{"as_of":"2026-08-22T09:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:299274ac15035cd7a1e4f125cf262097b01d2f84a87c2a4404fb2fde6fbd62e0","coverage":[{"denominator":60,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":60,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T21:02:49.434805Z","state":"measured"},{"denominator":60,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":60,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/2505.11204/citation-record","integrity":"/paper/2505.11204/integrity","json":"/paper/2505.11204/citation-record.json","paper":"/paper/2505.11204"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:49.214978Z","title":"Structured pruning of deep convolutional neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.214978Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:a0dfd9212eb45189035fc01e5415c78191b7c7d1096e9da9b2b2f03bb796eeda","observation_id":"f1eccf67-0a0f-441c-b157-d22476b60601","resolution":{"observed_at":"2026-08-15T21:02:49.214978Z","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":"2026-08-15T21:02:49.219467Z","title":"Food-101--mining discriminative components with random forests","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.219467Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:53eea6a427a1d4a4205e71b932b965a02b7434d9f7181dee3287b4bd9daa0e62","observation_id":"68a065b0-eacf-419f-9593-b71d31d732a4","resolution":{"observed_at":"2026-08-15T21:02:49.219467Z","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":"2026-08-15T21:02:49.223940Z","title":"Remote sensing image scene classification: Benchmark and state of the art","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.223940Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:1b309410bb16fa027eac0f6e8500b24a0bc1c6fd4acffbac05f85e3f3b5611bc","observation_id":"865fb8c8-314e-4d51-8371-0ebde65c7710","resolution":{"observed_at":"2026-08-15T21:02:49.223940Z","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":"2026-08-15T21:02:49.228216Z","title":"Superposition of many models into one","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.228216Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:37bc5fc87bf5b2e7e8a9dcb450b96a64f09a9c0f9834043682e66773096c0975","observation_id":"951ecd1e-7d9f-43f4-b911-bd68148586eb","resolution":{"observed_at":"2026-08-15T21:02:49.228216Z","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":"2026-08-15T21:02:50.244757Z","title":"On the efficacy of knowledge distillation","venue":null,"work_id":"7fd8294d-abbb-4e91-a6df-a833acdcf8c5","year":2019},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.232014Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:d558e3f46d17588c6624f75f3fe3a25f8158f779532b1e4b55cb43f08da2264f","observation_id":"cc53f51b-eafd-42c0-8790-ec1c6f7c03ba","resolution":{"observed_at":"2026-08-15T21:02:50.248782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T21:02:49.235983Z","title":"Cimpoi, S","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.235983Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:165ef6c17b8ef796d2a6d1e441ce18744219b2ae1680c919f1f9d470682f3b55","observation_id":"2bd65762-5858-4592-bd25-2df40dad5dfd","resolution":{"observed_at":"2026-08-15T21:02:49.235983Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.01718","last_updated":"2018-12-03T12:37:31Z","snapshot_observed_at":"2026-08-14T23:13:55.892736Z","submitted_at":"2018-12-03T12:37:31Z","title":"Deep Learning for Classical Japanese Literature","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.01718","snapshot_observed_at":"2026-08-15T21:02:49.240019Z","title":"Deep learning for classical japanese literature","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.240019Z"},"links":{"cited_paper":"/paper/1812.01718","citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:ec3ce37bafb5c049ce4cef13cd8caeb654f8d1cb81af31d319cb83ce049d293a","observation_id":"5dd1d952-528c-4eea-a6a5-c7b03b56a4f7","resolution":{"observed_at":"2026-08-15T21:02:49.240019Z","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":"2026-08-15T21:02:50.225928Z","title":"An analysis of single-layer networks in unsupervised feature learning","venue":null,"work_id":"956e03d3-46a8-4d6f-834c-4e7a148ce01b","year":2011},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.243996Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:b26088243526041f34ca08f543e1da195dc4fa138ae862edf80f6b4e832575d9","observation_id":"1b1d199b-02ad-42a6-b79f-4d68f4a42cc5","resolution":{"observed_at":"2026-08-15T21:02:50.229616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T21:02:50.214054Z","title":"Emnist: Extending mnist to handwritten letters","venue":null,"work_id":"a693ddf3-58b4-48fd-a3bf-c65c821645a6","year":2017},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.247601Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:9ccbeab649430a5f8cf264ecbea199648c41f3278c4dc126487525bae0ddb43c","observation_id":"4c64ed37-7cc0-420a-8954-4c3226f79393","resolution":{"observed_at":"2026-08-15T21:02:50.217799Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T21:02:49.251115Z","title":"The mnist database of handwritten digit images for machine learning research","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.251115Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:d53ad18d829ef002e2f5d1fb217f266a829e64a1ac9b4f0cdaee0c6dfdef3dd4","observation_id":"eb75f7f0-db26-48f9-aa85-b04ea442916b","resolution":{"observed_at":"2026-08-15T21:02:49.251115Z","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":"2026-08-15T21:02:50.195868Z","title":"Depgraph: Towards any structural pruning","venue":null,"work_id":"29a954f7-774d-4c4c-b344-6181d44d35dd","year":2023},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.255038Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:2a4e5cbc98a70519972188445d8d051b5e371a8c4f66c4ce54424f8792e3a029","observation_id":"ee59d966-1dc0-4f8f-8bf9-0c3796679b61","resolution":{"observed_at":"2026-08-15T21:02:50.199750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T21:02:50.183913Z","title":"Linear mode connectivity and the lottery ticket hypothesis","venue":null,"work_id":"acd31ba9-f764-4893-86a7-251558db081a","year":2020},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.258644Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:f3e6ce2e48fc8f374322ae5ed3d6137e0ed0525dff126d4615f6726faa405de7","observation_id":"17cb41ca-a7d5-4858-8fcd-f936240453a3","resolution":{"observed_at":"2026-08-15T21:02:50.188005Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T21:02:50.172941Z","title":"A survey of quantization methods for efficient neural network inference","venue":null,"work_id":"becafeaa-0ce2-4f79-9ca4-aa8f369ff7b5","year":2022},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.262190Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:5c58b0f8d30e9c8acce187fe853f5b259066221e1da3977f8bf79b0c7f16ee2c","observation_id":"96aadcd7-8702-4246-8247-84770a8a3871","resolution":{"observed_at":"2026-08-15T21:02:50.176615Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T21:02:50.161397Z","title":"Challenges in representation learning: A report on three machine learning contests","venue":null,"work_id":"b4cef5d3-d464-4d9a-bc72-cc68902937e4","year":2013},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.266059Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:82f9c34a8879c6461a0bedee1ed902745ebc4478499c8d30f6b1337b628b90db","observation_id":"f37cf13e-1bd7-4cab-bfa1-cb019376562c","resolution":{"observed_at":"2026-08-15T21:02:50.165711Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T21:02:49.269618Z","title":"Knowledge distillation: A survey","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.269618Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:2e3b343954f99f3b1e22b5085dd895bc91b7422afdfc741bc43dad70dadac432","observation_id":"20b5f6b6-e189-44af-be49-85fba20a5998","resolution":{"observed_at":"2026-08-15T21:02:49.269618Z","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":"2026-08-15T21:02:50.141112Z","title":"Pela: Learning parameter-efficient models with low-rank approximation","venue":null,"work_id":"b8ca9ded-fff8-4875-97f4-04ac9c1e11d7","year":2024},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.273351Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:e33bed09802a4c8c7ec0fdba41f4f3e3454a7a5f0ac74f72586d77add1291eab","observation_id":"38c44b43-93cd-44fa-b076-345d316a1b38","resolution":{"observed_at":"2026-08-15T21:02:50.145437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T21:02:49.277156Z","title":"Structured pruning for deep convolutional neural networks: A survey","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.277156Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:d247db7e84829502605be1bd310d3549b9ec06cc30c57868e79ab060070583bb","observation_id":"60805fab-c6ea-4352-8696-b44704c9e53b","resolution":{"observed_at":"2026-08-15T21:02:49.277156Z","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":"2026-08-15T21:02:49.280766Z","title":"Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.280766Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:f98a8901f1722dd6c7fb6302d68ed5f7ec27f10a033a9264b96d6de4970ac82a","observation_id":"eaf64051-4b0e-4f1b-b912-a7d705c0eb2a","resolution":{"observed_at":"2026-08-15T21:02:49.280766Z","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":"2026-08-20T11:47:17.477107Z","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":"2026-08-15T21:02:49.284525Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.284525Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:e7bbc689c93b768d2f966d9f6ad96d7964562e79b04cb892a7ec3de4418cfe79","observation_id":"ea6b47d5-6e8e-4646-9bc4-edb7c31749e4","resolution":{"observed_at":"2026-08-15T21:02:49.284525Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.04089","last_updated":"2023-03-31T15:27:01Z","snapshot_observed_at":"2026-08-13T03:27:01.609831Z","submitted_at":"2022-12-08T05:50:53Z","title":"Editing Models with Task Arithmetic","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.04089","snapshot_observed_at":"2026-08-15T21:02:49.288134Z","title":"Editing models with task arithmetic","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.288134Z"},"links":{"cited_paper":"/paper/2212.04089","citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:0fe8f0fd0863ac8ec72d855ed4c297e695403de7adccb76363295918ed666c2c","observation_id":"fe23a2c4-d201-4e49-920e-e95c699287e2","resolution":{"observed_at":"2026-08-15T21:02:49.288134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09849","last_updated":"2025-05-21T23:53:00Z","snapshot_observed_at":"2026-08-16T16:07:30.940052Z","submitted_at":"2022-12-19T20:46:43Z","title":"Dataless Knowledge Fusion by Merging Weights of Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09849","snapshot_observed_at":"2026-08-15T21:02:49.291841Z","title":"Dataless knowledge fusion by merging weights of language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.291841Z"},"links":{"cited_paper":"/paper/2212.09849","citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:a1357abcd67ed059caba02d510a21ca02106beb2db750ceef32b8636e0714b4c","observation_id":"b43ba204-37ad-4006-aa08-ba8efe0b428a","resolution":{"observed_at":"2026-08-15T21:02:49.291841Z","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":"2026-08-15T21:02:50.099406Z","title":"3d object representations for fine-grained categorization","venue":null,"work_id":"85675c53-9933-460a-ba17-222b3854eeac","year":2013},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.296014Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:9971e96edc490b2da8c7021646c9762c832cbbaf81750729fbd3bf33c1c7e062","observation_id":"1dafd15c-dde8-4a20-a3af-4305a897309f","resolution":{"observed_at":"2026-08-15T21:02:50.115962Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T21:02:49.299249Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.299249Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:e25f6a52e0a6ec38da98626017790327753eab96c72ddf16fb907d26deeb248f","observation_id":"78e4d469-0acb-4dfb-ac0b-ece59feb5a98","resolution":{"observed_at":"2026-08-15T21:02:49.299249Z","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":"2026-08-15T21:02:50.070886Z","title":"Structured compression by weight encryption for unstructured pruning and quantization","venue":null,"work_id":"164fc914-4882-4900-9881-05d3ce49af9d","year":1909},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.302426Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:adfee7c3d97b38ee5d5f16908e9e0c508bfe6a1dd222ab74647cd0d65fbf55e1","observation_id":"64da730c-f7ae-4912-8a81-69fc828d2fb7","resolution":{"observed_at":"2026-08-15T21:02:50.075788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.03641","last_updated":"2024-07-23T06:19:21Z","snapshot_observed_at":"2026-08-19T08:58:58.577293Z","submitted_at":"2024-07-04T05:23:22Z","title":"Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.03641","snapshot_observed_at":"2026-08-15T21:02:49.305405Z","title":"Scalable learned model soup on a single gpu: An efficient subspace training strategy","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.305405Z"},"links":{"cited_paper":"/paper/2407.03641","citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:f20d94ffae74cffedc90e9a584c75dd7f7f5dcdd01ba1bd51cfeb08869828d5b","observation_id":"ce33e99e-f12c-47b3-8911-6b8c0012f999","resolution":{"observed_at":"2026-08-15T21:02:49.305405Z","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":"2026-08-15T21:02:49.308804Z","title":"Losparse: Structured compression of large language models based on low-rank and sparse approximation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.308804Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:e1c28545d24a0b3b0bedcb8719a51a2d1d10fe391d843d3d3533835840e2b761","observation_id":"c7d13a7e-9a92-4398-8fdd-cc26362a7a77","resolution":{"observed_at":"2026-08-15T21:02:49.308804Z","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":"2026-08-15T21:02:50.049621Z","title":"Can unstructured pruning reduce the depth in deep neural networks? In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1402--1406, 2023","venue":null,"work_id":"7d415fa2-8ba9-40fe-8e5b-9d12d3d7cc2a","year":2023},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.312065Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:adfda5d6476bcf736b3d38dffd6a0aec359f648a89ea7d41c0b7e2d7b139e560","observation_id":"59501d6e-41e1-474c-8809-ba64770045eb","resolution":{"observed_at":"2026-08-15T21:02:50.054156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.10193","last_updated":"2024-10-13T20:42:37Z","snapshot_observed_at":"2026-08-21T12:43:02.276605Z","submitted_at":"2024-02-15T18:50:06Z","title":"BitDelta: Your Fine-Tune May Only Be Worth One Bit","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.10193","snapshot_observed_at":"2026-08-15T21:02:49.315434Z","title":"Bitdelta: Your fine-tune may only be worth one bit","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.315434Z"},"links":{"cited_paper":"/paper/2402.10193","citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:4d8e905b93f6f01b7a1095ca7ac157b8863fe8ec89ba85ce235478492f447ef6","observation_id":"5caf369a-4ae3-4476-842b-d8976943cf1f","resolution":{"observed_at":"2026-08-15T21:02:49.315434Z","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":"2026-08-15T21:02:50.037555Z","title":"Post-training quantization for vision transformer","venue":null,"work_id":"d1012285-3185-482d-8ae3-3bc5c2d9b4ec","year":2021},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.320336Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:efb9085d565027930f110c7cedd20417f2abadc37d909bfd30747cbd48083252","observation_id":"75ecca4d-888e-4f1b-b7f3-8fbadf5a75b7","resolution":{"observed_at":"2026-08-15T21:02:50.041724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T21:02:49.324319Z","title":"The flan collection: Designing data and methods for effective instruction tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.324319Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:9582cff2a879ad2ba0399f9c243a5a5f81debbd851a2db6d84e7f3674ce893f8","observation_id":"846f1043-126a-4587-b279-86a4d53f95a3","resolution":{"observed_at":"2026-08-15T21:02:49.324319Z","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":"2026-08-15T21:02:49.328347Z","title":"Merging models with fisher-weighted averaging","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.328347Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:1f6fe476733e3c21c7c52a952ea4acdfd3bc47f0a112be028091949bf886cfd4","observation_id":"ca55bd1d-fa27-46c7-b99b-447794dfa0b1","resolution":{"observed_at":"2026-08-15T21:02:49.328347Z","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":"2026-08-15T21:02:49.331937Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.331937Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:8afd36179c235555fe4b8e94c3338bc092ad8e0ec610e6e52f0a74b9eae1188b","observation_id":"0ac06195-91b3-4d95-8d3e-121747435a9c","resolution":{"observed_at":"2026-08-15T21:02:49.331937Z","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":"2026-08-15T21:02:49.335595Z","title":"What is being transferred in transfer learning? Advances in neural information processing systems, 33: 0 512--523, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.335595Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:a521f35711c086ce3f0a6e9f7d9b0e84299509c355457e7c9a879cd93a9aaf5c","observation_id":"b2ad4a43-a71a-4f76-89b9-6b89cad6b315","resolution":{"observed_at":"2026-08-15T21:02:49.335595Z","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":"2026-08-15T21:02:49.338900Z","title":"Automated flower classification over a large number of classes","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.338900Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:0055bf676151c9a1a9eb5f9359c6dd78c2eba2728dafa7456d54a194c37d82a9","observation_id":"29f6c79f-3b65-4d5a-9803-03ba03393edd","resolution":{"observed_at":"2026-08-15T21:02:49.338900Z","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":"2026-08-15T21:02:49.342699Z","title":"Task arithmetic in the tangent space: Improved editing of pre-trained models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.342699Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:6b6829bacad4a68341e4ede7e886d0c85ea9b2acbce6eafc9edefc9ca75ef4fd","observation_id":"8839bdd1-7e3f-4ac6-90d4-657993fe8213","resolution":{"observed_at":"2026-08-15T21:02:49.342699Z","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":"2026-08-15T21:02:49.967142Z","title":"Relational knowledge distillation","venue":null,"work_id":"983dbbcd-18f5-47b9-8c98-5d0a6c41d434","year":2019},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.346254Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:668f3698b04570c3aa6cbb353ea04d3f40a2eaad2dbedd42a83ccd2e021f31d8","observation_id":"6cff0bc7-c120-49d9-92d6-cf18506e88fb","resolution":{"observed_at":"2026-08-15T21:02:49.970951Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T21:02:49.349891Z","title":"Cats and dogs","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.349891Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:f90741ca58400bd7256a24e7972af5496c283cac8f542f22fbc140718a358ca1","observation_id":"d1ca9fd3-e6cb-4a20-9378-b0484564c4df","resolution":{"observed_at":"2026-08-15T21:02:49.349891Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.08903","last_updated":"2024-11-26T08:50:52Z","snapshot_observed_at":"2026-08-19T05:34:35.749421Z","submitted_at":"2024-06-13T07:57:27Z","title":"Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.08903","snapshot_observed_at":"2026-08-15T21:02:49.353194Z","title":"Delta-come: Training-free delta-compression with mixed-precision for large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.353194Z"},"links":{"cited_paper":"/paper/2406.08903","citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:8cd227159a45b08617fc489bd649615ea44735b6afafde191ce770bef70dee2b","observation_id":"1497a052-df9e-4106-898d-9636f7186730","resolution":{"observed_at":"2026-08-15T21:02:49.353194Z","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":"2026-08-15T21:02:49.357035Z","title":"Language models are unsupervised multitask learners","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.357035Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:7582f1b1c15d7c05717e825c07518e506e3385142401166b1cbef2e7543f0478","observation_id":"7dd9f957-e0f9-4412-810e-4b4c5c4f05e2","resolution":{"observed_at":"2026-08-15T21:02:49.357035Z","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":"2026-08-15T21:02:49.360388Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.360388Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:9534730efa0819a3a04037bc5b8bbe01b7011dbc477a165ab9701ad181d0c0e7","observation_id":"84646c53-29bd-45d0-ae96-ce836f0a672d","resolution":{"observed_at":"2026-08-15T21:02:49.360388Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.18425","last_updated":"2023-05-28T21:10:22Z","snapshot_observed_at":"2026-08-18T11:39:32.716654Z","submitted_at":"2023-05-28T21:10:22Z","title":"Efficient Storage of Fine-Tuned Models via Low-Rank Approximation of Weight Residuals","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.18425","snapshot_observed_at":"2026-08-15T21:02:49.363941Z","title":"Efficient storage of fine-tuned models via low-rank approximation of weight residuals","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.363941Z"},"links":{"cited_paper":"/paper/2305.18425","citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:50ddf6958e3567a66f9686f5caef72ac217859b408ae2a0966c30983728be252","observation_id":"99c104d8-68ee-4858-a504-3114e9f08537","resolution":{"observed_at":"2026-08-15T21:02:49.363941Z","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":"2026-08-15T21:02:49.367647Z","title":"Recursive deep models for semantic compositionality over a sentiment treebank","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.367647Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:a6fe8df65cb36004bbb161209e76ff91e2b7021d5e4a06e9f56bb01e5f1a727e","observation_id":"a0085ca6-0303-49fa-905a-fa9148ec5f66","resolution":{"observed_at":"2026-08-15T21:02:49.367647Z","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":"2026-08-15T21:02:49.925648Z","title":null,"venue":null,"work_id":"63107a14-ce71-41c3-86b2-cb2f606687cd","year":2012},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.371570Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:36f99d5292167a1a2d947fd473e1036aab6be9c4309e9a4be5e667e7b37ab756","observation_id":"020f9f46-72f5-4b48-be2a-3ce47b9e24ea","resolution":{"observed_at":"2026-08-15T21:02:49.929591Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T21:02:49.375208Z","title":"Fusionbench: A comprehensive benchmark of deep model fusion","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.375208Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:6432dba7502866c54369d78db2cba461b927dfa65bf3bb118304ef8e6b12fedd","observation_id":"9ff8ab22-ec49-4f64-9fa0-6a5451475dcc","resolution":{"observed_at":"2026-08-15T21:02:49.375208Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.10174","last_updated":"2024-08-26T07:34:46Z","snapshot_observed_at":"2026-08-16T13:25:26.752785Z","submitted_at":"2024-08-19T17:32:15Z","title":"SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.10174","snapshot_observed_at":"2026-08-15T21:02:49.378675Z","title":"Smile: Zero-shot sparse mixture of low-rank experts construction from pre-trained foundation models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.378675Z"},"links":{"cited_paper":"/paper/2408.10174","citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:feceecb5b9aa4743af3e1f489bd6d3d0885c53c4d5f94c9f63669dbbb11aa25f","observation_id":"34517050-974c-4721-bc44-73533387c67e","resolution":{"observed_at":"2026-08-15T21:02:49.378675Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00433","last_updated":"2024-06-07T08:06:52Z","snapshot_observed_at":"2026-08-16T14:22:35.849436Z","submitted_at":"2024-02-01T08:58:57Z","title":"Merging Multi-Task Models via Weight-Ensembling Mixture of Experts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00433","snapshot_observed_at":"2026-08-15T21:02:49.382521Z","title":"Merging multi-task models via weight-ensembling mixture of experts","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.382521Z"},"links":{"cited_paper":"/paper/2402.00433","citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:3b134f0361e20bddc53790cb1ab888bd8d568f8f9e784c6469b7797b01dfa8b3","observation_id":"efb3267d-f4e1-441e-a68b-b9bbf01115a8","resolution":{"observed_at":"2026-08-15T21:02:49.382521Z","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":"2026-08-15T21:02:49.911163Z","title":"Rotation equivariant cnns for digital pathology","venue":null,"work_id":"c6e9892d-f3fb-4b04-b366-3b80336f6805","year":2018},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.386295Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:7916fe9bd815a53583a59cdbf0759924b2abcb8017a6fe35ac9f34efa77ba796","observation_id":"eab6bde7-04b5-4208-ad00-4686fa6606d4","resolution":{"observed_at":"2026-08-15T21:02:49.915391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.02852","last_updated":"2022-07-05T20:55:38Z","snapshot_observed_at":"2026-08-16T16:48:07.135932Z","submitted_at":"2022-07-05T20:55:38Z","title":"Machine Learning Model Sizes and the Parameter Gap","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.02852","snapshot_observed_at":"2026-08-15T21:02:49.390544Z","title":"Machine learning model sizes and the parameter gap","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.390544Z"},"links":{"cited_paper":"/paper/2207.02852","citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:3d20c598a75ce851714dbe9a2e6bceb17d6f48c332e4c1c941bdb46b5c9650b4","observation_id":"08e07525-72d9-4f3f-a194-611aeefdff20","resolution":{"observed_at":"2026-08-15T21:02:49.390544Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.07461","last_updated":"2019-02-22T23:53:34Z","snapshot_observed_at":"2026-08-16T09:50:11.319379Z","submitted_at":"2018-04-20T06:35:04Z","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.07461","snapshot_observed_at":"2026-08-15T21:02:49.394629Z","title":"Glue: A multi-task benchmark and analysis platform for natural language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.394629Z"},"links":{"cited_paper":"/paper/1804.07461","citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:f64014b44fcb2c874898f52d6605786724099e0821de7d41dd2a1a1b51f401a5","observation_id":"83d2bd49-9c08-4b1b-a21d-27f5d76c7d3f","resolution":{"observed_at":"2026-08-15T21:02:49.394629Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.07813","last_updated":"2024-05-13T14:54:37Z","snapshot_observed_at":"2026-08-19T13:56:53.837038Z","submitted_at":"2024-05-13T14:54:37Z","title":"Localizing Task Information for Improved Model Merging and Compression","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.07813","snapshot_observed_at":"2026-08-15T21:02:49.398493Z","title":"Localizing task information for improved model merging and compression","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.398493Z"},"links":{"cited_paper":"/paper/2405.07813","citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:41cbd090ac9b692c49760c7a19466a0c509a9a4abfdcea4447dc66480b84ce3c","observation_id":"05c7037e-8f52-4143-a486-1ccd3ce4c4ca","resolution":{"observed_at":"2026-08-15T21:02:49.398493Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.04732","last_updated":"2021-03-28T19:04:25Z","snapshot_observed_at":"2026-08-14T00:39:23.744952Z","submitted_at":"2019-10-10T17:44:18Z","title":"Structured Pruning of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.04732","snapshot_observed_at":"2026-08-15T21:02:49.403695Z","title":"Structured pruning of large language models","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.403695Z"},"links":{"cited_paper":"/paper/1910.04732","citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:5e7445751f7c5af04329023ad7672efc01ad021e244952f672908d13dda70190","observation_id":"08954015-7cd2-4680-bd0f-cd6a22bb2d63","resolution":{"observed_at":"2026-08-15T21:02:49.403695Z","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":"2026-08-15T21:02:49.407091Z","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.407091Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:2ffb7f5e1ccc6b5501d44e2d3585678f3e4ff3225342de4644bb85d8154c1533","observation_id":"1dbd6475-6a97-4d1f-8912-20baad640865","resolution":{"observed_at":"2026-08-15T21:02:49.407091Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-08-13T15:13:33.081929Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-15T21:02:49.410329Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.410329Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:ccb72eb77d281870dd2490917eb27b66d83e7347b210d47ff9aca644c7c79ada","observation_id":"75f0d2ea-1abb-4058-8169-f266d22e8c96","resolution":{"observed_at":"2026-08-15T21:02:49.410329Z","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":"2026-08-15T21:02:49.413448Z","title":"Ehinger, Aude Oliva, and Antonio Torralba","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.413448Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:21c88b4dc3ee274aecac0b2b43b7d25dd6876842970f5a3c1aa050d92bf03548","observation_id":"59c3436e-080d-4364-b90d-c0162468a59a","resolution":{"observed_at":"2026-08-15T21:02:49.413448Z","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":"2026-08-15T21:02:49.416843Z","title":"Ties-merging: Resolving interference when merging models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.416843Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:4871a649fc9abc95267be42882823e225ff1803c666d1c506974691e2a63f8d6","observation_id":"a657afef-66c5-4034-99c9-2914ad6ff182","resolution":{"observed_at":"2026-08-15T21:02:49.416843Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02575","last_updated":"2024-05-28T06:42:31Z","snapshot_observed_at":"2026-08-16T14:55:15.252360Z","submitted_at":"2023-10-04T04:26:33Z","title":"AdaMerging: Adaptive Model Merging for Multi-Task Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.02575","snapshot_observed_at":"2026-08-15T21:02:49.419908Z","title":"Adamerging: Adaptive model merging for multi-task learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.419908Z"},"links":{"cited_paper":"/paper/2310.02575","citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:3331e6250e04b6fe1c7c51840165ed9c40ac9aceef079eb15d1db6d4bb63c138","observation_id":"3562587e-a1fc-41bc-86c8-bc080ceab0f7","resolution":{"observed_at":"2026-08-15T21:02:49.419908Z","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":"2026-08-15T21:02:49.423267Z","title":"Language models are super mario: Absorbing abilities from homologous models as a free lunch","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.423267Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:d4dfe5cc62be11a1c626766f48891a1290bc1dad6f40cff7470a3850377eb958","observation_id":"204ad4d4-3248-4de1-88f4-3714a506b854","resolution":{"observed_at":"2026-08-15T21:02:49.423267Z","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":"2026-08-15T21:02:49.868190Z","title":"On compressing deep models by low rank and sparse decomposition","venue":null,"work_id":"0418fc2d-2f29-4c4f-a210-0eb8e74cd72a","year":2017},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.426857Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:33ef7ff10f4351ef4a5ba3747ba6cc0e3506f9b6946a43cc8abb4455122f88c5","observation_id":"b6ed2f2a-11f6-49c5-a1e1-52251f0b0b9a","resolution":{"observed_at":"2026-08-15T21:02:49.875016Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T21:02:49.851309Z","title":"Ptq4vit: Post-training quantization for vision transformers with twin uniform quantization","venue":null,"work_id":"7c38d122-b8b1-4754-adae-ed30e66fcc56","year":2022},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.430995Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:1ea6bef3e160b78fb56c6f069cd6aa064da4ac3e84b8bb77b8e92f34677ea550","observation_id":"f644a6da-e966-4943-be86-b902d55e2619","resolution":{"observed_at":"2026-08-15T21:02:49.856296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T21:02:49.836002Z","title":"Decoupled knowledge distillation","venue":null,"work_id":"29e41d31-f4ad-4061-b345-65c0b1e2f4aa","year":2022},"citing_paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-15T21:02:49.434805Z"},"links":{"citing_paper":"/paper/2505.11204"},"observation_digest":"sha256:f254258a20c02513cdb00a0cd70b6543147026304b14ee4bdcb38184d8ae086a","observation_id":"2ac57300-169f-4989-8d62-7e0c8ec6e504","resolution":{"observed_at":"2026-08-15T21:02:49.841376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.11204","last_updated":"2025-05-16T13:02:12Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-21T10:44:40.605368Z","submitted_at":"2025-05-16T13:02:12Z","title":"RanDeS: Randomized Delta Superposition for Multi-Model Compression"},"reference_resolution":{"displayed":60,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":43,"verified_exact":0,"verified_fuzzy":17},"total_outbound_references":60},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 60 of 60 outbound references and 0 inbound Pith citation observations for arXiv:2505.11204."}