{"as_of":"2026-08-05T06:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c287fdf7cdbe07093c0fdeede5ae7713ca1cd2dea11f7378c31cde857329c61e","coverage":[{"denominator":75,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":75,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-13T07:21:04.820743Z","state":"measured"},{"denominator":76,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":76,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T00:35:21.410083Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.11011","snapshot_observed_at":"2026-08-03T00:35:21.410083Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28751","last_updated":"2026-07-30T18:18:03Z","snapshot_observed_at":"2026-08-05T05:10:35.716218Z","submitted_at":"2026-07-30T18:18:03Z","title":"ReLoop-UME: Recurrent Depth with Learnable Retrieval Registers for Universal Multimodal Embedding","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-03T00:35:21.410083Z"},"links":{"cited_paper":"/paper/2605.11011","citing_paper":"/paper/2607.28751"},"observation_digest":"sha256:30e5761a20674cb0798fb2e84bcd5ef56b03e416dbded901975ec039486dfd1f","observation_id":"04425d2d-36af-4a18-83a1-d49579ddf019","resolution":{"observed_at":"2026-08-03T00:35:21.410083Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2605.11011/citation-record","integrity":"/paper/2605.11011/integrity","json":"/paper/2605.11011/citation-record.json","paper":"/paper/2605.11011"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mamba-3: Improved sequence modeling using state space principles","venue":null,"work_id":"3bc64e9a-fa01-42c8-8291-8e230bcf940c","year":2026},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:8b9d7cf0adaca540c0ddf7a3fd3f6624b45f54ba7933bca093b21e6285cb93f7","observation_id":"3421bad1-130b-4ccc-a8d3-e497bad46291","resolution":{"observed_at":"2026-05-13T08:27:32.552446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Inference scaling laws: An empirical analysis of compute-optimal inference for LLM problem-solving","venue":null,"work_id":"d3afb56a-44f1-4ffc-b633-16980a777b31","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:8d953b1a41b084c029d4188dbf9c9ce6be9684e054ad0c749ba68844042a0dc7","observation_id":"040eba49-57b8-472e-b2a1-9185aa487959","resolution":{"observed_at":"2026-05-13T08:27:32.560982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Scaling LLM test- time compute optimally can be more effective than scaling parameters for reasoning","venue":null,"work_id":"ce045b3f-8d29-49bb-9c87-466962a17737","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:9b6f3457f61de3a44aab5b344be9dcf1bd77b905d62ef8a65dee82c2db3a44f0","observation_id":"8f0aec32-c3eb-4566-acf3-19c2745d6c38","resolution":{"observed_at":"2026-05-13T08:27:32.556982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2510.25741","last_updated":"2026-07-01T23:25:58Z","snapshot_observed_at":"2026-08-04T07:30:51.188041Z","submitted_at":"2025-10-29T17:45:42Z","title":"Scaling Latent Reasoning via Looped Language Models","version":5},"cited_work":{"arxiv_id":"2510.25741","doi":"10.48550/arxiv.2510.25741","metadata_source":"pith","pith_arxiv_id":"2510.25741","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Scaling Latent Reasoning via Looped Language Models","venue":"cs.CL","work_id":"0c087b6b-1850-498b-9197-a0a85ed89937","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/2510.25741","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:faf6f51c278ef99eefe1e6c217b60e03ec5f1b5910c4c6de22e0e6e916b87886","observation_id":"1d884d67-139f-46f9-84a5-8a76aa1b582c","resolution":{"observed_at":"2026-05-15T07:43:12.191103Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T05:19:22.789498+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T05:19:22.789498+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Mixture-of- recursions: Learning dynamic recursive depths for adaptive token-level computation","venue":null,"work_id":"c927b329-648e-4333-af97-ef95861dbc47","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:a0144aedfb9d5022f0e8c042a9e147b25374a6f1082610fd16ec203b50de2476","observation_id":"f1120ad0-6cf4-4486-bed2-1d04ad526b5b","resolution":{"observed_at":"2026-05-13T08:27:32.545074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.05171","last_updated":"2025-02-17T17:14:04Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-07T18:55:02Z","title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","version":2},"cited_work":{"arxiv_id":"2502.05171","doi":"10.1016/0041-5553(81)90075-6","metadata_source":"pith","pith_arxiv_id":"2502.05171","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","venue":"cs.LG","work_id":"1ee7474f-a930-486e-897c-207b8755f2c9","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/2502.05171","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:a76e6c4f386b6c9c86e136593ec5f548b88378b9132c8145305337d0df34b975","observation_id":"08756bd9-1f19-45c7-a70e-32ebf9bc0b76","resolution":{"observed_at":"2026-05-13T07:22:28.708278Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Energy-based transformers are scalable learners and thinkers","venue":null,"work_id":"027222ae-d826-4830-ad9b-1852e7f8dc86","year":null},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:54ca0ab4302797bb755f3716e0204550df5dd61e919f11c6eb956275ed0ef3cf","observation_id":"fada187a-6f0e-495e-886a-9f04501a2281","resolution":{"observed_at":"2026-05-13T08:27:32.498325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"09e12582-40b8-4970-89cf-c06983580d92","year":null},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:01989991d762ce04f46c1b5bcc563403b39b6f942e7c959fc1408f022bb86efc","observation_id":"25c36a4f-712d-40ed-98fe-79bae7f27733","resolution":{"observed_at":"2026-05-13T08:27:32.505719Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.21734","last_updated":"2025-08-04T08:45:08Z","snapshot_observed_at":"2026-08-02T04:59:02.894959Z","submitted_at":"2025-06-26T19:39:54Z","title":"Hierarchical Reasoning Model","version":3},"cited_work":{"arxiv_id":"2506.21734","doi":"10.48550/arxiv.2506.21734","metadata_source":"pith","pith_arxiv_id":"2506.21734","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Hierarchical Reasoning Model","venue":"cs.AI","work_id":"81fb438f-27d0-4a73-8fa3-5e65f127ca94","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/2506.21734","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:03c1096c8958a0285b6d4cd5e5e8b336c5f13b857b10f103a01bada3a8c13395","observation_id":"0428d386-5acb-4e1f-ad6d-d7d5a067e1b4","resolution":{"observed_at":"2026-05-15T04:58:03.874482Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-05-25T17:53:21.543618+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T17:53:21.543618+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Large language diffusion models","venue":null,"work_id":"0071011f-9319-456f-b3f0-8068df925f3c","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:5a309f1c2db60fea9e624eb6055c5827b5c317be8474f12f8f3072beee3ffda7","observation_id":"f81b21cb-f33a-4027-a722-b074fc7e1fff","resolution":{"observed_at":"2026-05-13T08:27:32.540675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2511.07384","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T06:36:44.173284Z","title":"Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Jonas Geiping, Tom Goldstein, and Micah Goldblum","venue":null,"work_id":"9157a551-e862-4655-a5f4-7f4d6ca01c36","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:4ae9a6459f3d1efb65c1b7470f282992e58dfa637f9f5c4dd2ec22a80d7cfb13","observation_id":"b7c9b9aa-cfc0-49c6-870a-385d7c79f959","resolution":{"observed_at":"2026-05-13T07:22:28.739485Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Relaxed recursive transformers: Effective parameter sharing with layer-wise loRA","venue":null,"work_id":"0672a84b-8e50-4ce6-a380-cce54e47856e","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:8f3d0d293001968299be2567921bc5d1feab5c3ab993c022831b34babeb2bc6b","observation_id":"c99bd131-6173-46bf-bc37-f886daf96ce9","resolution":{"observed_at":"2026-05-13T08:27:32.482965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2601.10242","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Loop as a bridge: Can looped transformers truly link representation space and natural language outputs?CoRR, abs/2601.10242","venue":null,"work_id":"a0330f35-3a3d-477e-a6d9-05e14dd4aabf","year":2026},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:8c1d5d483455be8b75f1625c6420e490849bd4b570be14bbb3c0ec6f6b03c183","observation_id":"5c8ad26f-5e79-4cde-9a93-35946c53e57d","resolution":{"observed_at":"2026-05-13T07:22:28.723394Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"bdd41a31-6cff-48b2-9477-0bcd5278f5ee","year":2013},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:a51fbefd674968dc8cee83ea8cd9018485d99cfcb8ae0975f4a936444d35bfc3","observation_id":"bea98e34-b94c-4782-ac5b-131ca71193a1","resolution":{"observed_at":"2026-05-13T08:27:32.494456Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"On the difficulty of training recurrent neural networks","venue":null,"work_id":"1f8806f8-54cb-482c-aab7-904bf3a12c09","year":2013},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:9f58b1947caa69f9e179c48b2e82c83c3f5f7b2ab8c10ea8fd1ba17971e4b862","observation_id":"a665e8f8-3835-4d0d-8b3a-a2dd31400029","resolution":{"observed_at":"2026-05-13T08:27:32.478289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.06203","last_updated":"2025-07-10T16:43:36Z","snapshot_observed_at":"2026-08-02T21:17:27.897148Z","submitted_at":"2025-07-08T17:29:07Z","title":"A Survey on Latent Reasoning","version":2},"cited_work":{"arxiv_id":"2507.06203","doi":"10.48550/arxiv.2507.06203","metadata_source":"pith","pith_arxiv_id":"2507.06203","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"A survey on latent reasoning.arXiv preprint arXiv:2507.06203, 2025c","venue":"cs.CL","work_id":"ef554cf3-8ad8-4c89-8fa6-f8a1670ca6a1","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/2507.06203","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:c2ae9ac0e04f1eecfe25e38592795a50c94e91af3a83442fdc945537272a1a36","observation_id":"d4338d14-893e-4fde-a32d-98c033a3f949","resolution":{"observed_at":"2026-05-13T07:22:28.637973Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2601.18302","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Suppressing final layer hidden state jumps in transformer pretraining","venue":null,"work_id":"f0ddb70a-6893-4a48-8718-5d9463ce5b6d","year":2026},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:f9c8f1b43f6263921090378d66135378a9bf6ebe9f4a743cae7d022c3fcc51ea","observation_id":"d79fba7c-99bd-4d12-a8b6-b769b3047be2","resolution":{"observed_at":"2026-05-13T07:22:28.718174Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"6252.376089","doi":"10.1145/3746252.3760890","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Frozen in the middle: Hidden states remain unchanged across intermediate layers of language models","venue":null,"work_id":"74e30140-8342-4d48-b924-017468093757","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:d04506aaa64c076b53ad7e84d3ce0d65fdeede74af079fb6167efb8198a3ab14","observation_id":"993e7959-f69f-4e3d-9d04-813aa1df706b","resolution":{"observed_at":"2026-05-13T07:22:27.807334Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Llm neuroanatomy: How i topped the llm leaderboard without changing a single weight","venue":null,"work_id":"78d92453-06b4-44fd-a997-300efbf52430","year":2026},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:ec290a64c2cb8d1d826557f37a0c2320bfd73e3a04199194ccbaeff9831b5821","observation_id":"2730d4dd-a99e-4bcb-a7bb-f273f3e0feae","resolution":{"observed_at":"2026-05-13T08:27:32.530351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Mapping the mind of a large language model","venue":null,"work_id":"761aea82-9313-406c-bda6-b48c48868156","year":2024},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:ad354799e4731b87b9501616a79a3b9aba1aa99a468e1225a795e3334b957669","observation_id":"3ac37841-0db5-4aa0-93b5-2c850749b453","resolution":{"observed_at":"2026-05-13T08:27:32.501977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"On the biology of a large language model","venue":null,"work_id":"3fe1426c-e8f7-415e-8cb3-24d7f758b11e","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:b875b5e6ae21dd12d8cc2a3550a25d7dc6a0deb59e64bd60ecbac83c654741a7","observation_id":"55981505-e12b-4537-b326-e4631f43eca9","resolution":{"observed_at":"2026-05-13T08:27:32.535704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Interpreting GPT: The logit lens","venue":null,"work_id":"53852d09-e64d-4ea6-ab50-ab178428f417","year":2020},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:cce85f9443a7a2752e5cd563e4e63c6b1a6d9e39607ee573576a38bebca5a1d6","observation_id":"c75fe7a4-7e9e-46ec-a3b3-e9592830389c","resolution":{"observed_at":"2026-05-13T08:27:32.486642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"The bottom-up evolution of representations in the transformer: A study with machine translation and language modeling objectives","venue":null,"work_id":"6e364eb5-2637-4538-ba7b-cd270e254fdf","year":2019},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:aba84fefb09d3225881fb8cde5b084ac3b64e97ed6b09ed349c3588fe4a547f8","observation_id":"8d1e4cd8-c689-43e2-a7d6-4d28f08ac8b9","resolution":{"observed_at":"2026-05-13T08:27:32.521523Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"SOLAR 10.7B: Scaling large language models with simple yet effective depth up-scaling","venue":null,"work_id":"478a7030-8d03-4b0a-8e8f-0f78778ccebb","year":2024},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:9892a68f50fa7ecb0bb37b6b4fdf4d18388cff8a15194c9c6488495127a234f3","observation_id":"f11d3c81-1de9-4858-9229-428bc8166933","resolution":{"observed_at":"2026-05-13T08:27:32.525943Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2024.naacl-industry.3","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"doi: 10.18653/v1/2024.naacl-industry.3","venue":null,"work_id":"75c4ddc6-c20c-4f4e-a4ad-ee5689692b3f","year":2024},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:6a70bfd7844c2d6d37a8238c196ef89cd92eb1156806fe3639e766452f8b7f31","observation_id":"05d5c018-48c0-4629-8b02-7b7c211d64ab","resolution":{"observed_at":"2026-05-13T07:22:27.821116Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-09T07:46:03.958129Z","title":"Chi, Quoc V Le, and Denny Zhou","venue":null,"work_id":"bcfa509b-54ac-4854-8e9b-9c21521ae5ef","year":2022},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:8ff84ab633108bded231601ac39b27936710e2dfb2e9fde93fc4ce2c68fb92ec","observation_id":"1ae1d1b6-3bcc-45fb-af4e-edc5dc043731","resolution":{"observed_at":"2026-05-13T08:27:32.548500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2505.20674","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T11:37:03.287387Z","title":"Pretraining language models to ponder in continuous space.CoRR, abs/2505.20674","venue":null,"work_id":"9bb3fb2e-cfd1-4b17-be63-5afa2658cfc6","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:1b5b5e9eb9ccf6bbb595b3e79574bf5af26cadb7a45255e1f4325f4ffcd9e401","observation_id":"9375839c-8964-49ba-ac9f-6398d7d74848","resolution":{"observed_at":"2026-05-13T07:22:28.745632Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Think-at-hard: Teaching small language models to think on hard problems","venue":null,"work_id":"5ddee134-b119-4d95-95ff-9384bdc8a8ed","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:fde18ee07115e81ee12b3297a072347eb6b6f07cbbd0286abbe3737c99b776d2","observation_id":"e51dbe41-8333-4790-93e0-c0b34c50ab42","resolution":{"observed_at":"2026-05-13T07:22:30.261253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1807.03819","last_updated":"2019-03-05T16:46:19Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2018-07-10T18:39:15Z","title":"Universal Transformers","version":3},"cited_work":{"arxiv_id":"1807.03819","doi":"10.48550/arxiv.1807.03819","metadata_source":"pith","pith_arxiv_id":"1807.03819","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Universal Transformers","venue":"cs.CL","work_id":"8e5baefe-d209-411c-aefc-5acaa9275c8a","year":2018},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/1807.03819","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:cfd2b54bdf458726b4ba739670530ce028b4809eb2bcb994796781c24412faf0","observation_id":"32a12520-5d16-4ab0-949d-d765e921df3c","resolution":{"observed_at":"2026-05-13T08:04:31.534239Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Ouro: A latent reasoning model with adaptive depth via gated recurrence","venue":null,"work_id":"4e2a848d-0c40-49ca-935a-fd2210ce3a71","year":null},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:1e0baf18f201919d8a52ffcecf569a4fff52b8b57a6368d1626e596628d90425","observation_id":"0a39a41e-de51-47e1-a6c4-11e4cc0f4de4","resolution":{"observed_at":"2026-05-13T07:22:30.257480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.07919","last_updated":"2025-07-10T16:59:51Z","snapshot_observed_at":"2026-07-06T21:55:12.770268Z","submitted_at":"2025-07-10T16:59:51Z","title":"Plausible Counterfactual Explanations of Recommendations","version":1},"cited_work":{"arxiv_id":"2507.07919","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.07919","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"2e674e47-c5d2-4bfc-828b-872a32b9f165","year":null},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/2507.07919","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:646d14e436b0e568c6638f4bcd72a26f8f3f58670ded49f606cea2eed378cd98","observation_id":"5737f43c-c4cd-4398-a9f4-357b24120bcb","resolution":{"observed_at":"2026-05-13T07:22:28.647538Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Long short-term memory.Neural computation, 9(8): 1735–1780","venue":null,"work_id":"5714678b-8d1e-4725-bc65-64e16dd5687b","year":1997},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:84ae97e67f6d2f5f1e6938a0753cc56acfc57e0a843e8a4d0e29eed58052dd68","observation_id":"591cc8be-554d-485d-9a4c-e83aeabee43d","resolution":{"observed_at":"2026-05-13T08:27:32.514011Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.3115/v1/d14-1179","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"In: Moschitti, A., Pang, B., Daelemans, W","venue":null,"work_id":"938a9ac5-57f8-472b-baa1-4fbb755371fb","year":2014},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:be68a4fe22b4c4778720b497f5b7b04e22507849af697a2931c3e69716946692","observation_id":"90655ed0-af7c-40a0-a2e3-692831fbfef7","resolution":{"observed_at":"2026-05-13T07:22:27.816473Z","resolver_source":"doi","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-01T13:38:16.047867+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-01T13:38:16.047867+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1507.06228","last_updated":"2015-11-23T16:25:30Z","snapshot_observed_at":"2026-07-06T04:24:35.446533Z","submitted_at":"2015-07-22T15:29:14Z","title":"Training Very Deep Networks","version":2},"cited_work":{"arxiv_id":"1507.06228","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1507.06228","snapshot_observed_at":"2026-07-04T20:41:21.261963Z","title":"Training very deep networks","venue":null,"work_id":"83a83bf6-984c-4fe2-90f8-62723576f19f","year":2015},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/1507.06228","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:57c988e4d81f311efbde97d1ad5095e205d8b73664a9310e47a393d85d9da66d","observation_id":"7ea19e20-259d-4e76-bdbc-d337dce2f8dd","resolution":{"observed_at":"2026-07-04T20:41:21.261963Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1109/tpami","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Kristianto, G","venue":null,"work_id":"dae5fa3c-58f9-42b7-9de6-c0b565d5dec8","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:b31e314f90d350a236a91d350763c09c9c9fdd281a158eb871a25aabc80fcf66","observation_id":"4b63ec44-f19a-4527-8f0d-93180c1eb354","resolution":{"observed_at":"2026-05-13T07:22:27.800743Z","resolver_source":"doi_truncated","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-07T14:43:52.381951Z","title":"Mamba: Linear-time sequence modeling with selective state spaces","venue":null,"work_id":"3ccf85fb-2f33-473a-a1f7-1530dbf595d8","year":null},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:ebed374451a65119981a56675cd02a468f57b0b1da0ac14a148344ee379e52aa","observation_id":"420e3b4c-4fdc-4a86-8f02-5d3e7fc006ac","resolution":{"observed_at":"2026-05-13T07:22:30.253109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00752","last_updated":"2024-05-31T17:55:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-01T18:01:34Z","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","version":2},"cited_work":{"arxiv_id":"2312.00752","doi":"10.48550/arxiv.2312.00752","metadata_source":"pith","pith_arxiv_id":"2312.00752","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","venue":"cs.LG","work_id":"4ee75248-1199-492c-a52f-6661e0f4adff","year":2023},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/2312.00752","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:145ee4891a5e67e302aa566f0333c627e4bd22ca908cbfe12220ceae198ea75d","observation_id":"891c4040-f5f4-4d0a-a9db-c6f42730e202","resolution":{"observed_at":"2026-05-13T07:22:28.652734Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-05-30T19:25:31.081761+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-30T19:25:31.081761+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Efficiently modeling long sequences with structured state spaces","venue":null,"work_id":"a8bbc300-a8cd-419a-9613-ecd3423a7151","year":2022},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:07bd01c39b6d2e7d9d96a1597ef7b5623a6f7e781099fb2be5bb6d9b6c5a4c9b","observation_id":"42cf399d-f09c-4356-9ca3-e505cf5679e3","resolution":{"observed_at":"2026-05-13T07:22:30.244018Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"xLSTM: Ex- tended long short-term memory","venue":null,"work_id":"a685de26-0d3b-45b4-aaf2-b2d8a9548890","year":2024},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:d2e62b0e5f626a14ec2503fe8d25acb6407fae37460efede1e7789b21bc71ea3","observation_id":"d7896773-aaa3-4980-906a-6c8845d18397","resolution":{"observed_at":"2026-05-13T07:22:30.247985Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.00663","last_updated":"2024-12-31T22:32:03Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-31T22:32:03Z","title":"Titans: Learning to Memorize at Test Time","version":1},"cited_work":{"arxiv_id":"2501.00663","doi":"10.1016/j.est.2015.06.001","metadata_source":"pith","pith_arxiv_id":"2501.00663","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Titans: Learning to Memorize at Test Time","venue":"cs.LG","work_id":"fb2b7625-b733-43cb-af52-00b0a31a8d7f","year":2024},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/2501.00663","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:0ebbd2e0151b0bbbf298f464b229f7c7ffd2308e431a3e4cfd461be32c8a555f","observation_id":"abbcfcd5-b09e-4e6f-8dea-80cfba8cd598","resolution":{"observed_at":"2026-05-14T22:08:15.778565Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-05-25T06:55:03.802588+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T06:55:03.802588+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-07T11:13:41.813449Z","title":"Gated delta networks: Improving mamba2 with delta rule","venue":null,"work_id":"78bd411e-b993-4dfa-9848-e075ad159e4f","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:7878ca3ea3c8ad75d07055803332654ed75f03b077d53c1b6438079465d2cba8","observation_id":"88a66319-3abd-4e18-b125-a8cb9bcb3ce2","resolution":{"observed_at":"2026-05-13T07:22:30.240617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2601.09066","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T13:13:27.359183Z","title":"Mi: dm 2.0 korea-centric bilingual language models","venue":null,"work_id":"a3050fad-4600-46bf-ad25-7d35a929220e","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:addb40be65371d10745c18099f645dd4d3ea9fa25994efaf4f3c732cb69baf29","observation_id":"5ba8bd36-e333-41c0-b130-1ea9cbd260e3","resolution":{"observed_at":"2026-05-13T07:22:28.663987Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2510.04871","last_updated":"2025-10-06T14:58:08Z","snapshot_observed_at":"2026-07-06T22:31:49.574184Z","submitted_at":"2025-10-06T14:58:08Z","title":"Less is More: Recursive Reasoning with Tiny Networks","version":1},"cited_work":{"arxiv_id":"2510.04871","doi":"10.48550/arxiv.2510.04871","metadata_source":"pith","pith_arxiv_id":"2510.04871","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Less is More: Recursive Reasoning with Tiny Networks","venue":"cs.LG","work_id":"749dbba1-fbff-4b07-a1a7-9ccf98494da2","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/2510.04871","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:5f11ac150ac4bf10a01d0096026e67f078efb47257288b0ddf13489996bab188","observation_id":"1c97b03e-1244-4ca9-b891-55cc2465fc8e","resolution":{"observed_at":"2026-05-15T04:53:09.592494Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-14T04:50:12.755816+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-14T04:50:12.755816+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09748","last_updated":"2023-03-02T09:06:55Z","snapshot_observed_at":"2026-07-06T14:32:37.317828Z","submitted_at":"2022-12-19T18:59:58Z","title":"Scalable Diffusion Models with Transformers","version":2},"cited_work":{"arxiv_id":"2212.09748","doi":"10.48550/arxiv.2212.09748","metadata_source":"pith","pith_arxiv_id":"2212.09748","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Scalable Diffusion Models with Transformers","venue":"cs.CV","work_id":"a3a05169-18b1-42bb-8775-eada50163437","year":2022},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/2212.09748","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:b1546f6075fb8b8cddcc6b4e9249f7ad6ab3674301ed23f6676842fb56d4e05b","observation_id":"5e537ecd-73bd-401f-bc9f-e2e4bc826126","resolution":{"observed_at":"2026-05-13T07:22:28.750772Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T15:53:30.266292+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T15:53:30.266292+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-07T17:34:00.297435Z","title":"Sigmoid-weighted linear units for neural network function approximation in reinforcement learning.Neural networks, 107:3–11","venue":null,"work_id":"bb87c29b-d7f7-4747-a045-89481c311cdd","year":2018},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:97e4b699a3ef67cd9a6e6f52d1b24a05729371621401bb619091548df378abd3","observation_id":"558b79fe-3d3a-44c9-a342-1142fc0d5ed0","resolution":{"observed_at":"2026-05-13T07:22:30.237050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-09T15:56:19.760457Z","title":"Rectified linear units improve restricted boltzmann machines","venue":null,"work_id":"1e7c8ee7-2c3b-4dde-ab8c-5c83ac89a474","year":2010},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:6900e920cae0c7921160299e8dd08c8a3140e8ba3a28015fd8168bde09af51d3","observation_id":"ababb8be-2fe7-48e8-bb06-072aa1db7082","resolution":{"observed_at":"2026-05-13T07:22:30.217870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Self-normalizing neural networks.Advances in neural information processing systems, 30","venue":null,"work_id":"c81d5378-6f74-4f92-8111-9c12ce6d7277","year":2017},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:9758115e8ce6edfac7d006041cec5b12f1a850f7e12c65839f0aab5e06145fd0","observation_id":"7ace8159-5ae7-49e1-81af-975f6456b977","resolution":{"observed_at":"2026-05-13T07:22:30.221611Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":"2505.09388","doi":"10.1016/j.aiopen.2022.12","metadata_source":"pith","pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Qwen3 Technical Report","venue":"cs.CL","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:60cd83864f83f7de3425ff9eff0de1636b09d6e383e48d9be429eb6f4a256a3d","observation_id":"6eac191f-fa38-4a52-803f-41599818e07e","resolution":{"observed_at":"2026-05-13T07:22:28.627087Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Tinyllama: An open-source small language model","venue":null,"work_id":"20af042f-2764-42c8-ae60-3b58c98f71c6","year":2024},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:bd1a224a140cfe173d66bf153ed3408c0f0cf60bbb349f38e11063df3478c884","observation_id":"666ca1f5-9904-47b3-8910-b263b75869fe","resolution":{"observed_at":"2026-05-13T07:22:30.197659Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.08905","last_updated":"2024-12-12T03:37:41Z","snapshot_observed_at":"2026-08-05T04:04:21.846023Z","submitted_at":"2024-12-12T03:37:41Z","title":"Phi-4 Technical Report","version":1},"cited_work":{"arxiv_id":"2412.08905","doi":"10.48550/arxiv.2412.08905","metadata_source":"pith","pith_arxiv_id":"2412.08905","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Phi-4 Technical Report","venue":"cs.CL","work_id":"b6274271-7af9-4ee8-993b-ba1ba4205ba8","year":2024},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/2412.08905","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:86adba1483c524e8a6086e067790e71477118040ce5afc03b84a649aa81dbcdc","observation_id":"4cc8242d-a1ba-4818-9550-fc91bd61b4dc","resolution":{"observed_at":"2026-05-13T07:22:28.692481Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-02T03:08:11.323957+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-02T03:08:11.323957+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"The fineweb datasets: Decanting the web for the finest text data at scale","venue":null,"work_id":"2a51f457-fb43-4212-bb64-1c2a8a2e5df5","year":2024},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:5199d045982d311614adf0c4d235a3465ad546a1f965d542ba5d00bd9a85d815","observation_id":"4a5be956-75c2-44ba-aed2-59054b7233dc","resolution":{"observed_at":"2026-05-13T07:22:30.210619Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"A framework for few-shot language model evaluation, 12 2023","venue":null,"work_id":"a03abae7-679a-494b-88f5-14cdbf5f1e9d","year":2023},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:e1d703f8ec49f12c65c75e7825d03d63247052b8b5b1a9ec250bcc9ea651c23a","observation_id":"6d16ed92-9565-42ab-a2b2-9481ea869e90","resolution":{"observed_at":"2026-05-13T07:22:30.206380Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Pointer sentinel mixture models","venue":null,"work_id":"1094240a-adc6-423b-9a05-f7e81a65cade","year":2017},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:5a2481fd57d1edfea17f3480872b0f5baab4415cd79950131ada38efdd24cf1f","observation_id":"1ae4605e-22b4-4caa-baad-c203b4f1abe9","resolution":{"observed_at":"2026-05-13T07:22:30.214141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/p16-1144","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","venue":null,"work_id":"242aebff-fbcb-4225-bba0-a6a9f0b24ad7","year":2016},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:6790849a0c903e9b276238bfd69011ce8fc4570d4856687753c18d90da1fb689","observation_id":"ed3ca835-b91c-435a-805c-ad338d318240","resolution":{"observed_at":"2026-05-13T07:22:27.795951Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-17T19:51:13.335185+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-17T19:51:13.335185+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2009.03300","last_updated":"2021-01-12T18:57:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-09-07T17:59:25Z","title":"Measuring Massive Multitask Language Understanding","version":3},"cited_work":{"arxiv_id":"2009.03300","doi":"10.48550/arxiv.2009.03300","metadata_source":"pith","pith_arxiv_id":"2009.03300","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Measuring Massive Multitask Language Understanding","venue":"cs.CY","work_id":"e87ec49a-544b-4ec8-8991-75298c64ff5e","year":2020},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/2009.03300","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:c4cd6e095579bafb03d679585a004136c09ffb2bcab12cb4e5d8085730e62fc2","observation_id":"c545078f-290c-4f78-9af5-663b27315c41","resolution":{"observed_at":"2026-05-13T07:22:28.712797Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T01:08:06.256034+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-04T01:08:06.256034+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.07830","last_updated":"2019-05-19T23:57:23Z","snapshot_observed_at":"2026-07-31T00:09:56.948833Z","submitted_at":"2019-05-19T23:57:23Z","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","version":1},"cited_work":{"arxiv_id":"1905.07830","doi":"10.48550/arxiv.1905.07830","metadata_source":"pith","pith_arxiv_id":"1905.07830","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","venue":"cs.CL","work_id":"79f44c0c-96f4-4edb-bc50-a3c9d6b85936","year":2019},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/1905.07830","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:1533c571486105df8327816b1962c060635ff6fee60de9ad85c597760aa1279f","observation_id":"d81046ca-537b-44b6-9394-f924e11a4581","resolution":{"observed_at":"2026-05-13T07:22:28.608719Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05457","last_updated":"2018-03-14T18:04:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2018-03-14T18:04:21Z","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","version":1},"cited_work":{"arxiv_id":"1803.05457","doi":"10.1162/tacl_a_00448.https://aclanthology.org/2022.tacl-1.5","metadata_source":"pith","pith_arxiv_id":"1803.05457","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","venue":"cs.AI","work_id":"28ea1282-d657-4c61-a83c-f1249be6d6b1","year":2018},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/1803.05457","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:c969744a5783c5f17b55e01c3931a9bfa68da6a7eb64d103cf00954b75dc49c8","observation_id":"d3422f46-9757-45ae-af8c-75308181c636","resolution":{"observed_at":"2026-05-13T07:22:28.604115Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.11641","last_updated":"2019-11-26T15:31:46Z","snapshot_observed_at":"2026-07-06T08:40:06.727297Z","submitted_at":"2019-11-26T15:31:46Z","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","version":1},"cited_work":{"arxiv_id":"1911.11641","doi":"10.48550/arxiv.1911.11641","metadata_source":"pith","pith_arxiv_id":"1911.11641","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","venue":"cs.CL","work_id":"0d865a62-6376-4606-8d3a-eeb3b6e9ba6d","year":2019},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/1911.11641","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:b132301ead4edf5c8a928fb8c8692355d323983c4f31a1843c2b6577ddd30f61","observation_id":"1777d359-b573-4c32-a51e-c559d5d51554","resolution":{"observed_at":"2026-05-17T14:55:18.098549Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Winogrande: An adversarial winograd schema challenge at scale","venue":null,"work_id":"90003787-d3d5-4318-9141-b8a3ae7b7f88","year":2019},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:d522988ccb5b3c8d27437ddeca595d2b1dd2f392493927152fdefa667dae98dc","observation_id":"0bd4ec57-9c15-4a0b-90a2-053488de30b5","resolution":{"observed_at":"2026-05-13T07:22:30.193559Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1809.02789","last_updated":"2018-09-08T11:47:16Z","snapshot_observed_at":"2026-07-06T06:59:57.168051Z","submitted_at":"2018-09-08T11:47:16Z","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","version":1},"cited_work":{"arxiv_id":"1809.02789","doi":"10.48550/arxiv.1809.02789","metadata_source":"pith","pith_arxiv_id":"1809.02789","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","venue":"cs.CL","work_id":"b9d68fc0-5b23-4def-bc5e-6ad71d64eec6","year":2018},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/1809.02789","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:154ca68a373ccd7fa713f0064b5f26a1454c887e991cfc4064bc3553c46fd7bd","observation_id":"b200c77f-37a8-4a8e-9df6-c13e06bf425b","resolution":{"observed_at":"2026-05-13T08:14:48.923977Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2512.15605","last_updated":"2026-05-25T15:54:35Z","snapshot_observed_at":"2026-08-03T15:55:40.945793Z","submitted_at":"2025-12-17T17:14:26Z","title":"Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction","version":4},"cited_work":{"arxiv_id":"2512.15605","doi":null,"metadata_source":"pith","pith_arxiv_id":"2512.15605","snapshot_observed_at":"2026-07-03T04:27:36.156368Z","title":"Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction","venue":"cs.LG","work_id":"7d137c4f-0d46-4e91-a11e-a2a26ad936da","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/2512.15605","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:8b9d3671b4b9b1cd042dc742e753112fdc09897c047dd887e084bd2a69c6ca96","observation_id":"0bcd6925-ea18-4921-80b6-56ad952f616d","resolution":{"observed_at":"2026-05-13T07:22:28.622080Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Incor- porating second-order functional knowledge for better option pricing","venue":null,"work_id":"7f39c8d6-1da2-4fce-9fed-b1559252fda7","year":2000},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:68c507ae5c4840278ba1b4c77c5bf9c0d17644c8568266c7b986d3591122a931","observation_id":"61c4bbfa-b3cb-46e9-bbed-a7a796715c59","resolution":{"observed_at":"2026-05-13T07:22:30.202357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1049/cp:19991218","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"and Schmidhuber, J","venue":null,"work_id":"f6fb9e8d-83b3-4e0f-b7f7-71243986a004","year":1999},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:178f47de29f616a89c7d1826f7ffbbe0a3ed6829448ebeeec1018036d9e6e2e9","observation_id":"eaa8f018-2a46-4037-abc4-b0d2882726f4","resolution":{"observed_at":"2026-05-13T07:22:27.811482Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1109/icpr56361.2022.9956414","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Flashattention-2: Faster attention with better parallelism and work partitioning","venue":"2022 26th International Conference on Pattern Recognition (ICPR)","work_id":"466e0a6a-f0f2-4c88-88d5-948f7327f982","year":2024},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:51445082f1f69dc02e79456f3b419f272217c4ec6aed574cd94fac4db0b60e9c","observation_id":"0d02b73a-7233-4edb-b287-6ba2add15d17","resolution":{"observed_at":"2026-05-13T07:22:30.226301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Denoising diffusion implicit models","venue":null,"work_id":"2cc3e294-b2d1-450b-b37b-1c165b081fb3","year":2021},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:9809f50f068c543b23ac277047110e56449bbd358dffe5c908ce1683adf02a6a","observation_id":"eace7f3e-3fa1-4d20-908f-3a2a622cd4e3","resolution":{"observed_at":"2026-05-13T08:27:32.517559Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2602.09080","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T03:37:35.890174Z","title":"Looping back to move forward: Recursive transformers for efficient and flexible large multimodal models","venue":null,"work_id":"5f2b4815-1710-4c65-bc4e-af0c69d88af8","year":2026},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:accc84293af7aa06bb9afef42d744c92c625aefbc2bdfa7d690105c512165e7c","observation_id":"eb92a33d-6e8d-49a4-91ec-fc42a9c4f26f","resolution":{"observed_at":"2026-05-13T07:22:28.728002Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Qwen3.6-27B: Flagship-level coding in a 27B dense model, April 2026","venue":null,"work_id":"be1173e5-9f28-45e4-a246-dabf30e93ddc","year":2026},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:77f222ccf5553492a55b709042296141b0b486211b543e12f65ac318a2978948","observation_id":"c7fc4eb3-0b68-4fae-9b21-7fd1d85d6c6c","resolution":{"observed_at":"2026-05-13T08:27:32.509670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-10T17:07:26.457128Z","title":"Deepseek-v4: Towards highly efficient million-token context intelligence","venue":null,"work_id":"b5a5843d-47c0-432e-88d5-c9eaac555a7f","year":2026},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:133113abb3150d38f0c4a739eadd21ace16b222af08d73a783e5c26ac0d8dc22","observation_id":"7fa5de58-3d66-43f9-b38e-3d7a78770a5d","resolution":{"observed_at":"2026-05-13T08:27:32.490970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2601.01739","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T16:09:56.433526Z","title":"K-exaone technical report","venue":null,"work_id":"29bee2c8-e35d-42ba-9fcd-7f63c1aead07","year":2026},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:c1a4f6479edbcfaee2a6714fc497b4936bef9eb890d4542ad55722f18e999b91","observation_id":"baff6871-1e21-4b1f-8901-1245726a1102","resolution":{"observed_at":"2026-05-13T07:22:28.756472Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2601.07022","doi":"10.48550/arxiv.2601.07022","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Solar open technical report","venue":"arXiv (Cornell University)","work_id":"e106cfe8-9043-4d81-9669-ac2a82ac5622","year":2026},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:8137dbb82b6c0264645921a98478b2ea80a03b8b72777412d082ea5aae178e3c","observation_id":"080c59ca-149e-41ad-8e1e-36671eedfe29","resolution":{"observed_at":"2026-05-13T07:22:28.643185Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2512.20856","last_updated":"2025-12-24T00:24:05Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-12-24T00:24:05Z","title":"NVIDIA Nemotron 3: Efficient and Open Intelligence","version":1},"cited_work":{"arxiv_id":"2512.20856","doi":"10.48550/arxiv.2512.20856","metadata_source":"pith","pith_arxiv_id":"2512.20856","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"NVIDIA Nemotron 3: Efficient and Open Intelligence","venue":"cs.CL","work_id":"58d1532f-1164-4b9a-a02a-e1f826067ac2","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/2512.20856","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:125692f31c61426684b9ab31c36859fce6f66e9508df4f1a94f397749369a58f","observation_id":"7dcad8f6-c7b3-4be9-8dbb-47ec5c6ce1bb","resolution":{"observed_at":"2026-05-18T01:40:43.189893Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2603.15031","last_updated":"2026-03-16T09:32:21Z","snapshot_observed_at":"2026-08-02T08:46:00.749789Z","submitted_at":"2026-03-16T09:32:21Z","title":"Attention Residuals","version":1},"cited_work":{"arxiv_id":"2603.15031","doi":"10.48550/arxiv.2603.15031","metadata_source":"pith","pith_arxiv_id":"2603.15031","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Attention Residuals","venue":"cs.CL","work_id":"7356447b-f55f-41d1-b128-b3a54c4c879d","year":2026},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/2603.15031","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:71f226a5337bc4f8a919ddc45944359cbc1b713d98aff370c48b705cd574cf94","observation_id":"c4251de7-1817-4176-80a0-0f497771c026","resolution":{"observed_at":"2026-05-21T06:39:04.582456Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-05-25T12:53:25.083932+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T12:53:25.083932+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.06072","last_updated":"2025-08-01T01:52:05Z","snapshot_observed_at":"2026-08-02T10:09:08.081724Z","submitted_at":"2025-03-08T05:41:42Z","title":"A Survey on Post-training of Large Language Models","version":3},"cited_work":{"arxiv_id":"2503.06072","doi":"10.48550/arxiv.2503.06072","metadata_source":"pith","pith_arxiv_id":"2503.06072","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"press/v274/thede25a.html","venue":"cs.CL","work_id":"9da1f966-0b72-4212-add9-795e0232302e","year":2025},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"cited_paper":"/paper/2503.06072","citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:8dcccbc58b03a13479794a34da822ae9a843f3e590d8e020997acaebeeca79db","observation_id":"baa8338e-4d8c-4e59-b001-0520fc461a9e","resolution":{"observed_at":"2026-05-13T07:22:28.687150Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2602.22661","doi":"10.48550/arxiv.2602.22661","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"dllm: Simple diffusion language modeling.arXiv preprint arXiv:2602.22661","venue":"Open MIND","work_id":"79bb3c31-3372-49bf-a075-d9da0118f456","year":2026},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:e5ece34e73189c12511d46c2332b314547c4ee8b0f8e3f7ec0013b3d97f5c171","observation_id":"cfc109cf-6d20-407b-afd9-f4da74adab98","resolution":{"observed_at":"2026-05-13T07:22:28.762889Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"all but 9 run away","venue":null,"work_id":"22193cbe-2ab7-4801-8dfd-1750b0768b6b","year":2000},"citing_paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-05-13T07:21:04.820743Z"},"links":{"citing_paper":"/paper/2605.11011"},"observation_digest":"sha256:91fd60027c5c6c2505e302690d8e11a4f641e8a8a98eee8702a81b465bfd83b9","observation_id":"fdd0b592-b977-4956-9732-6536fef7c75f","resolution":{"observed_at":"2026-05-13T07:22:30.233496Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.11011","last_updated":"2026-05-10T11:05:20Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T23:22:52.369277Z","submitted_at":"2026-05-10T11:05:20Z","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models"},"reference_resolution":{"displayed":75,"state_counts":{"malformed_identifier":3,"metadata_mismatch":6,"parse_uncertain":0,"unresolved":2,"verified_exact":30,"verified_fuzzy":34},"total_outbound_references":75},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 75 of 75 outbound references and 1 inbound Pith citation observation for arXiv:2605.11011."}