{"as_of":"2026-08-21T22:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d5e55ad6c614cbc930b73d72c6a5bdde9866e1a11f290c64e129932c69757dff","coverage":[{"denominator":84,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":84,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:09:48.773621Z","state":"measured"},{"denominator":84,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":84,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2506.03391/citation-record","integrity":"/paper/2506.03391/integrity","json":"/paper/2506.03391/citation-record.json","paper":"/paper/2506.03391"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-17T09:58:46.058102Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-07T11:09:46.415015Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:46.415015Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:10dfc08090ceb0f733ed02f32df2223f5ac111d67ecf4a1fd267d0733c257576","observation_id":"0df3d952-d0f0-4189-b107-47003f320b3a","resolution":{"observed_at":"2026-08-07T11:09:46.415015Z","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":"2026-08-07T11:09:46.491051Z","title":"Adomavicius and A","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:46.491051Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:80066870109dcb0fda9394353baba2b236167f79917e6ef1c9c6ec1db58a1f8c","observation_id":"a0cf46a8-a787-4212-8500-0bb13834b40e","resolution":{"observed_at":"2026-08-07T11:09:46.491051Z","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":"2026-08-07T11:09:46.589039Z","title":"Auto-surprise: An automated recommender-system (autorecsys) library with tree of parzens estimator (tpe) optimization","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:46.589039Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:d0635955dffd282a5ccda1d9dd68f9b2c2006d9569f116de71f45b2330bbe401","observation_id":"3b542a2c-b7b4-4fd0-918e-49fc566b1fb5","resolution":{"observed_at":"2026-08-07T11:09:46.589039Z","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":"2026-08-07T11:09:46.706661Z","title":"Elliot: A comprehensive and rigorous framework for reproducible recommender systems evaluation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:46.706661Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:9a5eb9d96a8845887cf16c3c8c09067dcb20809d3b0d0e9b890e89d46ddd3aba","observation_id":"2da8ae15-3cbe-4cd4-829d-7d52871140d2","resolution":{"observed_at":"2026-08-07T11:09:46.706661Z","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":"2026-08-07T11:09:46.788257Z","title":"Exploiting graph structured cross-domain representation for multi-domain recommendation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:46.788257Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:92dcb5c6b5de158c3fa1698f2ee7174d5766222ddb204e53043bc91154482d4c","observation_id":"dcfd9e41-b664-4ed3-9a68-67462c59e9dc","resolution":{"observed_at":"2026-08-07T11:09:46.788257Z","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":"2026-08-07T11:09:49.601006Z","title":"Fab: content-based, collaborative recommendation","venue":null,"work_id":"32ae0059-5e20-42ac-a821-5d4e9463360c","year":1997},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:46.869704Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:d3cf4c81854ddd5990a10fd6e0ccc3ce1b0381bb7043c3050f7a34f9456cc06d","observation_id":"38056e1e-97d8-430b-8db1-da5974a2de4b","resolution":{"observed_at":"2026-08-07T11:09:49.604226Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:47.003301Z","title":"Tallrec: An effective and efficient tuning framework to align large language model with recommendation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:47.003301Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:818df04b021447ac23687728e9f0c9d22e18bb98df8c91cf0190d5518b0db66a","observation_id":"d3ac1039-04fa-4990-b0f3-f9f1be8fbfe7","resolution":{"observed_at":"2026-08-07T11:09:47.003301Z","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":"2026-08-07T11:09:49.584791Z","title":"Hyperopt: a python library for model selection and hyperparameter optimization","venue":null,"work_id":"7582428d-4fc9-473b-bbfc-5c733a893127","year":2015},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:47.141805Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:fe6255117edc68387ee3526ade4b84717b9f7c134dcbfbe7c8b0f3555b98cb14","observation_id":"6bdff0e3-dfb7-4da7-a2b4-9cbe16e86876","resolution":{"observed_at":"2026-08-07T11:09:49.588679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:47.302136Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:47.302136Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:2653a3e9bc61296ad36e660961041d2e063e24441be2c8f7b583909e1124e432","observation_id":"e01bce2b-8c77-4169-ba61-c15d6a23444c","resolution":{"observed_at":"2026-08-07T11:09:47.302136Z","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":"2026-08-07T11:09:49.568434Z","title":"Hybrid recommender systems: Survey and experiments","venue":null,"work_id":"75e75abe-8f4d-43f9-a147-5263a31f60bd","year":2002},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:47.426644Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:cfcfdf0613e8a26b21535e85e9f69b5ef5a7928b902ae5d70892e330e5bb0bb1","observation_id":"d6e030f4-d666-4c6b-902a-af7ec24eecd6","resolution":{"observed_at":"2026-08-07T11:09:49.571857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.557465Z","title":"A system- atic study on reproducibility of reinforcement learning in recommendation systems","venue":null,"work_id":"06ab201c-9560-4668-a163-8432e3b68d27","year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:47.551917Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:869b7857a70eabb61cc42928d7a2c62c71cfb485db0a4c93ef4626fb34cc626f","observation_id":"b576e7e5-5315-42ff-908c-e84cc2e404b1","resolution":{"observed_at":"2026-08-07T11:09:49.561732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.546488Z","title":"Pefa: Parameter-free adapters for large-scale embedding-based retrieval models","venue":null,"work_id":"2e0cfc1f-7d9c-4ff0-82c6-d75110729c0e","year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:47.693259Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:5e69fb13c7bc82e7caebb1ff416ea9b2a8758f0e6d83479738508ed330707fe2","observation_id":"0f07467b-ef4f-4503-966a-5c4dbc79870d","resolution":{"observed_at":"2026-08-07T11:09:49.550695Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.535846Z","title":"A comprehensive survey on automated machine learning for recommendations.ACM Transactions on Recommender Systems, 2(2):1–38, 2024","venue":null,"work_id":"88a2dd22-8bad-4dc4-917e-740765eb2025","year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:47.820620Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:4a3ceff0e088bc164116e889e8accd1f765ad8673ed9326df8c9ed52fc5bd55a","observation_id":"30245745-5153-412f-82f6-53795af6fc3e","resolution":{"observed_at":"2026-08-07T11:09:49.539850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.524575Z","title":"Neural feature search: A neural architecture for automated feature engineering","venue":null,"work_id":"efff56db-6026-46cd-bd51-aa810b655a08","year":2019},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:47.866415Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:a6ed9601e56de24b612409ccaf33143b489c3c6f023c8ab1717a9a10d52d7bae","observation_id":"398a7e7d-621d-4e06-978b-c343792fbea5","resolution":{"observed_at":"2026-08-07T11:09:49.529016Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.513867Z","title":"Uncovering chatgpt’s capabilities in recommender systems","venue":null,"work_id":"aa7c24d3-8100-4db9-b720-efddcf000512","year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:47.972763Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:cf8dcc3ba509b37146be4d992ea8c0589fbadffbf940ba455c9f8aa0dc7d9317","observation_id":"8d076621-2d6d-473c-91d8-b421c0f2a089","resolution":{"observed_at":"2026-08-07T11:09:49.517367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.502728Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":"1fa3973b-7c3f-40ff-98ca-c5b40963037d","year":2019},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.075851Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:2e4965782135ad3b0e52bf1176fb8351bed3bf86c9798a2d89c801c2effebcaa","observation_id":"55b5ba47-8e6e-425c-ba88-38dca20d8e0c","resolution":{"observed_at":"2026-08-07T11:09:49.507315Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-07T11:09:48.138372Z","title":"The llama 3 herd of models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.138372Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:ab0ec712642ef13460bafb192b1db2e847567de3155bfe45760d6388b02b1655","observation_id":"4b057978-6dd7-4fdf-af51-c57bd43b1e34","resolution":{"observed_at":"2026-08-07T11:09:48.138372Z","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":"2026-08-07T11:09:49.493148Z","title":"Lenskit: a modular recommender framework","venue":null,"work_id":"66357379-82b2-4da9-944b-e641ad6eb789","year":2011},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.192521Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:36b4810448acd91a3bbfc353eac9ee642e0230687002391d0e4b4c1d8a7173a4","observation_id":"0048cc5f-a6f7-4768-a821-7aef91f8bcc2","resolution":{"observed_at":"2026-08-07T11:09:49.496407Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:48.221895Z","title":"Neural architecture search: A survey","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.221895Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:c955198cf23f6e914393f0b2fb32b1d8035d7115c8d8e2c6335941624c27f6af","observation_id":"c41b97ef-58e4-4515-905e-af59968aca5c","resolution":{"observed_at":"2026-08-07T11:09:48.221895Z","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":"2026-08-07T11:09:49.477821Z","title":"Are we really making much progress? a worrying analysis of recent neural recommendation approaches","venue":null,"work_id":"0563f16f-8d8a-4a6f-9054-d6de45337580","year":2019},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.277371Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:2d996d53a901e9901ab306c84baf6559606b31474be58e771a8a9a89c1e19f5c","observation_id":"1f9d501e-3a9a-48e0-bd01-052c4125802e","resolution":{"observed_at":"2026-08-07T11:09:49.481360Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.468063Z","title":"Cross- domain meta-learner for cold-start recommendation","venue":null,"work_id":"4b2e4cfa-cbd6-4e9a-bcb9-65ef3cbc27f2","year":2022},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.337448Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:fa34f4fb970d44d372e1ffb39be59dd97e241bd24dffa7d47704cfb70fe742af","observation_id":"353b20d2-b510-46de-a365-0b7daa90edaf","resolution":{"observed_at":"2026-08-07T11:09:49.471570Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-08-15T12:33:55.451951Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-07T11:09:48.372501Z","title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.372501Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:50f5464b6004c020f70ade5b82672b2997fbcd9f5a21a181a0dc32f61c3a7300","observation_id":"23963dcb-5a96-4b8d-9288-8dc0a3a3b277","resolution":{"observed_at":"2026-08-07T11:09:48.372501Z","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":"2026-08-07T11:09:49.457955Z","title":"The effect of third party implementations on reproducibil- ity","venue":null,"work_id":"5ebe724b-ff3a-4ddc-b166-d3bc11ed6927","year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.458321Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:d1ffa9575106e503525180817da006a3cf0578952bd14553f49ec3e5418e8a22","observation_id":"910c0d4d-1179-44fd-8825-7aaba4a9a0ca","resolution":{"observed_at":"2026-08-07T11:09:49.461827Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:48.502493Z","title":"The autofeat python library for automated feature engineering and selection","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.502493Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:31d9bf5f201f174e51f6952927259bbde9c240aec2f52d503a528895c20b1f55","observation_id":"4a3428a4-df4c-4e7f-bf17-5cf07ae2eb1e","resolution":{"observed_at":"2026-08-07T11:09:48.502493Z","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":"2026-08-07T11:09:49.440983Z","title":"Ecat: A entire space continual and adaptive transfer learning framework for cross-domain recommendation","venue":null,"work_id":"abdb4354-630b-4095-8f0f-e3e117cbd60b","year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.572006Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:f1e88de530fb66c302f597f22cccd06f8865aa92be614f7a6d7bd944cdf68e80","observation_id":"6bcd4ac3-0599-4400-879c-4299cb9768e8","resolution":{"observed_at":"2026-08-07T11:09:49.445047Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.431306Z","title":"Collaborative filtering for implicit feedback datasets","venue":null,"work_id":"4d472b42-0314-41dd-a4e9-9cba0e47f5ef","year":2008},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.585069Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:7e1f37d978a4679865c3c414973d2a4c1285003d54c9a33f04a06d42976c69df","observation_id":"fd300cc2-8ef8-4932-8654-1ec90c708ec9","resolution":{"observed_at":"2026-08-07T11:09:49.434831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.420896Z","title":"Self-supervised contrastive enhancement with symmetric few-shot learning towers for cold-start news recom- mendation","venue":null,"work_id":"245d7933-3d50-4107-a506-27f5cb509593","year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.592635Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:8f5d37b998ac624cba34466b0e3a99f60aaad13c7504e736c6e83e4f517d1d30","observation_id":"2a197e12-717c-4a26-be74-1ab298e9c36b","resolution":{"observed_at":"2026-08-07T11:09:49.424535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.411111Z","title":"Knowledge- aware cross-semantic alignment for domain-level zero-shot recommendation","venue":null,"work_id":"94465016-6431-4a48-898d-0e18b42bba5d","year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.596488Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:18baf0e7e32e1a7b85e219cb72f801427e14d9a3273266ab2d0fae8f72806f4c","observation_id":"f4ea4bb4-62e2-40f6-a7e8-76cb402f20fe","resolution":{"observed_at":"2026-08-07T11:09:49.414558Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.400845Z","title":"Automatic multi-task learning framework with neural architecture search in recommendations","venue":null,"work_id":"56767789-d261-42c9-ba29-3080f4b0a344","year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.599469Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:9a24f8e728d93ea186823b29e577a3912dada8926c3c641ae0f98fb8a204f1dd","observation_id":"69095090-d28b-4a40-8ddd-79ba1e0e3af5","resolution":{"observed_at":"2026-08-07T11:09:49.404810Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.391316Z","title":"Neural input search for large scale recommendation models","venue":null,"work_id":"c4d245e0-1ad3-468f-827c-0dec390e0a97","year":2020},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.602740Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:1d9a758f70fed11e3ddc13d444c5aae5ca8b7336608aec871d6c78e71d387e5f","observation_id":"3ae2b6e3-c129-4504-b05c-68faa87bee2f","resolution":{"observed_at":"2026-08-07T11:09:49.394677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.381439Z","title":"Large language models meet collaborative filtering: An efficient all-round llm-based recommender system","venue":null,"work_id":"6781a347-c38d-4cd8-9881-56c8b16f9958","year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.605865Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:5bde9346b8a9c34c43f51f9938c4dea7834e98e794ef9e0cfc105f58caf397d8","observation_id":"b12af8cf-03a2-4c33-a906-50d9f60e1edf","resolution":{"observed_at":"2026-08-07T11:09:49.384906Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:48.609436Z","title":"Large language models are zero-shot reasoners","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.609436Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:a1fb362e5a602cfea8f1f044f845659a73b46b05cb8ffdbbca4186a5c89529b0","observation_id":"19ba1f51-0091-46da-b20c-97ef920404b9","resolution":{"observed_at":"2026-08-07T11:09:48.609436Z","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":"2026-08-07T11:09:48.612901Z","title":"Matrix factorization techniques for recom- mender systems","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.612901Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:66e1f7313b60c468e14dab76d8fb0968b270b3f90b3a6affc79bf40a264a710c","observation_id":"061d01bc-90b3-4d83-b700-6216f9681502","resolution":{"observed_at":"2026-08-07T11:09:48.612901Z","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":"2026-08-07T11:09:48.615812Z","title":"Advances in collaborative filtering","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.615812Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:5804470ef62fedc379977811df2cf00562b655de922aa53052e695ec6c8cd1c9","observation_id":"521c50d4-e4ff-4fdc-be4f-325c29979bd5","resolution":{"observed_at":"2026-08-07T11:09:48.615812Z","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":"2026-08-07T11:09:49.351218Z","title":"Auto- weka 2.0: Automatic model selection and hyperparameter optimization in weka","venue":null,"work_id":"fbb8945a-9ab4-4195-bf1e-d4d145c8f0b7","year":2017},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.619025Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:4ebcd97cc370235cd8a099bca7fdf58f9162dcdb1a59970f91d31af0c59d051d","observation_id":"ee2e084a-093f-4bb8-9800-9150482326e2","resolution":{"observed_at":"2026-08-07T11:09:49.356052Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.340268Z","title":"Melu: Meta-learned user preference estimator for cold-start recommendation","venue":null,"work_id":"8148dab1-6800-45e1-a0ef-eb4eb3e9f0de","year":2019},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.622264Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:4bed7ba48cb3d3f37bf795b8048f85dcd1c05032f1967f70ad8a27a5ee9143e6","observation_id":"7018908d-bc6b-487d-a4a0-bae9593bab18","resolution":{"observed_at":"2026-08-07T11:09:49.343928Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.329681Z","title":"Prompt distillation for efficient llm-based recommenda- tion","venue":null,"work_id":"e01f8f55-96a3-4916-ac6d-04c8adef9209","year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.625292Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:1aaa686eee2b702b25d714def2e33cce9d9a1a6a84e2580ca9cf9de9c5238bff","observation_id":"9b7464c9-19b1-4d1a-b679-0b233b5859eb","resolution":{"observed_at":"2026-08-07T11:09:49.333579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.318342Z","title":"Automlp: Automated mlp for sequential recommendations","venue":null,"work_id":"9bdb5d06-771b-465e-8cd3-906d9e551347","year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.628572Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:547b96a166d133ccdea6b5985defbaf35a95c81d3873391171c097054c586fd3","observation_id":"eb8a6554-6bcb-467c-ae9e-6d0fff25d438","resolution":{"observed_at":"2026-08-07T11:09:49.322500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.307466Z","title":"Recai: Leveraging large language models for next-generation recommender systems","venue":null,"work_id":"5eb44bc3-1899-4bc3-ac29-faad1c3490c3","year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.631457Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:94fd0da33a6ae985adf993f157804133237330a77638a357202c52fad34eb0ab","observation_id":"6863f256-6b3e-46de-88fc-c28b0b200d47","resolution":{"observed_at":"2026-08-07T11:09:49.311706Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:48.634784Z","title":"Llara: Large language-recommendation assistant","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.634784Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:3d7585097780731b9e478b41cf0077126955e754562008b78ee620bec10d069f","observation_id":"ade655fe-7e2b-4492-b2db-e76869c5a827","resolution":{"observed_at":"2026-08-07T11:09:48.634784Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.05118","last_updated":"2018-07-13T15:00:17Z","snapshot_observed_at":"2026-08-19T20:35:38.129629Z","submitted_at":"2018-07-13T15:00:17Z","title":"Tune: A Research Platform for Distributed Model Selection and Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.05118","snapshot_observed_at":"2026-08-07T11:09:48.637568Z","title":"Tune: A research platform for distributed model selection and training","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.637568Z"},"links":{"cited_paper":"/paper/1807.05118","citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:a57d8eb1d7fb980bdd3742740fe04f595fb519e02347238c23509c5505620613","observation_id":"ac5f61e5-d2d5-40f9-9937-727b463e0534","resolution":{"observed_at":"2026-08-07T11:09:48.637568Z","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":"2026-08-07T11:09:49.290859Z","title":"DARTS: differentiable architecture search","venue":null,"work_id":"72a77f2a-3cfe-45c8-88f9-38933f6ee181","year":2019},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.641271Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:d0fb2b3cc1f1e44b055fc6b84189f321c595468002d8b013780d6e101f14818e","observation_id":"6aabdc36-1855-4e69-9c02-072a2d3d89c8","resolution":{"observed_at":"2026-08-07T11:09:49.294840Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.280093Z","title":"Automated feature selection: A reinforcement learning perspective","venue":null,"work_id":"a97f6355-0499-467c-8868-79e553e2024b","year":2021},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.644746Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:9e1a88fb0e88a720bf5e67cf457cb5bdcad9879106c7e490b2b6f2cf4e57e8ea","observation_id":"f8f380dc-b79a-458b-a046-5abbbd16b559","resolution":{"observed_at":"2026-08-07T11:09:49.283829Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.269340Z","title":"Online Meta-Learning for Model Update Aggregation in Federated Learning for Click-Through Rate Prediction","venue":null,"work_id":"20cecd79-5855-4e90-9d8f-d9258f64f92d","year":2022},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.647636Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:8b99e68cf18b3c7047e1aeee2c2dde6f5d4e3c58f28b089e45e31255f58f24c2","observation_id":"df4a8145-a5c0-4806-a212-2c8219917b1b","resolution":{"observed_at":"2026-08-07T11:09:49.272895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.258267Z","title":"Content-based recommender systems: State of the art and trends","venue":null,"work_id":"1d75a07b-d0e8-4984-9a51-b53b85be87ef","year":2011},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.650682Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:b639074a4b09766333311b9700e3eb900d5dc0b57ff32d820e02d15b801426bc","observation_id":"c3f584da-0e05-4d58-8670-cb7116074327","resolution":{"observed_at":"2026-08-07T11:09:49.262516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.244632Z","title":"Bayesian optimization for automated model selection","venue":null,"work_id":"2a2cdf04-d259-4eb1-9695-d2e6962a37a2","year":2016},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.653756Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:6a50438c45b721e7f335a391dec3a6c642680a5012a9e0c21e7b8a4c6d5273e5","observation_id":"2e94b7e5-faf1-42d5-a475-521f7e0f6a0e","resolution":{"observed_at":"2026-08-07T11:09:49.249681Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.232716Z","title":"Recpack: An (other) experimentation toolkit for top-n recommendation using implicit feedback data","venue":null,"work_id":"71cb34b6-74c4-49a4-a1cc-bbc5119edc8a","year":2022},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.657147Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:a66b0c413a7e8c3e5ebbbf4f2aecfc71fd335dbf7ed61c41a1d66dc0dd38e5e7","observation_id":"d218ca4d-89c9-4864-848b-7a85833374d3","resolution":{"observed_at":"2026-08-07T11:09:49.237442Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.221687Z","title":"Ctr-bert: Cost-effective knowledge distillation for billion-parameter teacher models","venue":null,"work_id":"8d2e9280-077a-4aa2-899a-0df5a2cea0f9","year":2021},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.660093Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:7e739158fba64a3a4e259fcc52543cb6e5fcec5ab9fc5213ea253ef772435054","observation_id":"a582ce71-64fb-4b85-a09b-f135a05d6cc3","resolution":{"observed_at":"2026-08-07T11:09:49.225512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.210400Z","title":"The elephant in the room: Rethinking the usage of pre-trained language model in sequential recommendation","venue":null,"work_id":"22a4fa2b-cbce-40b0-8385-184cb80d4f47","year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.663442Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:32018aeea02b183a2557db9c97801ddaa624556177e95869e863c1250d5c30f5","observation_id":"2774ad75-79cd-4405-a30e-3659b9a82607","resolution":{"observed_at":"2026-08-07T11:09:49.214549Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.199772Z","title":"Cornac: A comparative framework for multimodal recommender systems","venue":null,"work_id":"cea03ba2-b0e9-47a2-87be-d182c0918a0f","year":2020},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.666448Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:472abe1d9b0ac831ea369d3a7cd24ad8c1a7cbdfa0a35e5ee10f787b1475c21b","observation_id":"e534c5be-93d3-4387-a4e6-7fe8c4c08a20","resolution":{"observed_at":"2026-08-07T11:09:49.203743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:48.669534Z","title":"Item-based collaborative filtering recommendation algorithms","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.669534Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:9701fccc1f8832395a16b34c93c051c7d974b2eba673d3f93abb750212b78fff","observation_id":"8071370a-768c-4706-a27c-18fce4a52d54","resolution":{"observed_at":"2026-08-07T11:09:48.669534Z","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":"2026-08-07T11:09:49.181384Z","title":"Selecting a classification method by cross-validation","venue":null,"work_id":"eae9195e-1bc1-4be9-82c5-85e6130ee91c","year":1993},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.673131Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:3d248bb6b6dcf4526ac68b90f35c9ce58f4e6660d7b38ab579eb0b25f9e7165b","observation_id":"d26e15c7-ea7a-4f00-9555-12a288c0bb6b","resolution":{"observed_at":"2026-08-07T11:09:49.185810Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.170292Z","title":"Autorec: Autoencoders meet collaborative filtering","venue":null,"work_id":"5ee83240-56f5-46dc-ad52-353d3b4df185","year":2015},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.676072Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:90214cc7dbada5797529a283a3cadf9ed5487836186171d50eb088c9f2e7950b","observation_id":"09d220b3-464e-47b0-bf6b-8a87108b1ecc","resolution":{"observed_at":"2026-08-07T11:09:49.174285Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.05526","last_updated":"2024-09-10T16:46:10Z","snapshot_observed_at":"2026-08-19T08:24:39.293475Z","submitted_at":"2024-09-09T11:35:35Z","title":"RBoard: A Unified Platform for Reproducible and Reusable Recommender System Benchmarks","version":2},"cited_work":{"arxiv_id":"2409.05526","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.05526","snapshot_observed_at":"2026-08-07T11:09:48.847806Z","title":"RBoard: A Unified Platform for Reproducible and Reusable Recommender System Benchmarks","venue":"cs.IR","work_id":"a69e660a-99bf-421b-9c00-dfd28c515b27","year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.679168Z"},"links":{"cited_paper":"/paper/2409.05526","citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:6e0e595aaf12eb0366f3ffe6bfd15f0a0221c5d6a4dd12bb76cba540ce4cdc76","observation_id":"76c94cca-c0bf-4fd7-94ff-e0423454e88e","resolution":{"observed_at":"2026-08-07T11:09:48.851235Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.159168Z","title":"Librec-auto: A tool for recommender systems experimen- tation","venue":null,"work_id":"edc7ec3b-068b-47a5-b637-086d1563af80","year":2021},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.682766Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:82faefadc6776c174dde1cf4537f45cc95eba6849b471abdb5604313dfee56b3","observation_id":"9b2c0a11-bc50-4cc6-b334-a80512cf4ae6","resolution":{"observed_at":"2026-08-07T11:09:49.163532Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.148245Z","title":"Large language models enhanced collaborative filtering","venue":null,"work_id":"d32a48f4-b84b-48a1-82f6-b5e753852362","year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.686341Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:24fefee7e194815bb4c2d918d64feb43502faf67e6ee3554c5a69a5798370e3f","observation_id":"b961286c-dfaf-4c2a-b68a-4e33579e4ecf","resolution":{"observed_at":"2026-08-07T11:09:49.152023Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.136857Z","title":"Are we evaluating rigorously? benchmarking recommendation for reproducible evaluation and fair comparison","venue":null,"work_id":"4280b6e1-010e-4e72-a0d6-94a0364532a7","year":2020},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.689135Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:df780794073f6a0981fb4dcb6974bf526c33a932dedb81b1ba2fa0d569647326","observation_id":"2dfb6037-9cfe-496e-971d-ec0a5bb84799","resolution":{"observed_at":"2026-08-07T11:09:49.140821Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-08-20T18:27:04.837880Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-08-07T11:09:48.692397Z","title":"Gemini: a family of highly capable multimodal models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.692397Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:f332801ac2226f9c752577ff94db79b195514d1e1edf1e1cd3ed4665e85bfefa","observation_id":"4ea85dd0-d06f-46f1-b54e-bc0ee4d052dc","resolution":{"observed_at":"2026-08-07T11:09:48.692397Z","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":"2026-08-07T11:09:49.126526Z","title":"A meta-learning perspective on cold-start recommendations for items","venue":null,"work_id":"0e0c0ea0-24fe-45b8-9b09-f6c23dcbc887","year":2017},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.696170Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:798b7bc78486c84bf21b345e8be249af782752e98d0b078d1ce3f993fff8e9dd","observation_id":"cb09d921-51dc-49b5-8829-db608c7cc53a","resolution":{"observed_at":"2026-08-07T11:09:49.130264Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.116654Z","title":"Introducing lenskit-auto, an experimental au- tomated recommender system (autorecsys) toolkit","venue":null,"work_id":"b830587a-bc2a-4b6e-b6e6-eb45efab1913","year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.699102Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:1e71c08ad0956a37def3da8fb7b3ef9445049846cac52660638442d9feb6ce3f","observation_id":"0a0fd474-9348-4687-92c9-817a84139846","resolution":{"observed_at":"2026-08-07T11:09:49.120185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.106658Z","title":"Autosr: Automatic sequen- tial recommendation system design","venue":null,"work_id":"d66a5be5-318f-4886-bf2a-0625b67e9d22","year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.702060Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:8ee54921e74d5e018cc9d8a3b098e258d438f5d47dc48c677c8ccf5a26c97138","observation_id":"54c48c9f-a7e3-4b07-8c09-afa69050dfa7","resolution":{"observed_at":"2026-08-07T11:09:49.110187Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.095892Z","title":"Sta: Self-controlled text augmentation for improving text classifications","venue":null,"work_id":"84a76675-7f99-4865-8b0e-b5bfcf94eb92","year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.705020Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:7f1563fd07c5065992fc281f1ceeb930ee8df8942cc35cdec1c59e126c8d29d4","observation_id":"d21e3eb6-5569-48ba-b9a0-7ea26cc2395a","resolution":{"observed_at":"2026-08-07T11:09:49.100000Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.084884Z","title":"A pre-trained zero-shot sequential recom- mendation framework via popularity dynamics","venue":null,"work_id":"b7a6aa51-18ab-48ce-a8f6-62f57c4db9d9","year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.707697Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:a37da368c0071af8232a42ecad78ebf22810abe691a9593aca76f85c9ca341b5","observation_id":"303398da-76da-43df-8b84-55d4397402fc","resolution":{"observed_at":"2026-08-07T11:09:49.088696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.073636Z","title":"Au- torec: An automated recommender system","venue":null,"work_id":"c47a0bb6-b299-4dae-8869-461fd5ee5e00","year":2020},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.711084Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:a5e6a5f06f5839e28076024a71d44014830ef4be62c41c99b877233a6509c6ec","observation_id":"ea171600-fac6-4afb-90c3-4782f592a24d","resolution":{"observed_at":"2026-08-07T11:09:49.077871Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.062950Z","title":"Automatic fea- ture selection by one-shot neural architecture search in recommendation systems","venue":null,"work_id":"2a48983c-e5b6-444f-9771-0ef76c3785ad","year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.714043Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:4e238779973b5aeec81e261020d4bb5c070a63b13a754775a6af011c16bf61b3","observation_id":"4e254681-6616-490b-b943-523f7cb50b32","resolution":{"observed_at":"2026-08-07T11:09:49.066753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:48.717025Z","title":"Llmrec: Large language models with graph augmentation for recommendation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.717025Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:00f6dc9a0d478ec67ae6d9585079c17dfc0f9dc586677c394fd17a8d08633b31","observation_id":"e751e354-6945-4c4d-943b-7eb4decb9f15","resolution":{"observed_at":"2026-08-07T11:09:48.717025Z","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":"2026-08-07T11:09:49.046020Z","title":"Reproduce, replicate, reevaluate","venue":null,"work_id":"c0383a11-25d6-4299-b66d-04700d17946e","year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.720078Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:8751a043b282e9e83f18878ca93ed8b0eadddeb535c871b9ff2bfa1e21b755be","observation_id":"b41f30fc-f34c-42c4-bc3e-f6d992b755b6","resolution":{"observed_at":"2026-08-07T11:09:49.049445Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.035538Z","title":"Loureiro","venue":null,"work_id":"7a536528-a261-4db8-88b9-32e75c1bbc4e","year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.723641Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:29bf7b0e0d239d593c706e7146c10c4d9e15644a57f03d59a1eb6b2ca7a440fd","observation_id":"9f48a966-bf78-42fd-9306-42de1f6e31e1","resolution":{"observed_at":"2026-08-07T11:09:49.038856Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.07294","last_updated":"2025-04-23T08:52:50Z","snapshot_observed_at":"2026-08-19T20:38:26.474316Z","submitted_at":"2025-01-13T13:01:00Z","title":"Dataset-Agnostic Recommender Systems","version":2},"cited_work":{"arxiv_id":"2501.07294","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.07294","snapshot_observed_at":"2026-08-07T11:09:48.821645Z","title":"Dataset-Agnostic Recommender Systems","venue":"cs.IR","work_id":"f6f9db96-603a-4e9c-b168-769613f9c57b","year":2025},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.727045Z"},"links":{"cited_paper":"/paper/2501.07294","citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:419abbb25817b6d53896ce7293be2d9820a4b9dff84e0f3e38cc36deb6b5946d","observation_id":"a16fc283-198b-4d2c-b1c0-d65648bf2911","resolution":{"observed_at":"2026-08-07T11:09:48.825889Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.024023Z","title":"Empowering news recommendation with pre-trained language models","venue":null,"work_id":"c81b8c09-17d5-49f4-9594-125e5ec7ab2c","year":2021},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.730454Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:65419c1d9a695788935623b0997485f0d4231debcf508ed34186dea1aecbbf94","observation_id":"dce9ce48-d00a-4d76-8e49-37e461bb4542","resolution":{"observed_at":"2026-08-07T11:09:49.028456Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.07222","last_updated":"2024-08-14T08:38:00Z","snapshot_observed_at":"2026-08-21T14:52:33.763573Z","submitted_at":"2023-08-14T15:47:36Z","title":"MM-GEF: Multi-modal representation meet collaborative filtering","version":2},"cited_work":{"arxiv_id":"2308.07222","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.07222","snapshot_observed_at":"2026-08-07T11:09:48.803470Z","title":"MM-GEF: Multi-modal representation meet collaborative filtering","venue":"cs.IR","work_id":"0f786216-5f0b-42b8-86d7-515f7ced6499","year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.733534Z"},"links":{"cited_paper":"/paper/2308.07222","citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:e29dc3754f79a1618f9da387b66609609fd66ae522444ef2b1c41cdf6a6d018a","observation_id":"e76d7bf6-7f60-4981-be33-3536bb01a07a","resolution":{"observed_at":"2026-08-07T11:09:48.808828Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:49.012008Z","title":"M2eu: Meta learning for cold-start recommendation via enhancing user preference estimation","venue":null,"work_id":"6c0b5951-15e6-42e6-a6a3-eb29803eef29","year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.736750Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:ed3cae4dcaaa1b70f0d4ce6cda1cdded1a79ad79e38a1c43db5ed9814ad2cc38","observation_id":"d671de3f-8d6e-477d-b78d-8bdd0d7d5292","resolution":{"observed_at":"2026-08-07T11:09:49.016111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:48.740083Z","title":"Towards open-world recommendation with knowledge augmentation from large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.740083Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:558b1711cb6ed965d65e36e2939e4a862a082b95de64f918d0bcd50e779ada3a","observation_id":"86545577-8ca1-4cc8-896f-50824f3366bd","resolution":{"observed_at":"2026-08-07T11:09:48.740083Z","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":"2026-08-07T11:09:48.993711Z","title":"Extreme meta-classification for large- scale zero-shot retrieval","venue":null,"work_id":"dbf99d28-9f30-4169-8646-62a595db9b88","year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.743980Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:a1db332f209a07c884d9b083aee6a3288d2d5c28509d8cc4f8b14a818d6c06fd","observation_id":"7dd99aff-a756-41ca-b9e9-57841b519268","resolution":{"observed_at":"2026-08-07T11:09:48.997712Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:48.747287Z","title":"On hyperparameter optimization of machine learning algorithms: Theory and practice","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.747287Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:f09d1aaedfd1aa99d21e7b12519e2548f0b77f556ceea441e34a88ccf8acd7e8","observation_id":"797861bc-023f-4267-8862-9c6715696cef","resolution":{"observed_at":"2026-08-07T11:09:48.747287Z","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":"2026-08-07T11:09:48.976260Z","title":"ihas: Instance-wise hierarchical architecture search for deep learning recommendation models","venue":null,"work_id":"c102addb-28ca-43ec-8df1-7c77e715acd4","year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.750986Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:f3df2b03b29071cf3712c33e38325493d1501beb499921d5f773fa1c93bce3b2","observation_id":"195751e1-f819-4884-9e55-a88fea185048","resolution":{"observed_at":"2026-08-07T11:09:48.979456Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:48.965775Z","title":"Dns-rec: Data-aware neural architecture search for recommender systems","venue":null,"work_id":"df2f16f5-5018-4eea-80df-e2d43cdcf7d8","year":2024},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.753770Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:09f565900a4c3e3f504ed2b437843a10fe1b3609f070c22d31b7b04f8f365662","observation_id":"23d39771-a4de-4b8f-9658-9d14cb3244e7","resolution":{"observed_at":"2026-08-07T11:09:48.969094Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:48.954988Z","title":"A collaborative transfer learning framework for cross-domain recommendation","venue":null,"work_id":"40b39f41-765c-4aa4-903f-fc4af27f605e","year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.756351Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:075177c8952bf795f5ccdec7a1e3f282a42f3790533a9a4e596f434f1c065e25","observation_id":"dff1bf39-f2f1-49aa-84c8-176c21a65e97","resolution":{"observed_at":"2026-08-07T11:09:48.958611Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:48.943980Z","title":"Recbole: Towards a unified, comprehensive and efficient framework for recommendation algorithms","venue":null,"work_id":"ead505bd-e1d1-47a3-9159-ba79ea41383b","year":2021},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.759479Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:242107b6d3a49eb456a01b3812290152cca0cdc401eca3403ad038b924d4c82a","observation_id":"3b5d6648-4111-468b-abb2-fa794c1d53f8","resolution":{"observed_at":"2026-08-07T11:09:48.947673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:48.934500Z","title":"Automl for deep recommender systems: A survey","venue":null,"work_id":"b6d9502f-e75a-4eef-a20a-bcb2395fe519","year":2023},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.762059Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:69e64ddbea3eb2b189bae4c9bcf054bb0de3fb70d24a90a67482d55c2a4c59de","observation_id":"4798de8c-d982-4866-984b-88ae6cb49b6d","resolution":{"observed_at":"2026-08-07T11:09:48.937548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:48.924509Z","title":"Nas-ctr: efficient neural architecture search for click-through rate prediction","venue":null,"work_id":"aef805be-5d2d-4c58-b234-da808fcdb663","year":2022},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.764571Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:5f27528d6069c812fcd07c24a81ae5f2fbfb54e030e12633b829db6dd2dc0685","observation_id":"802591a1-efce-4f21-bbbc-b97c3fd6e2e2","resolution":{"observed_at":"2026-08-07T11:09:48.927891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:48.915167Z","title":"Difer: Differentiable automated feature engineering","venue":null,"work_id":"0f8ffb2a-4269-483b-9cca-dc81a333abe3","year":2022},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.767630Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:728ecaea22fd73e68786b9d6e8b3454151e2d2e642d60ce68332e7fba06251e4","observation_id":"cfddf425-a891-4dea-b05b-ba7501760032","resolution":{"observed_at":"2026-08-07T11:09:48.918424Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:48.905128Z","title":"Bars: Towards open benchmarking for recommender systems","venue":null,"work_id":"09fb6a3e-8c05-40b1-8bf1-8f1703ab27f3","year":2022},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.770533Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:e74c400fdc9d61ec519516bc6c034c8905facca8eafa175e48c1b204b572e0b6","observation_id":"d322fba5-68e9-4c54-8fb2-04a953a66651","resolution":{"observed_at":"2026-08-07T11:09:48.908805Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T11:09:48.895518Z","title":null,"venue":null,"work_id":"bcd19882-8e0a-402f-b82c-21846d4bb78f","year":2017},"citing_paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-07T11:09:48.773621Z"},"links":{"citing_paper":"/paper/2506.03391"},"observation_digest":"sha256:6285f0917b49dfbab35e7bdd4d23819ea7538d78ddee51822f045423f35f19d1","observation_id":"90e83a9f-7e79-4c15-8d9a-257ef39e0506","resolution":{"observed_at":"2026-08-07T11:09:48.898756Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.03391","last_updated":"2025-06-03T21:00:34Z","latest_version":1,"primary_category":"cs.IR","snapshot_observed_at":"2026-08-19T20:37:42.034726Z","submitted_at":"2025-06-03T21:00:34Z","title":"Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks"},"reference_resolution":{"displayed":84,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":3,"verified_fuzzy":59},"total_outbound_references":84},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 84 of 84 outbound references and 0 inbound Pith citation observations for arXiv:2506.03391."}