{"as_of":"2026-08-19T03:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:539286818727d877b0774b0b5a50f7278a5bc18d8e8dd5576416370e61508076","coverage":[{"denominator":40,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":40,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T23:04:26.625476Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2506.20057/citation-record","integrity":"/paper/2506.20057/integrity","json":"/paper/2506.20057/citation-record.json","paper":"/paper/2506.20057"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.795814Z","title":"Theoretical Computer Science 354(3), 391–404 (2006)","venue":null,"work_id":"40f270af-6258-4033-a9df-88066a896a68","year":2006},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.343816Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:1d52c60ddfd182010ce4fa89fdac71ca3ea21d2d34136615b5d8f4230928ba0e","observation_id":"7892e3aa-a84e-4b28-82ac-56d439713c12","resolution":{"observed_at":"2026-08-06T23:04:27.834749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:26.361154Z","title":"Computer 49(05), 54–63 (may 2016)","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.361154Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:e45cd5c876ec7a0315b7e310db7f04809c14815f21fea20dea5b968a1882dd9f","observation_id":"a6e5dcfa-5de9-4eb3-a2ff-e198d81de6ac","resolution":{"observed_at":"2026-08-06T23:04:26.361154Z","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":"2026-08-06T23:04:27.751579Z","title":"In: International conference on algorithmic learning theory","venue":null,"work_id":"a13e35f0-a6d6-4373-9c86-1934e8f9c88a","year":2014},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.382438Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:b9c8f8905c393bf638e3af3daf52da211741a5df3fa96756c58ff970aab59745","observation_id":"3f9dc1c6-a6cc-4c32-a607-82485525df9e","resolution":{"observed_at":"2026-08-06T23:04:27.756265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.715113Z","title":"In: Algorithmic Learning Theory: 26th International Conference, ALT 2015, Banff, AB, Canada, October 4-6, 2015, Proceedings 26","venue":null,"work_id":"7a270e18-e666-45c5-ad58-85001c43fe36","year":2015},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.391386Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:46aff3315f72a742cc456e192336cdfb07ddf1b4fbd2f2882502949e72d5299c","observation_id":"c43d5654-3685-4dbe-8d2a-2d198626aa08","resolution":{"observed_at":"2026-08-06T23:04:27.719458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.681612Z","title":null,"venue":null,"work_id":"9a312d0a-f510-4616-9592-842af40aacac","year":null},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.397905Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:a4c7064310b556b144fe592ba3d90204d1519555add26e37a7f706ca4b35fc05","observation_id":"d7285496-6197-4800-85db-540ee6af8d3e","resolution":{"observed_at":"2026-08-06T23:04:27.704110Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.624752Z","title":"Ihre geschichtliche Entwicklung und wirtschaftliche Seite","venue":null,"work_id":"467ac0ad-65b5-4b58-9e10-980fed85cd95","year":1901},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.404271Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:9be9232da209210a9e19f76318755c768a75d8bf6bb8611055c936672ecf9c42","observation_id":"0a951dad-6ede-4ff4-942d-f5532061ba75","resolution":{"observed_at":"2026-08-06T23:04:27.640118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.565105Z","title":"Advances in neural information processing sys- tems 34, 28431–28441 (2021)","venue":null,"work_id":"ac9b1752-4029-40eb-9dad-ce2c52e6ac89","year":2021},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.408901Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:5a73da1cd7d0f518bc17db18fe3f45cfae954a95bc51549c7295bfd7f686dc4d","observation_id":"e48e0b0f-c6d6-4cd1-a20f-ba3d61c73250","resolution":{"observed_at":"2026-08-06T23:04:27.577435Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.543410Z","title":"IEEE Access 9, 51416–51431 (2021)","venue":null,"work_id":"6c4cb4ca-a7ff-473a-9797-5f8f7a593190","year":2021},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.414505Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:9465051ec5c5722a576b2da388479c3bc20d53bec887d282c71f85fc7dc00875","observation_id":"988c7736-4c98-42d4-bb11-2eb0c553ea04","resolution":{"observed_at":"2026-08-06T23:04:27.552408Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.524865Z","title":null,"venue":null,"work_id":"1662878c-6873-498c-b9bb-90eb16071c73","year":null},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.419103Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:3176470f6d84d5e3095abf32cf9ed1a709016c85b9bea6e52909dbcc94f8026a","observation_id":"11549d92-ca71-4504-9c1f-a5066b1f70e8","resolution":{"observed_at":"2026-08-06T23:04:27.531790Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.508397Z","title":"John Wiley & Sons (1999)","venue":null,"work_id":"2c09530b-79c9-48a1-ae7b-cec89bb1c03c","year":1999},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.425584Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:9f3159a31617552290a8d2f9a20f41144d9c104a9e0b40316964af3b3cda5e6d","observation_id":"a2934f24-13d1-4c17-84bd-87f5fae19125","resolution":{"observed_at":"2026-08-06T23:04:27.512561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.05366","last_updated":"2024-06-07T19:56:33Z","snapshot_observed_at":"2026-08-16T15:41:13.728690Z","submitted_at":"2023-04-11T17:22:22Z","title":"The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.05366","snapshot_observed_at":"2026-08-06T23:04:26.436738Z","title":"arXiv preprint arXiv:2304.05366 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.436738Z"},"links":{"cited_paper":"/paper/2304.05366","citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:a0535ee456899b7816ef5e1d4df3213a1b344d90c4a53f71fa3ce6f7a1c2f6f1","observation_id":"34dc3177-f199-44a9-b9e3-ba55e4d27ede","resolution":{"observed_at":"2026-08-06T23:04:26.436738Z","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":"2026-08-06T23:04:27.476934Z","title":"ICML (2024) 28","venue":null,"work_id":"d34ca3bd-a133-4925-b6aa-50af1b8687eb","year":2024},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.442026Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:c99bc60c654fbc4d96052993298016e47f9819bc9060e9fe1d9d15d6da420a72","observation_id":"1a3da2a5-a370-4a93-9bed-7fe72697cc69","resolution":{"observed_at":"2026-08-06T23:04:27.495836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.445177Z","title":"MIT press (2007)","venue":null,"work_id":"a9dd9c80-b2ce-4a07-8975-d2e617d53c19","year":2007},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.446672Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:3e051b5413e3def99f26459407e4ec8c7f545ecfe411fece38115449bb4f2d74","observation_id":"6b6fa579-b29d-4bcb-a3c9-b01fae0f7369","resolution":{"observed_at":"2026-08-06T23:04:27.449513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.426249Z","title":null,"venue":null,"work_id":"3fa28795-adac-4a52-a517-56734f8e1efa","year":2021},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.453614Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:873ad50a6560d1b5a2366db8757e621d77bae63bf584b9e3053fd89efea6f241","observation_id":"3952433a-57f2-4b8f-9413-1dc9604b6d36","resolution":{"observed_at":"2026-08-06T23:04:27.434743Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.384836Z","title":"Neural compu- tation 9(8), 1735–1780 (1997)","venue":null,"work_id":"48959aa2-3db4-4125-9903-6f4be213e9a4","year":1997},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.460529Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:04dd5f41f4007f1ac1301c64d5631044e30c093a554bfc44da39deec8f29be72","observation_id":"b554d650-437a-4df9-8852-ed69b0645c0c","resolution":{"observed_at":"2026-08-06T23:04:27.397545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.340912Z","title":"Nature 637(8045), 319–326 (2025)","venue":null,"work_id":"525c4be7-74a6-49f5-bdad-876ad974190b","year":2025},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.465745Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:4a5fda55e096c1fe2ffc728e7f3b575e07e9deec12bc0aaeb383fb278879bee7","observation_id":"ca126510-7b5a-47b7-bf67-456cf44c563b","resolution":{"observed_at":"2026-08-06T23:04:27.361375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.302138Z","title":null,"venue":null,"work_id":"bca9094c-176c-4dff-b9ab-645afc7299b8","year":2006},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.471696Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:a248568a2a544e763f08054d07b975f5e6062e691ff8768aecf65fb0e18fb27f","observation_id":"ff869533-f68f-4896-803f-fe4ff123b0ed","resolution":{"observed_at":"2026-08-06T23:04:27.307541Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.261673Z","title":"Digital Communications and Networks 9(1), 79– 89 (2023)","venue":null,"work_id":"6d64bc33-8b29-4399-b298-67ea84900d49","year":2023},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.476985Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:ae962a055c9e341c324de30661dec69788471cfc174a17e599fa6927cb56c193","observation_id":"58b18e4e-398b-48c0-958a-67fd98b41b30","resolution":{"observed_at":"2026-08-06T23:04:27.285056Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.222974Z","title":"In: Algorithmic Probability and Friends","venue":null,"work_id":"874d0eca-02d9-47b8-a379-6fd10f548237","year":2013},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.481690Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:049a9a1e6634833360382258881f8a8960af00b3709edcfcb1ae4be3cc95df80","observation_id":"fe84d037-cdda-43b1-9d2d-2f3038c7c7c3","resolution":{"observed_at":"2026-08-06T23:04:27.228543Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.12467","last_updated":"2021-01-17T18:17:31Z","snapshot_observed_at":"2026-08-12T00:50:54.021191Z","submitted_at":"2020-06-22T17:47:09Z","title":"The Depth-to-Width Interplay in Self-Attention","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.12467","snapshot_observed_at":"2026-08-06T23:04:26.485803Z","title":"arXiv preprint arXiv:2006.12467 (2020)","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.485803Z"},"links":{"cited_paper":"/paper/2006.12467","citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:b29ffd0df533678cb502fcf636ee4083eecdf6ea69b2f36094c8b71c9f8ec8a0","observation_id":"5aafb491-ef5e-4671-8fe2-fe3e23d93085","resolution":{"observed_at":"2026-08-06T23:04:26.485803Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-14T20:13:52.872565Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-06T23:04:26.495445Z","title":"arXiv preprint arXiv:1711.05101 5, 5 (2017)","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.495445Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:25de5d558f2b376cf88e93d65a33c71b4ffd984ba69ecdaf0cacd6fd3a623c66","observation_id":"cfacdf18-09ec-4878-adaf-05c211f08c6a","resolution":{"observed_at":"2026-08-06T23:04:26.495445Z","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":"2026-08-06T23:04:27.185498Z","title":"In: Algorithms and complexity , pp","venue":null,"work_id":"b92ece47-5a0c-474e-a842-a86d51a8924d","year":1990},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.509892Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:486eaea2c40908eff4102d51a75e93a8b0d7cc66840a2cb8a95687e643b577e6","observation_id":"2ec485cf-acfe-4371-ab9c-f52cfeedcb53","resolution":{"observed_at":"2026-08-06T23:04:27.196066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.163233Z","title":"The Guardian https://www.theguardian.com/technology/2025/jun/11/ disney-universal-ai-lawsuit","venue":null,"work_id":"28906733-86a7-4fdc-87e8-3a41db2cff4f","year":2025},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.517997Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:36c90034828100a85b540413a9f02b534dd141d925ab1e32f1464a3bc7de9996","observation_id":"136777cc-6fd0-4755-8f2b-24e9fbcb8e46","resolution":{"observed_at":"2026-08-06T23:04:27.167942Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.10510","last_updated":"2024-08-13T09:58:44Z","snapshot_observed_at":"2026-08-16T17:33:17.947651Z","submitted_at":"2021-12-20T13:07:39Z","title":"Transformers Can Do Bayesian Inference","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.10510","snapshot_observed_at":"2026-08-06T23:04:26.522582Z","title":"arXiv preprint arXiv:2112.10510 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.522582Z"},"links":{"cited_paper":"/paper/2112.10510","citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:2fe7ccc8070f415943767a631e6c82149b33112c53bdc09ab71b7951176a1e70","observation_id":"b2683e1c-53f6-48ed-a635-8e98d1d0a242","resolution":{"observed_at":"2026-08-06T23:04:26.522582Z","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":"2026-08-06T23:04:27.142488Z","title":"In: In- ternational Conference on Machine Learning","venue":null,"work_id":"8c7e2cb3-fc9a-41a0-a7cd-272db10a363f","year":2023},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.528840Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:ee82364f4aed93a9b9fc481858295a73ca6269a1ea21d21a0b9542dcfbe31448","observation_id":"86cfb366-7561-4d44-a2af-a69fee520b6a","resolution":{"observed_at":"2026-08-06T23:04:27.148611Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.124094Z","title":null,"venue":null,"work_id":"38305591-bf70-4083-90d4-a664fad6e43f","year":2024},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.533090Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:ba7229967dc89cad1104add2352c6d22a3a046a5924e65283878140c671aad8c","observation_id":"c5a29a2d-f604-4894-adcc-3547562e06b1","resolution":{"observed_at":"2026-08-06T23:04:27.128669Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.092105Z","title":"The Guardian https://www.theguardian.com/books/2023/sep/20/ authors-lawsuit-openai-george-rr-martin-john-grisham","venue":null,"work_id":"fd44c9b0-9811-4cfd-93a6-ca6dffd40bf5","year":2023},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.538086Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:60dc9dd27576a70b919898dd58129883fe34b61a20a12100c586ee60dc3f888b","observation_id":"d823d3b9-335d-4fe2-9f8e-e12ec487bacb","resolution":{"observed_at":"2026-08-06T23:04:27.109019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:26.543018Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.543018Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:d725913ecf2038d4c9ef025133d8e74322a53517e39d7959ca64332201ef8f0c","observation_id":"ebcb7065-8775-4070-ae78-81082e85db08","resolution":{"observed_at":"2026-08-06T23:04:26.543018Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.01745","last_updated":"2016-08-15T19:41:47Z","snapshot_observed_at":"2026-08-17T22:39:22.495499Z","submitted_at":"2016-08-05T03:16:07Z","title":"Play and Learn: Using Video Games to Train Computer Vision Models","version":2},"cited_work":{"arxiv_id":"1608.01745","doi":null,"metadata_source":"pith","pith_arxiv_id":"1608.01745","snapshot_observed_at":"2026-08-06T23:04:26.776934Z","title":"Play and Learn: Using Video Games to Train Computer Vision Models","venue":"cs.CV","work_id":"29030d31-cfcf-46e7-84a4-43a2f24a7a7f","year":2016},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.547744Z"},"links":{"cited_paper":"/paper/1608.01745","citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:a6d6d60c03b18d79e4863cd6aafe4dce31b5cf1d73ac69ccbd3e6d379b0a1585","observation_id":"72d48d14-4042-4ebc-91ec-97c1f05dcbb8","resolution":{"observed_at":"2026-08-06T23:04:26.784424Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.052570Z","title":"In: Proceedings of the fifth annual workshop on Computational learning theory","venue":null,"work_id":"41da58c3-183c-43a4-80c7-feb187248f65","year":1992},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.556386Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:6c19b04dc36732332e1259113425ae0f83546273666a6741a176c6ce1cc48caa","observation_id":"85482239-4061-4749-84b0-cbeb1819d2cd","resolution":{"observed_at":"2026-08-06T23:04:27.056916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.038043Z","title":null,"venue":null,"work_id":"eeb4db97-260b-4e6c-a836-75860ab2cc8e","year":1964},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.563032Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:f80b3ad99585cae0b718eba079fbf6f478eba9b14aeb5b1453d49ccfbbbdd17f","observation_id":"81760e1f-5813-449c-aebf-d9db856872b6","resolution":{"observed_at":"2026-08-06T23:04:27.042557Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.014729Z","title":null,"venue":null,"work_id":"11f4f823-391d-41b0-84a5-f2119635c978","year":1964},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.569977Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:72c1a351e324076dc5eb177084d500119f056b31549753dc670e9cdb3c51d1c9","observation_id":"4b9a6ca8-681d-43b9-a319-246fadacf300","resolution":{"observed_at":"2026-08-06T23:04:27.027010Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:27.000082Z","title":null,"venue":null,"work_id":"7d9c058f-ce22-43a5-a383-4eb60ff14e66","year":1936},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.577802Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:96aa1a5be4b216fc4b4c131754e94208e88ca70edd11a3a4b369b67c3aa4e3a1","observation_id":"541112bc-83aa-44b6-b3b3-7fd800bad0eb","resolution":{"observed_at":"2026-08-06T23:04:27.004523Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:26.587582Z","title":"Advances in neural information processing systems 30 (2017)","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.587582Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:aceed72b02612992e20516534cfd9df550c04b64397b31637930146a86f126d4","observation_id":"8961aab8-8f7f-460d-bab3-c692b0dbe367","resolution":{"observed_at":"2026-08-06T23:04:26.587582Z","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":"2026-08-06T23:04:26.969970Z","title":"In: The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","venue":null,"work_id":"6356888c-5710-4434-8a0e-f0e101a362ca","year":2024},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.594762Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:b1cdb06c2d2c856d2bc5f9a4ba3160062a1e02adb2fd94967c5094417ea3636a","observation_id":"eb7a707a-4680-44e7-80c6-477dc9db6459","resolution":{"observed_at":"2026-08-06T23:04:26.975616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:26.939744Z","title":"ICML (2024)","venue":null,"work_id":"2384defe-c378-4077-a11f-77f45ef47f6a","year":2024},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.599754Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:276b4d43610c93c02f558a8e65031bfb1bc1da72da7fb43c3250e082e209260e","observation_id":"9b3760d5-6792-4bc4-898d-3bafc5f53935","resolution":{"observed_at":"2026-08-06T23:04:26.946758Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:26.610332Z","title":"arXiv preprint arXiv:2405.09591 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.610332Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:be472055e147987845e3d734878e27c5a1a2bab211a35b850037a522368f6888","observation_id":"dda439b9-ae71-412b-a0a2-f2ead70aebe0","resolution":{"observed_at":"2026-08-06T23:04:26.610332Z","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":"2026-08-06T23:04:26.919537Z","title":"IEEE transactions on evolutionary computation 1(1), 67–82 (1997) 30","venue":null,"work_id":"94a4d07c-3a6e-4ced-a367-900386e17989","year":1997},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.616579Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:fab16ebbab77f9d3d603ccacf291e8df913bd78e37ee60f875d7ef67075d0547","observation_id":"1e9ec1ca-75f1-469f-a4e9-fe43c3dcd43f","resolution":{"observed_at":"2026-08-06T23:04:26.925611Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:26.896654Z","title":null,"venue":null,"work_id":"aa397ccc-b80e-48a8-b4e9-7286044020fe","year":2021},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.620781Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:fbc908088aefc7f225ee00411ed723a8011caabbee2698606e9720acd1308fe0","observation_id":"8912acec-2869-4e77-8493-475ab3bbcfd2","resolution":{"observed_at":"2026-08-06T23:04:26.907836Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:04:26.881404Z","title":"We clip gradients by scaling every gradient vector larger than 1 to norm 1","venue":null,"work_id":"740ddce4-66b8-4b07-998a-815e21c7fbce","year":null},"citing_paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T23:04:26.625476Z"},"links":{"citing_paper":"/paper/2506.20057"},"observation_digest":"sha256:bc47abb267f50c7e592eb5d67c1a7dc2f1393ed72bc898b1eb40a75c3259f0cd","observation_id":"c4a660d1-97ef-4452-a0f8-f59325f4099c","resolution":{"observed_at":"2026-08-06T23:04:26.886443Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.20057","last_updated":"2025-06-24T23:36:35Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T03:54:29.189721Z","submitted_at":"2025-06-24T23:36:35Z","title":"Universal pre-training by iterated random computation"},"reference_resolution":{"displayed":40,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":17,"verified_exact":0,"verified_fuzzy":22},"total_outbound_references":40},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2506.20057."}