolution":{"observed_at":"2026-08-06T16:35:22.078435Z","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":"2026-08-06T16:35:29.271990Z","title":"Scaling rectified flow transformers for high-resolution image synthesis,","venue":null,"work_id":"2ad3a4b9-d4fc-4987-a4c2-90cace46ce79","year":2024},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:22.155771Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:5ff66e245f5d041de4b2c1193adddfa6d29fde0858f35d3a927ec221a5078850","observation_id":"ab593036-6e58-4364-9a83-36be9008a319","resolution":{"observed_at":"2026-08-06T16:35:29.328838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:22.206143Z","title":"Photorealistic text-to-image diffusion models with deep language understanding,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:22.206143Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:0c6360d9b021210ef5874bc7a692d28d7575f2917c02324b3621c83bb6b7b889","observation_id":"c3639ddb-ce74-41b1-90dc-2aca08542d6e","resolution":{"observed_at":"2026-08-06T16:35:22.206143Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:22.312309Z","title":"Denoising diffusion probabilistic models,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:22.312309Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:a7bf114e3930d89b3f409be5b561c6cee8640bae78390b936446178faf3730e2","observation_id":"af09e77f-f660-4c81-be28-06f46ff6c4c4","resolution":{"observed_at":"2026-08-06T16:35:22.312309Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.01618","last_updated":"2022-08-02T17:50:36Z","snapshot_observed_at":"2026-08-02T23:40:32.342515Z","submitted_at":"2022-08-02T17:50:36Z","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.01618","snapshot_observed_at":"2026-08-06T16:35:22.373746Z","title":"An image is worth one word: Person- alizing text-to-image generation using textual inversion,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:22.373746Z"},"links":{"cited_paper":"/paper/2208.01618","citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:cd00b3e402e85f219b4c7084c206f57f8c60de7222637d278820ab2aa874eb35","observation_id":"6062ff73-4225-42d4-bec4-66422ab8b632","resolution":{"observed_at":"2026-08-06T16:35:22.373746Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:22.457687Z","title":"Dreambooth: Fine tuning text-to-image diffusion models for subject- driven generation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:22.457687Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:b16dd07c7f0b6481d6f514e0760c57a1576be40a33ca6ff3280a42e0cb026dbf","observation_id":"f3cf1193-8207-4bc8-8e9f-48d79380ce93","resolution":{"observed_at":"2026-08-06T16:35:22.457687Z","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":"2026-08-06T16:35:29.123075Z","title":"Controlling text-to-image diffusion by orthogo- nal finetuning,","venue":null,"work_id":"bd6cc3ee-0b19-4cf5-876d-b678c5e653d3","year":2023},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:22.523871Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:d795975505ddeb3210ae20aba46ded20e1a82f510b83ae0f63292ebb648aef28","observation_id":"7cfbcf71-78f6-40c8-9608-d9b6deae5d77","resolution":{"observed_at":"2026-08-06T16:35:29.178454Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:28.924346Z","title":"Personalized residuals for concept-driven text-to-image generation,","venue":null,"work_id":"aa89ea9c-d6a4-476f-84eb-822373522da6","year":2024},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:22.581725Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:b32ef23d453d3a407a13d92137ab6e91ddc72acfc3f7aa4e7ad8d0cd686ce43d","observation_id":"297a831f-21da-4db2-8090-730d94cdffed","resolution":{"observed_at":"2026-08-06T16:35:29.054320Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:28.722833Z","title":"Sgdm: an adaptive style- guided diffusion model for personalized text to image generation,","venue":null,"work_id":"2fd0cbdb-7a38-452f-bc89-3e96569a2a5d","year":2024},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:22.626524Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:54310c33109fc6b4a8e893da1162b03f0fdf4bb9c22f68dfdca4848cf0aa65d3","observation_id":"ec2d21c5-d456-495a-b402-feda86967188","resolution":{"observed_at":"2026-08-06T16:35:28.823359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:28.534893Z","title":"A two-stage personalized virtual try-on framework with shape control and texture guidance,","venue":null,"work_id":"57134448-2b7e-4abf-a3ec-7a3fb4f8963c","year":2024},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:22.717119Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:39d3564b2c5ab6507997c6da9b07f9ed807d659045966e1065413c9e1e4bd11f","observation_id":"3588cfb8-7f0b-4c7c-8fe0-809165cfc629","resolution":{"observed_at":"2026-08-06T16:35:28.658033Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:28.415986Z","title":"Videodreamer: Customized multi-subject text-to-video generation with disen-mix finetuning on language-video foundation models,","venue":null,"work_id":"7e66e7e6-ab9e-4406-8b3b-5ae366ee1c1a","year":2025},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:22.777200Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:281ac93cc7615cd5cd2e193bb93dcee2f8ef2d5c0b1a46021fa5d44a9d140d22","observation_id":"fc6c60ca-a382-440e-8643-af4d2bd55ca6","resolution":{"observed_at":"2026-08-06T16:35:28.453586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:22.794442Z","title":"Multi- concept customization of text-to-image diffusion,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:22.794442Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:9397900872a9ceece2775e2a388827415cdca145fd3eb91f888989a88b69f20f","observation_id":"3db9f74a-771e-4f7e-8a62-88975d169ed3","resolution":{"observed_at":"2026-08-06T16:35:22.794442Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.11305","last_updated":"2023-07-02T21:16:39Z","snapshot_observed_at":"2026-08-16T15:46:47.600483Z","submitted_at":"2023-03-20T17:45:02Z","title":"SVDiff: Compact Parameter Space for Diffusion Fine-Tuning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.11305","snapshot_observed_at":"2026-08-06T16:35:22.820345Z","title":"Svdiff: Compact parameter space for diffusion fine-tuning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:22.820345Z"},"links":{"cited_paper":"/paper/2303.11305","citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:5977b710322b893782d722fc1cb90555a0c1e03f3390271649a4eca12a395a3d","observation_id":"d9d1bf7b-598e-45a8-8486-26b08d3a9ca6","resolution":{"observed_at":"2026-08-06T16:35:22.820345Z","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":"2026-08-06T16:35:28.193447Z","title":"Animediff: Customized image generation of anime characters using diffusion model,","venue":null,"work_id":"33f8f0c4-4ed5-455e-a630-efd8166dd0e0","year":2024},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:22.892437Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:e6177fd950b9b665fa1380a315b5471906d9505fe6b99830a14be093e621a3a8","observation_id":"dc317c8b-5920-460d-a1fc-47d513449e4c","resolution":{"observed_at":"2026-08-06T16:35:28.318150Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:27.975306Z","title":"Mix-of-show: Decentralized low- rank adaptation for multi-concept customization of diffusion models,","venue":null,"work_id":"520f7474-c4a0-4e14-baee-14a6e384be79","year":2024},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:22.987263Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:31edfee33224f119312e510a540b58de4f1a8bda91d31ea389fc4da7e43648f6","observation_id":"5a928f4c-d777-49e5-8472-ee30b8e3f02d","resolution":{"observed_at":"2026-08-06T16:35:28.063546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:27.689802Z","title":"Orthogonal adaptation for modular customization of diffusion models,","venue":null,"work_id":"dd6fb24e-46e4-45c2-9c7e-1241a3bb7bea","year":2024},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:23.103650Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:0b268d67e63d7e4fb780ff2af6921cb8b9b430e63a80db7a35fcff7f8724fe92","observation_id":"a36a3d8b-3808-4c16-8510-af1d6e25d744","resolution":{"observed_at":"2026-08-06T16:35:27.893391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:27.275590Z","title":"Multi-lora composition for image generation,","venue":null,"work_id":"70d04082-e9cd-42c8-940a-da7878cde91e","year":2024},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:23.209767Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:c09acf1d1a984deb4c4bda0c63b034818e8b1e902ac9e2ae9a12a9c58c8e25db","observation_id":"9c2ee216-d17e-4d85-ad3c-945dae320e05","resolution":{"observed_at":"2026-08-06T16:35:27.481965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:26.970321Z","title":"Multi-view user preference modeling for personalized text-to-image generation,","venue":null,"work_id":"c2e2bff3-f544-44c6-a10f-3598c5ada35f","year":2025},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:23.286085Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:55955f6b5001cd65c7a7af79af9504f9df2aff579d149f1efb786567a2bc7b1c","observation_id":"577e19f4-1940-4fee-a6a1-8bead0521160","resolution":{"observed_at":"2026-08-06T16:35:27.132841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:26.630735Z","title":"Continual diffusion: Continual customization of text-to-image diffusion with c-lora,","venue":null,"work_id":"ee7be26b-977a-440a-9cb6-c1cc6c492fbf","year":2024},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:23.341962Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:092a390cc744fd5c78afd28f0ce05b1046f335664c9b6146508274b8c194f5ec","observation_id":"6718d5ab-2250-4dd3-9243-47ead66dcf01","resolution":{"observed_at":"2026-08-06T16:35:26.792424Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:26.354682Z","title":"Create your world: Lifelong text-to-image diffusion,","venue":null,"work_id":"9537f6c3-84e5-4a1f-85fd-fcf2b8a1e80b","year":2024},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:23.430229Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:0ef171119da7d8e89387760992b37c851547761476d3b2c83bf6d1af5da7ecd3","observation_id":"565acb88-8ab6-4342-b298-24c919a44879","resolution":{"observed_at":"2026-08-06T16:35:26.487739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:26.110654Z","title":"How to continually adapt text-to-image diffusion models for flexible customization?","venue":null,"work_id":"e97fbba4-20f3-4e40-9c82-975a9c937342","year":2024},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:23.571134Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:090961035e3bad07812ad162ec20b7e436dbe224e76e695ca57aa471eeb1930f","observation_id":"47b98731-c0f7-4db3-ba0a-2f8cb5b9f6dc","resolution":{"observed_at":"2026-08-06T16:35:26.190572Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:26.057692Z","title":"Conceptguard: Continual personalized text-to-image generation with forgetting and confusion mitigation,","venue":null,"work_id":"49ea092e-151e-47ee-93a4-a6ecef47019d","year":2025},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:23.677509Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:2a326e55b359b08e51230915e1664e9dcf40d603f80d95989438307acac1a762","observation_id":"e22e4c87-679d-4669-ad4f-b146cc357b9a","resolution":{"observed_at":"2026-08-06T16:35:26.078911Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:23.750724Z","title":"Catastrophic interference in connec- tionist networks: The sequential learning problem,","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:23.750724Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:b632682430109b1ddb3a3e2cbdc214392e90b0df6ce92b0d3a22aa7afb989989","observation_id":"d88e396e-7d1d-4a69-98e9-2cdaca5e63f8","resolution":{"observed_at":"2026-08-06T16:35:23.750724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-17T09:58:46.058102Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-06T16:35:23.820273Z","title":"Gpt-4 technical report,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:23.820273Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:7726913e8c41e963fa49ce95a9ea1ddb122dd9f12c1dd3de7af63575ecc7e5f6","observation_id":"0c9d8b3a-ddee-4979-a44b-a85c79dca92b","resolution":{"observed_at":"2026-08-06T16:35:23.820273Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.02643","last_updated":"2023-04-05T17:59:46Z","snapshot_observed_at":"2026-08-08T05:14:59.435033Z","submitted_at":"2023-04-05T17:59:46Z","title":"Segment Anything","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.02643","snapshot_observed_at":"2026-08-06T16:35:23.915129Z","title":"Segment anything,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:23.915129Z"},"links":{"cited_paper":"/paper/2304.02643","citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:fb139ec7f33aa69568b7a2980e9038a49ab437c35eb2f3e36f5fce43274a5183","observation_id":"63f32b69-24cb-416e-91c8-25052d4d90d8","resolution":{"observed_at":"2026-08-06T16:35:23.915129Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.03411","last_updated":"2023-04-06T23:26:38Z","snapshot_observed_at":"2026-08-16T15:42:07.986767Z","submitted_at":"2023-04-06T23:26:38Z","title":"InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.03411","snapshot_observed_at":"2026-08-06T16:35:23.986674Z","title":"Instantbooth: Personalized text-to-image generation without test-time finetuning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:23.986674Z"},"links":{"cited_paper":"/paper/2304.03411","citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:9a82570d42044451e25fb079f8db9fb9b1347558c5c219c13be9fca971c2401c","observation_id":"bdb23cb9-c918-4b29-941c-088c671db279","resolution":{"observed_at":"2026-08-06T16:35:23.986674Z","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":"2026-08-06T16:35:24.067644Z","title":"Hierarchical text-conditional image generation with clip latents,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:24.067644Z"},"links":{"cited_paper":"/paper/2204.06125","citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:44241ddcfcc91942bafa2d65ef7a218867220c6428cd338a7ffe51ce10bc174b","observation_id":"fac782d8-3cf9-47cd-9b3f-78ee983422f0","resolution":{"observed_at":"2026-08-06T16:35:24.067644Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-17T18:04:53.578114Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-06T16:35:24.175198Z","title":"Lora: Low-rank adaptation of large language models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:24.175198Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:7c3577bf0bd7660899775073e58401d427e419b5fd9f8ef0109f66cb1872e4a1","observation_id":"c87ec436-1f80-42a4-ad8a-e40d023b51fa","resolution":{"observed_at":"2026-08-06T16:35:24.175198Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:24.236856Z","title":"Adaptive mixtures of local experts,","venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:24.236856Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:34e7a15e2c43c8a41a079a737937b1725620cd07b1a5e6cdc34af6f6eeead57e","observation_id":"1b2a4d17-1b92-4580-9c59-ecbd968ef6f3","resolution":{"observed_at":"2026-08-06T16:35:24.236856Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1701.06538","last_updated":"2017-01-23T18:10:00Z","snapshot_observed_at":"2026-08-13T11:35:07.866136Z","submitted_at":"2017-01-23T18:10:00Z","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1701.06538","snapshot_observed_at":"2026-08-06T16:35:24.319276Z","title":"Outrageously large neural networks: The sparsely- gated mixture-of-experts layer,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:24.319276Z"},"links":{"cited_paper":"/paper/1701.06538","citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:b9028708049cb47899ca59b446142e1c742b5f17251e94f55806033b2821b451","observation_id":"898355ee-4887-4030-abca-9b87d5ee4edb","resolution":{"observed_at":"2026-08-06T16:35:24.319276Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.03432","last_updated":"2024-03-06T03:33:48Z","snapshot_observed_at":"2026-08-16T14:12:26.842842Z","submitted_at":"2024-03-06T03:33:48Z","title":"Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.03432","snapshot_observed_at":"2026-08-06T16:35:24.388242Z","title":"Mixture-of-loras: An efficient multitask tuning for large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:24.388242Z"},"links":{"cited_paper":"/paper/2403.03432","citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:ef8bb028f0d5c001482a8078a386f919627bad361c009806786e11aa4762a5ab","observation_id":"20708068-61ae-4a48-966c-274ddbd34f87","resolution":{"observed_at":"2026-08-06T16:35:24.388242Z","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":"2026-08-16T13:59:08.863607Z","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":"2026-08-06T16:35:24.446607Z","title":"Mixture of lora experts,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:24.446607Z"},"links":{"cited_paper":"/paper/2404.13628","citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:568c3ff276534c86993bb1b7b107ecb346a36c3faf3f6d84c0e268f5af1e2f83","observation_id":"de67dcb1-6d43-4968-a2ae-9aa076c3f821","resolution":{"observed_at":"2026-08-06T16:35:24.446607Z","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":"2026-08-06T16:35:25.901872Z","title":"Expert gate: Lifelong learning with a network of experts,","venue":null,"work_id":"e6972e9d-1731-4c22-9568-96d3952ef975","year":2017},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:24.516212Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:ffca2b4fb4258d83a6751ac0d0f058765d9d54c9298f22c674e50636be743e32","observation_id":"76e6caa0-1fe9-49d7-9264-5fbbddffad19","resolution":{"observed_at":"2026-08-06T16:35:26.015206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:25.725821Z","title":"Lifelong language pretraining with distribution-specialized experts,","venue":null,"work_id":"5c24e535-344a-407b-ae23-2ba9ca0ed7e2","year":2023},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:24.587569Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:46fcda268adc9091bbc2f68688a63668b19c29401c075668afa8c7648d5fac98","observation_id":"ed757949-a0aa-42d0-87e0-a517f5d15e1b","resolution":{"observed_at":"2026-08-06T16:35:25.827064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:25.624058Z","title":"Boosting continual learning of vision-language models via mixture-of-experts adapters,","venue":null,"work_id":"4e58a7cf-2a90-427c-a8e9-e0df681cacc4","year":2024},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:24.654171Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:73756d4f44ae174053717fc79df1b9e70fdc3ea3aaca2064b4b36f554b4d1b95","observation_id":"3e83d980-cd01-47ca-965d-07fe1c03d77c","resolution":{"observed_at":"2026-08-06T16:35:25.665940Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.15432","last_updated":"2025-03-14T03:47:02Z","snapshot_observed_at":"2026-08-16T01:24:21.028334Z","submitted_at":"2024-11-23T03:19:40Z","title":"Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.15432","snapshot_observed_at":"2026-08-06T16:35:24.705839Z","title":"Lifelong knowledge editing for vision language models with low-rank mixture- of-experts,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:24.705839Z"},"links":{"cited_paper":"/paper/2411.15432","citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:4e922644e19518b6b450c3c7b836b3a8871eab41acba3cc657eeb69d30288e45","observation_id":"93f26c23-fe13-4185-9b29-0135d4cc8c0c","resolution":{"observed_at":"2026-08-06T16:35:24.705839Z","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":"2026-08-06T16:35:25.475360Z","title":"Coin: A benchmark of continual instruction tuning for multimodel large language models,","venue":null,"work_id":"08a126b3-f6f5-465f-be84-9e793347b0fe","year":2024},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:24.776810Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:7bd750e6ae703402469006bb1df9ecbda4279eb8e5237461acd2c3924660daba","observation_id":"3c6f9bba-628a-4c76-a00e-87b233f3a850","resolution":{"observed_at":"2026-08-06T16:35:25.548718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.06066","last_updated":"2024-01-11T17:31:42Z","snapshot_observed_at":"2026-08-13T15:18:04.411100Z","submitted_at":"2024-01-11T17:31:42Z","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.06066","snapshot_observed_at":"2026-08-06T16:35:24.838518Z","title":"Deepseekmoe: Towards ultimate expert specialization in mixture-of-experts language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:24.838518Z"},"links":{"cited_paper":"/paper/2401.06066","citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:3f63f80c53945cac75b7a39d7b027e855a3b0cc7e5e77362ce10d9f84ee3836a","observation_id":"b870deb8-4728-483b-b983-0e2009c980bf","resolution":{"observed_at":"2026-08-06T16:35:24.838518Z","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":"2026-08-06T16:35:25.320921Z","title":"An image is worth multiple words: Multi-attribute inversion for constrained text-to- image synthesis,","venue":null,"work_id":"5b5e55c6-ddd6-4b63-a1cd-65925d3c1904","year":2025},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:24.899476Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:08d0915ad5c4f61e23e2ded2e7715ce1c609892b0f507aac1aa6315e9c4f9769","observation_id":"927ed754-42e2-4416-b490-6441f1624886","resolution":{"observed_at":"2026-08-06T16:35:25.384586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:24.967727Z","title":"Overcoming catastrophic forgetting in neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:24.967727Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:dfced01bc0d9e6e8cedde405eb67b203737c29e2ec05b3d880a792bce9a3ab9f","observation_id":"ebf47871-a821-4aee-91f1-9c128cab861d","resolution":{"observed_at":"2026-08-06T16:35:24.967727Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:35:25.044975Z","title":"Learning without forgetting,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:25.044975Z"},"links":{"citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:e0c0cb871188d21427f234a07c1ce2d3b118c0c09f1f91b4d418bc8316de53ab","observation_id":"55b0dca0-d1fb-4fe6-87e2-f227003be9df","resolution":{"observed_at":"2026-08-06T16:35:25.044975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.12598","last_updated":"2022-07-26T01:42:07Z","snapshot_observed_at":"2026-08-14T06:37:15.299690Z","submitted_at":"2022-07-26T01:42:07Z","title":"Classifier-Free Diffusion Guidance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.12598","snapshot_observed_at":"2026-08-06T16:35:25.128475Z","title":"Classifier-free diffusion guidance,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T16:35:25.128475Z"},"links":{"cited_paper":"/paper/2207.12598","citing_paper":"/paper/2507.13107"},"observation_digest":"sha256:f643a910108aeedd4acb47793b65d7d375897d50eaceadc0ce83c6e0d280b0ff","observation_id":"77b783b9-32a2-43ed-a3c7-338faf03936d","resolution":{"observed_at":"2026-08-06T16:35:25.128475Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.13107","last_updated":"2025-07-17T13:22:40Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T12:23:17.204902Z","submitted_at":"2025-07-17T13:22:40Z","title":"R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept Learning"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":23,"verified_exact":0,"verified_fuzzy":20},"total_outbound_references":43},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 1 inbound Pith citation observation for arXiv:2507.13107."}