{"as_of":"2026-08-12T14:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ddc432cce59cbbf903d8174cb64d9a22ef6cedd4ea7ed11c863ca911a62ddc7e","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T17:42:11.741714Z","state":"measured"},{"denominator":39,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":39,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"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":[],"links":{"evidence":"/evidence","html":"/paper/2412.08781/citation-record","integrity":"/paper/2412.08781/integrity","json":"/paper/2412.08781/citation-record.json","paper":"/paper/2412.08781"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08797","last_updated":"2025-10-09T00:43:44Z","snapshot_observed_at":"2026-07-06T15:03:52.079498Z","submitted_at":"2023-03-15T17:43:42Z","title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08797","snapshot_observed_at":"2026-08-11T17:42:11.586101Z","title":"S., Boffi, N","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.586101Z"},"links":{"cited_paper":"/paper/2303.08797","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:09ec8595c4182c8da9e41572eda3defb7ffe6e6a3d487bbefd18abcb5045426d","observation_id":"68a9001f-a48b-4265-b137-c5594497f844","resolution":{"observed_at":"2026-08-11T17:42:11.586101Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10733","last_updated":"2025-05-18T21:17:22Z","snapshot_observed_at":"2026-08-08T21:24:29.917572Z","submitted_at":"2024-10-14T17:15:07Z","title":"Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10733","snapshot_observed_at":"2026-08-11T17:42:11.600091Z","title":"Deep compression autoen- coder for efficient high-resolution diffusion models.arXiv preprint arXiv:2410.10733, 2024a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.600091Z"},"links":{"cited_paper":"/paper/2410.10733","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:a9db65b5a371dca0c506b1c3ad8546f60b0fc01adc29bda9170aaeae31708981","observation_id":"f94e3083-e903-4c58-ae47-bc0b9f15f388","resolution":{"observed_at":"2026-08-11T17:42:11.600091Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14404","last_updated":"2024-01-25T18:59:57Z","snapshot_observed_at":"2026-08-06T14:37:40.501908Z","submitted_at":"2024-01-25T18:59:57Z","title":"Deconstructing Denoising Diffusion Models for Self-Supervised Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.14404","snapshot_observed_at":"2026-08-11T17:42:11.604491Z","title":"Deconstructing denoising diffusion models for self-supervised learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.604491Z"},"links":{"cited_paper":"/paper/2401.14404","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:98d4ac82df2798e6488c2b3feb6439cc8b6d69825cc06592860c2e5b419a54ca","observation_id":"fbc05112-b163-492b-8c5f-7727d957c114","resolution":{"observed_at":"2026-08-11T17:42:11.604491Z","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":"2026-08-11T17:42:12.098892Z","title":"We then create nine interpolated snippets ˆsi by linearly interpolating between s1 and s2 with interpolation coefficients αi ranging from 0.1 to 0.9 in increments of 0.1","venue":null,"work_id":"5e2e88ca-16d1-4b9c-9a97-658f663224f7","year":2021},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.727368Z"},"links":{"citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:c1440219003deab8fc8afee60a1d49631498dbf8284d84416df76a9aed749262","observation_id":"c0ed2279-842f-40ff-b610-fa80df2c7656","resolution":{"observed_at":"2026-08-11T17:42:12.104541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02557","last_updated":"2024-04-12T15:48:47Z","snapshot_observed_at":"2026-08-10T17:14:13.774632Z","submitted_at":"2023-10-04T03:30:32Z","title":"Generalization in diffusion models arises from geometry-adaptive harmonic representations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.02557","snapshot_observed_at":"2026-08-11T17:42:11.622532Z","title":"P., and Mal- lat, S","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.622532Z"},"links":{"cited_paper":"/paper/2310.02557","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:15fd7cf94607d2c1ee012d858722c871195a9f69f38940a32f2995869ebf1153","observation_id":"351cca57-84a6-4f8e-ba5e-43ece73c92bb","resolution":{"observed_at":"2026-08-11T17:42:11.622532Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6114","last_updated":"2022-12-10T21:04:00Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2013-12-20T20:58:10Z","title":"Auto-Encoding Variational Bayes","version":11},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6114","snapshot_observed_at":"2026-08-11T17:42:11.626567Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.626567Z"},"links":{"cited_paper":"/paper/1312.6114","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:a2774a34411bca89eabd51b46a69c553200aedabf4db4f07bc64dd7fcbc43642","observation_id":"3c7cae1c-7e4f-4211-b7a0-fdfaa7aab3ea","resolution":{"observed_at":"2026-08-11T17:42:11.626567Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.07022","last_updated":"2022-08-15T06:32:57Z","snapshot_observed_at":"2026-08-12T02:29:57.175717Z","submitted_at":"2022-08-15T06:32:57Z","title":"Memory-Driven Text-to-Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.07022","snapshot_observed_at":"2026-08-11T17:42:11.634344Z","title":"C., Prabhudesai, M., Duggal, S., Brown, E., and Pathak, D","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.634344Z"},"links":{"cited_paper":"/paper/2208.07022","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:518fda13491be52b544c926ab5f4083698e1e32a64219edb47572a363feb8230","observation_id":"9817f8ec-460c-4afb-8a60-9a47f2792294","resolution":{"observed_at":"2026-08-11T17:42:11.634344Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.03701","last_updated":"2024-11-01T14:48:57Z","snapshot_observed_at":"2026-08-10T22:15:41.413935Z","submitted_at":"2023-12-06T18:59:31Z","title":"Return of Unconditional Generation: A Self-supervised Representation Generation Method","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.03701","snapshot_observed_at":"2026-08-11T17:42:11.638327Z","title":"Self-conditioned image gen- eration via generating representations","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.638327Z"},"links":{"cited_paper":"/paper/2312.03701","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:84d3c80578ff8995d60d9b5e97493a2ecafc833b402628311f8f6b03c568cd98","observation_id":"82f9e333-39ae-4757-a4b5-f307e8513fbd","resolution":{"observed_at":"2026-08-11T17:42:11.638327Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.14416","last_updated":"2023-08-30T14:22:32Z","snapshot_observed_at":"2026-07-06T14:56:43.786434Z","submitted_at":"2023-02-28T08:48:45Z","title":"DREAM: Efficient Dataset Distillation by Representative Matching","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.14416","snapshot_observed_at":"2026-08-11T17:42:11.642367Z","title":"Dream: Efficient dataset distillation by representative matching","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.642367Z"},"links":{"cited_paper":"/paper/2302.14416","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:1b2315a199bdc7790de9171c893ba9b19160903aece058dfa40c82c992492881","observation_id":"424bc95d-a33f-4228-bd61-b32652ab58d7","resolution":{"observed_at":"2026-08-11T17:42:11.642367Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.11081","last_updated":"2025-03-01T09:52:49Z","snapshot_observed_at":"2026-07-06T19:33:30.263638Z","submitted_at":"2024-10-14T20:43:25Z","title":"Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.11081","snapshot_observed_at":"2026-08-11T17:42:11.646273Z","title":"and Song, Y","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.646273Z"},"links":{"cited_paper":"/paper/2410.11081","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:86062dc3a0540dd2749b5b5659eb4e79f7118e634ab8476a7f18bb9596907d0d","observation_id":"2dc4e993-47a4-46e4-adc2-b289a3760cbe","resolution":{"observed_at":"2026-08-11T17:42:11.646273Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08740","last_updated":"2024-09-23T15:59:41Z","snapshot_observed_at":"2026-08-10T16:29:09.535299Z","submitted_at":"2024-01-16T18:55:25Z","title":"SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08740","snapshot_observed_at":"2026-08-11T17:42:11.650291Z","title":"S., Boffi, N","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.650291Z"},"links":{"cited_paper":"/paper/2401.08740","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:41968b4bbb496ed0be06f52aa280aab85be88510fb923aca2e59d60d6386dca7","observation_id":"9f34fcf2-1805-4abd-973f-b7e2911601c4","resolution":{"observed_at":"2026-08-11T17:42:11.650291Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-08-11T10:12:11.384939Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-08-11T17:42:11.654253Z","title":"Dinov2: Learning robust visual features without supervision","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.654253Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:a167e1f4c229f993658af444ffdf738bb29a9664095b1c7dcf894eef142e3cb6","observation_id":"4bc0332f-e2cc-488e-bd5f-cb2fd167e638","resolution":{"observed_at":"2026-08-11T17:42:11.654253Z","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":"2026-07-06T02:11:23.670680Z","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":"2026-08-11T17:42:11.658200Z","title":"SDXL: Im- proving latent diffusion models for high-resolution image synthesis","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.658200Z"},"links":{"cited_paper":"/paper/2307.01952","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:2700ae26e1f91ccc2dbe1eebaa41ad3e8115cd18fdb48b1781838711ecf528bb","observation_id":"7ec2fcaf-25ff-40df-b9e2-69143dd9cafd","resolution":{"observed_at":"2026-08-11T17:42:11.658200Z","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":"2026-08-11T17:42:11.662781Z","title":"Stylegan-xl: Scaling stylegan to large diverse datasets","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.662781Z"},"links":{"citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:503ca8ce466d543b51fca0696e57809a97c7d62e27b54bc325da39f226e680f4","observation_id":"15e957d9-6c6b-42c0-b9b2-2900fee412aa","resolution":{"observed_at":"2026-08-11T17:42:11.662781Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.02849","last_updated":"2022-10-02T11:55:59Z","snapshot_observed_at":"2026-08-06T04:16:14.037579Z","submitted_at":"2022-04-06T14:13:35Z","title":"KNN-Diffusion: Image Generation via Large-Scale Retrieval","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.02849","snapshot_observed_at":"2026-08-11T17:42:11.666796Z","title":"Knn-diffusion: Im- age generation via large-scale retrieval","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.666796Z"},"links":{"cited_paper":"/paper/2204.02849","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:62bd7e95f6d6f142f0aa986cb8dd23cf7a08b03306b18c0782cb7de77d265fd2","observation_id":"e9299f34-8726-47a2-8f05-3af56e178862","resolution":{"observed_at":"2026-08-11T17:42:11.666796Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02502","last_updated":"2022-10-05T20:19:21Z","snapshot_observed_at":"2026-08-11T15:38:14.931716Z","submitted_at":"2020-10-06T06:15:51Z","title":"Denoising Diffusion Implicit Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02502","snapshot_observed_at":"2026-08-11T17:42:11.670836Z","title":"Denoising diffusion im- plicit models","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.670836Z"},"links":{"cited_paper":"/paper/2010.02502","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:aa2ca0d35ddd8bee2e41070b8cf1cb05e6afcfa45189ab9bebe5efa8abb46835","observation_id":"64d75610-23ee-4997-83b4-6b3c9a7fb433","resolution":{"observed_at":"2026-08-11T17:42:11.670836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.02262","last_updated":"2023-08-25T16:33:42Z","snapshot_observed_at":"2026-08-02T22:32:37.041591Z","submitted_at":"2022-06-05T20:45:01Z","title":"Diffusion-GAN: Training GANs with Diffusion","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.02262","snapshot_observed_at":"2026-08-11T17:42:11.679076Z","title":"Diffusion-gan: Training gans with diffusion","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.679076Z"},"links":{"cited_paper":"/paper/2206.02262","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:8b92dcf555f7f99f99d8b0511a79419c9b66c91ee06283aba9c6130bdb599ac0","observation_id":"9560ea57-cd97-41eb-8019-2acc48c09a54","resolution":{"observed_at":"2026-08-11T17:42:11.679076Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.07804","last_updated":"2022-04-04T18:55:28Z","snapshot_observed_at":"2026-08-12T02:28:34.526991Z","submitted_at":"2021-12-15T00:09:38Z","title":"Tackling the Generative Learning Trilemma with Denoising Diffusion GANs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.07804","snapshot_observed_at":"2026-08-11T17:42:11.683251Z","title":"Tackling the generative learning trilemma with denoising diffusion gans","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.683251Z"},"links":{"cited_paper":"/paper/2112.07804","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:b5fdb7011a57bb5e6d0302b17c85289b06a47bb23ca66b70b1dad02963011400","observation_id":"bdb12dd1-9b82-4b5c-91b2-94341851107c","resolution":{"observed_at":"2026-08-11T17:42:11.683251Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.01423","last_updated":"2025-03-10T11:43:42Z","snapshot_observed_at":"2026-08-11T01:06:46.210110Z","submitted_at":"2025-01-02T18:59:40Z","title":"Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.01423","snapshot_observed_at":"2026-08-11T17:42:11.687126Z","title":"and Wang, X","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.687126Z"},"links":{"cited_paper":"/paper/2501.01423","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:97f0d49c4d08e346021f925f5fb7fbcd92baa683995501f8c29c20b06daa9c93","observation_id":"9fb6f089-c296-439b-be83-7d342bd63acb","resolution":{"observed_at":"2026-08-11T17:42:11.687126Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.14867","last_updated":"2024-05-24T17:08:32Z","snapshot_observed_at":"2026-08-05T03:51:41.162350Z","submitted_at":"2024-05-23T17:59:49Z","title":"Improved Distribution Matching Distillation for Fast Image Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14867","snapshot_observed_at":"2026-08-11T17:42:11.695214Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.695214Z"},"links":{"cited_paper":"/paper/2405.14867","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:c104f2646c8ed81b2549f5cffffd1f5d614cb5950431f3080d65ab67df182818","observation_id":"d846b3f1-ff4a-4fa0-b20d-e97a3a731597","resolution":{"observed_at":"2026-08-11T17:42:11.695214Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05737","last_updated":"2024-03-29T17:44:41Z","snapshot_observed_at":"2026-08-02T18:23:02.746177Z","submitted_at":"2023-10-09T14:10:29Z","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05737","snapshot_observed_at":"2026-08-11T17:42:11.699689Z","title":"B., Versari, L., Sohn, K., Minnen, D., Cheng, Y ., Birodkar, V ., Gupta, A., Gu, X., et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.699689Z"},"links":{"cited_paper":"/paper/2310.05737","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:c0afb00f83aa81dbc5e146208a46a9667c47ea36b1e7222927de8bfbb929b297","observation_id":"ec87665a-d71f-4a0f-b440-29ee383166c8","resolution":{"observed_at":"2026-08-11T17:42:11.699689Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.06940","last_updated":"2025-06-18T04:35:42Z","snapshot_observed_at":"2026-07-06T19:30:26.233621Z","submitted_at":"2024-10-09T14:34:53Z","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.06940","snapshot_observed_at":"2026-08-11T17:42:11.703397Z","title":"Representation alignment for generation: Training diffusion transformers is easier than you think","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.703397Z"},"links":{"cited_paper":"/paper/2410.06940","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:58de04f63262467deba302f6c4c3860dc90129b1fe30eed44c3319ce9938c445","observation_id":"cd3e058f-444e-4aaf-9967-d5c6ddf37b30","resolution":{"observed_at":"2026-08-11T17:42:11.703397Z","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":"2026-08-11T17:42:12.164263Z","title":"Therefore, we adopted Zero mask for all major experiments","venue":null,"work_id":"8643ec4a-24bc-47a2-b64c-060a58663b62","year":2024},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.707095Z"},"links":{"citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:d8fc11061d288065bd937b62f5f6d515768ba4c5a255d6bdd7cfbc343e2cbcb8","observation_id":"a6409ebc-c5fb-4366-a42f-922a59017d17","resolution":{"observed_at":"2026-08-11T17:42:12.168198Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T17:42:12.141221Z","title":null,"venue":null,"work_id":"ec4d9fa0-482d-47dd-985b-be1901310b21","year":2024},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.715808Z"},"links":{"citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:0593ab124f3cebe3c95d8a34b577d4e3f547b05b9bf967b3ccf0c5fd2225b57b","observation_id":"82e37b67-6471-467a-a91d-b268f7ff0829","resolution":{"observed_at":"2026-08-11T17:42:12.145794Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T17:42:12.128619Z","title":"In contrast, for pixel space generation, we directly use the raw pixel data as input","venue":null,"work_id":"cd680814-89ed-4022-a64d-6cb62b085e14","year":2024},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.719372Z"},"links":{"citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:b70df4d2611251d782c9b5a6e439a4a18a61176391caf07885af5b69d9f5f53a","observation_id":"e739e60a-ca9a-4333-8849-dc0fee14f16d","resolution":{"observed_at":"2026-08-11T17:42:12.133385Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T17:42:12.114595Z","title":"Dinov2-B offers superior performance, making it an ideal choice for facilitating the efficient training for constructing the memory bank","venue":null,"work_id":"bb4f3011-1514-4d06-a9d8-4c96b2c3909e","year":2024},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.723009Z"},"links":{"citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:c669911c5d0c4a93a6f978d119bcf05ad28a1d9de73326c0eb5ee34b7f915d7e","observation_id":"4e8fde72-1f55-4c89-99f3-6e6c92c12553","resolution":{"observed_at":"2026-08-11T17:42:12.119854Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T17:42:12.086471Z","title":"In the DDPM framework introduced by Ho et al","venue":null,"work_id":"4ef536b3-63c0-4bb7-8fd5-3d14cb9a5e38","year":2020},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.731191Z"},"links":{"citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:62f4c0743508806e6a967eebf73558b24e696d9732275cbdeba8d54223840d04","observation_id":"5711d9b3-5414-48b9-aa06-c3305c0dca79","resolution":{"observed_at":"2026-08-11T17:42:12.090578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T17:42:12.072922Z","title":"The process is formulated as: xt = αtx0 + σtε, with α0 = σ1 = 1, α 1 = σ0 = 0, where αt decreases and σt increases as functions of t","venue":null,"work_id":"9c8690b1-1fd0-4fe6-9097-061322d46a56","year":2023},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.734699Z"},"links":{"citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:83203a30048e4538e0df6a6b6f3c4fabd25e318f6a58f362f5c2c669b85b3ce5","observation_id":"77b79757-6e94-4f5f-b9e2-6160b9fed416","resolution":{"observed_at":"2026-08-11T17:42:12.077307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T17:42:12.060723Z","title":"Consequently, simple interpolants can be utilized by defining αt and σt as straightforward functions during training and inference","venue":null,"work_id":"0d5b9875-ceb2-4ef2-8510-e43e50c4377d","year":2020},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.738154Z"},"links":{"citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:634c7283dec9c44a45fe2a45ab84ce223caeebd8e9e87fb935499fe3f9da0c51","observation_id":"2c88bb8f-e50a-474a-bfae-db4b5861e4e7","resolution":{"observed_at":"2026-08-11T17:42:12.065070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T17:42:12.153139Z","title":"↓ means lower is better and all results reported are without classifier-free guidance","venue":null,"work_id":"ba083e1c-b1f2-4d2c-a40c-b52ea70e0e81","year":2025},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":256,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.710692Z"},"links":{"citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:3d29808de63949108b5f22911434eb85525e2cd87bf49dd4f8f919df57e85dd3","observation_id":"d2cc78b7-119c-4106-8fa9-0160accd9a00","resolution":{"observed_at":"2026-08-11T17:42:12.157035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T17:42:12.047165Z","title":"Generation involves solving the corresponding reverse SDE, starting from random Gaussian noise xT ∼ N(0, I)","venue":null,"work_id":"b099a749-d89e-4b52-8c44-e27babc4a448","year":2022},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":1000,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.741714Z"},"links":{"citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:f9fcfd2d1923db49748182cf871c7803f0f35be87fe14383b7fe936cc9d553eb","observation_id":"c85bd474-0405-4501-a7c5-31f031722956","resolution":{"observed_at":"2026-08-11T17:42:12.052986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-07-30T09:12:38.100527Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-11T17:42:11.614009Z","title":"Bert: Pre-training of deep bidirectional trans- formers for language understanding","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.614009Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:14497cf5d5dff996c4384b0146e2640b5f060ce53d15bd3b62b60bf9aa10ae80","observation_id":"68f4d551-5166-4fae-82c8-418e8a54201a","resolution":{"observed_at":"2026-08-11T17:42:11.614009Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-11T17:42:11.630550Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.630550Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:95c90a5987b31d7e0a67fb767c9c2a50e9381c2d5eb99c8fa2c941939e2058d0","observation_id":"be42d545-5c95-4574-b5f2-c5b815853af4","resolution":{"observed_at":"2026-08-11T17:42:11.630550Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.13456","last_updated":"2021-02-10T18:17:04Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-11-26T19:39:10Z","title":"Score-Based Generative Modeling through Stochastic Differential Equations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.13456","snapshot_observed_at":"2026-08-11T17:42:11.675074Z","title":"P., Kumar, A., Er- mon, S., and Poole, B","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.675074Z"},"links":{"cited_paper":"/paper/2011.13456","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:33f2a4daa7f48bb2ec889bc5f71c27f497fefa351ff2bd2373dc220376358ebd","observation_id":"9511fb33-5477-4fab-811a-116851754da7","resolution":{"observed_at":"2026-08-11T17:42:11.675074Z","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":"2026-08-11T17:42:11.609124Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.609124Z"},"links":{"citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:6d4959612310d29964bb38b44956c5169adfc90091f5e6785275e4eda3e22ce2","observation_id":"09457cac-858b-451f-8cbd-94ceddc6de7f","resolution":{"observed_at":"2026-08-11T17:42:11.609124Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.11096","last_updated":"2019-02-25T21:32:06Z","snapshot_observed_at":"2026-07-06T07:04:57.275371Z","submitted_at":"2018-09-28T15:38:49Z","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.11096","snapshot_observed_at":"2026-08-11T17:42:11.595660Z","title":"Brock, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.595660Z"},"links":{"cited_paper":"/paper/1809.11096","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:787ad850cf36bca9b83afa9a4273fe67c38b25bc1d36e6dd853e9f53305edb0c","observation_id":"decef20b-f63e-422d-9502-9e1ea287b62a","resolution":{"observed_at":"2026-08-11T17:42:11.595660Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.11824","last_updated":"2022-10-24T17:59:04Z","snapshot_observed_at":"2026-08-11T21:20:04.837232Z","submitted_at":"2022-04-25T17:55:26Z","title":"Semi-Parametric Neural Image Synthesis","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.11824","snapshot_observed_at":"2026-08-11T17:42:11.591242Z","title":"Semi-parametric neural image synthesis","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.591242Z"},"links":{"cited_paper":"/paper/2204.11824","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:72544605c86157bb37a510c8f14d4067ada013dbaee9fb6505fafc1543229d32","observation_id":"ccc6baac-8a20-460d-a6c1-da7af1f46a42","resolution":{"observed_at":"2026-08-11T17:42:11.591242Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.00783","last_updated":"2024-06-30T17:59:58Z","snapshot_observed_at":"2026-08-10T09:55:22.812749Z","submitted_at":"2024-06-30T17:59:58Z","title":"Diffusion Models and Representation Learning: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.00783","snapshot_observed_at":"2026-08-11T17:42:11.618595Z","title":"S., Hu, V","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.618595Z"},"links":{"cited_paper":"/paper/2407.00783","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:bcd7d4c47cc2f1c99e6c2ed1f4d3591ecb680cb908e1cc05c8a1681990882e1d","observation_id":"f62512a5-5460-461b-9c10-735f3b426457","resolution":{"observed_at":"2026-08-11T17:42:11.618595Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10356","last_updated":"2024-10-31T12:49:09Z","snapshot_observed_at":"2026-08-12T11:59:14.495794Z","submitted_at":"2024-10-14T10:17:24Z","title":"FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10356","snapshot_observed_at":"2026-08-11T17:42:11.691106Z","title":"Fasterdit: To- wards faster diffusion transformers training without archi- tecture modification","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-11T17:42:11.691106Z"},"links":{"cited_paper":"/paper/2410.10356","citing_paper":"/paper/2412.08781"},"observation_digest":"sha256:9263aee8d52e74a7f38f44c6c7adde24b6fd9e4a5f7a785709b30f4fad85912d","observation_id":"2bd14ada-9722-47bf-a8ab-1dd0402a024b","resolution":{"observed_at":"2026-08-11T17:42:11.691106Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.08781","last_updated":"2025-02-11T23:05:30Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T02:29:00.559144Z","submitted_at":"2024-12-11T21:23:24Z","title":"GMem: A Modular Approach for Ultra-Efficient Generative Models"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":30,"verified_exact":0,"verified_fuzzy":8},"total_outbound_references":39},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2412.08781."}