{"as_of":"2026-08-10T13:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3b6c4a55ff77a3c2ba4a54087d4efd88610ad7c77747ec80a871b39844fa82bb","coverage":[{"denominator":26,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":26,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T18:33:20.582143Z","state":"measured"},{"denominator":29,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":29,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T22:00:48.944002Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-02T12:36:57.338642Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"cited_work":{"arxiv_id":"2507.07996","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.07996","snapshot_observed_at":"2026-07-02T12:36:57.338642Z","title":"Skip a layer or loop it? test-time depth adaptation of pretrained llms.arXiv preprint arXiv:2507.07996","venue":null,"work_id":"a896c5d4-7c84-4641-878f-5f366003bd39","year":null},"citing_paper":{"arxiv_id":"2510.12773","last_updated":"2026-05-18T21:02:06Z","snapshot_observed_at":"2026-08-03T04:39:11.410726Z","submitted_at":"2025-10-14T17:51:26Z","title":"Dr.LLM: Dynamic Layer Routing in LLMs","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-21T20:01:48.806709Z"},"links":{"cited_paper":"/paper/2507.07996","citing_paper":"/paper/2510.12773"},"observation_digest":"sha256:24b2577a03b74f25839aa4e9fd715784fb43165c587f730faa4d2685eba06bb1","observation_id":"8468b482-8a3c-4a7c-8aed-3c8825e93da9","resolution":{"observed_at":"2026-05-21T20:04:20.298986Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"cited_work":{"arxiv_id":"2507.07996","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.07996","snapshot_observed_at":"2026-07-02T12:36:57.338642Z","title":"Skip a layer or loop it? test-time depth adaptation of pretrained llms.arXiv preprint arXiv:2507.07996","venue":null,"work_id":"a896c5d4-7c84-4641-878f-5f366003bd39","year":null},"citing_paper":{"arxiv_id":"2606.06574","last_updated":"2026-06-04T17:59:58Z","snapshot_observed_at":"2026-07-06T23:46:24.981618Z","submitted_at":"2026-06-04T17:59:58Z","title":"Skip a Layer or Loop It? Learning Program-of-Layers in LLMs","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-28T01:56:34.435152Z"},"links":{"cited_paper":"/paper/2507.07996","citing_paper":"/paper/2606.06574"},"observation_digest":"sha256:d00f4f1338174a127027e671dd7d570390144ff9b4b5c4a72aa691b04d4bf6ef","observation_id":"da8f35f1-6a78-44dc-8505-e22bebcc4ddd","resolution":{"observed_at":"2026-07-02T12:36:57.341253Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.07996","snapshot_observed_at":"2026-08-07T22:00:48.944002Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.05872","last_updated":"2026-08-06T10:51:34Z","snapshot_observed_at":"2026-08-09T23:11:45.705312Z","submitted_at":"2026-08-06T10:51:34Z","title":"MACRO: Markov Chain Routing of Transformer Layers","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T22:00:48.944002Z"},"links":{"cited_paper":"/paper/2507.07996","citing_paper":"/paper/2608.05872"},"observation_digest":"sha256:8d11c5ec4be8dbeacdc33a9368ac738ae90aa833ea6ee935540a3f5a2169e31a","observation_id":"f25bee59-153a-4efb-b85a-4f65d9f843e3","resolution":{"observed_at":"2026-08-07T22:00:48.944002Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2507.07996/citation-record","integrity":"/paper/2507.07996/integrity","json":"/paper/2507.07996/citation-record.json","paper":"/paper/2507.07996"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:33:18.674198Z","title":"Neural module networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:18.674198Z"},"links":{"citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:8307a59bd450763140b28481e38af076c50e8810c081fedaa2a2b0e339122621","observation_id":"d7a26cbd-3509-4c66-8327-d869ad55327d","resolution":{"observed_at":"2026-08-06T18:33:18.674198Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:33:22.482984Z","title":"Early exit optimizations for additive machine learned ranking systems","venue":null,"work_id":"ae1033e6-1c08-4800-9014-00b59b2f39c8","year":2010},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:18.728193Z"},"links":{"citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:ca867d08876de9f2074b89923567b8b0382109c716179753b42c7a9a3871d60f","observation_id":"1869c13a-d85f-422e-a9af-5f817c52bed5","resolution":{"observed_at":"2026-08-06T18:33:22.592653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13842","last_updated":"2025-02-23T04:31:53Z","snapshot_observed_at":"2026-08-07T18:04:36.168113Z","submitted_at":"2025-02-19T16:02:23Z","title":"Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13842","snapshot_observed_at":"2026-08-06T18:33:18.824715Z","title":"Inner thinking transformer: Leveraging dynamic depth scaling to foster adaptive internal thinking","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:18.824715Z"},"links":{"cited_paper":"/paper/2502.13842","citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:34ec57a426ad5ca34a49fe085acfb983fdbc6c5fb4d20371577dfe2959d8b778","observation_id":"32bceb12-cd5d-4a01-b1ae-e9b06aed766f","resolution":{"observed_at":"2026-08-06T18:33:18.824715Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.05457","snapshot_observed_at":"2026-08-06T18:33:18.869586Z","title":"Think you have solved question answering? try arc, the ai2 reasoning challenge","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:18.869586Z"},"links":{"cited_paper":"/paper/1803.05457","citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:8f95d961933ee42503732b8b7e06698cd2d13299a7cc3594e494a79f91b5a5c7","observation_id":"b921a512-63f0-4d9e-9224-722786fa34d0","resolution":{"observed_at":"2026-08-06T18:33:18.869586Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.03819","snapshot_observed_at":"2026-08-06T18:33:18.945114Z","title":"Uni- versal transformers","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:18.945114Z"},"links":{"cited_paper":"/paper/1807.03819","citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:1574b128daa69b3528068360593c7cc7ed9292ebd8d7e46f8a4e6936dd990471","observation_id":"7cea9865-718d-460f-8427-48947d1a9eea","resolution":{"observed_at":"2026-08-06T18:33:18.945114Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:33:22.254769Z","title":"Faith and fate: Limits of transformers on compositionality","venue":null,"work_id":"b5f72d4f-c69a-4e94-bbca-8ff62029dfa4","year":2023},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:19.014231Z"},"links":{"citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:78963714cda6310e88e14cc2f5cc9afa6e65cf88a8139c350cc684fc28dcb690","observation_id":"aabbfb14-2008-4e3f-b531-226e1d10bdcb","resolution":{"observed_at":"2026-08-06T18:33:22.383678Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.11745","last_updated":"2021-09-24T04:45:55Z","snapshot_observed_at":"2026-08-10T07:07:45.101263Z","submitted_at":"2021-09-24T04:45:55Z","title":"DACT-BERT: Differentiable Adaptive Computation Time for an Efficient BERT Inference","version":1},"cited_work":{"arxiv_id":"2109.11745","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.11745","snapshot_observed_at":"2026-08-06T18:33:20.795652Z","title":"DACT-BERT: Differentiable Adaptive Computation Time for an Efficient BERT Inference","venue":"cs.CL","work_id":"56c5cdfc-3277-41c9-bcbf-496acbfea30f","year":2021},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:19.080315Z"},"links":{"cited_paper":"/paper/2109.11745","citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:f6d005f7b0960d11c139563fde4ade47196be6ca5e2b367966331bc1a3b146d6","observation_id":"b2fcee33-9d97-4b71-8394-cfd48c516dbd","resolution":{"observed_at":"2026-08-06T18:33:20.896116Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.11556","last_updated":"2019-09-25T15:35:03Z","snapshot_observed_at":"2026-08-08T18:02:18.011077Z","submitted_at":"2019-09-25T15:35:03Z","title":"Reducing Transformer Depth on Demand with Structured Dropout","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.11556","snapshot_observed_at":"2026-08-06T18:33:19.194766Z","title":"Reducing transformer depth on demand with structured dropout","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:19.194766Z"},"links":{"cited_paper":"/paper/1909.11556","citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:e18f29190b803861de829706c6deec2f15190401d7a6b74b1606dea3aeafc315","observation_id":"54e80b2d-9a4e-45cd-b894-d3ffe7f781a1","resolution":{"observed_at":"2026-08-06T18:33:19.194766Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.15647","last_updated":"2025-05-12T03:51:20Z","snapshot_observed_at":"2026-08-10T10:38:38.855488Z","submitted_at":"2024-09-24T01:21:17Z","title":"Looped Transformers for Length Generalization","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.15647","snapshot_observed_at":"2026-08-06T18:33:19.337300Z","title":"Looped transformers for length generalization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:19.337300Z"},"links":{"cited_paper":"/paper/2409.15647","citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:fb0af637d15102ec5930283a29b8b939271733a1aca94097856600ee07433dc2","observation_id":"94078844-e10c-4e60-8423-adbe8c9346e9","resolution":{"observed_at":"2026-08-06T18:33:19.337300Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.05171","snapshot_observed_at":"2026-08-06T18:33:19.442435Z","title":"Scaling up test-time compute with latent reasoning: A recurrent depth approach","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:19.442435Z"},"links":{"cited_paper":"/paper/2502.05171","citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:6f97155172990c47942001631d7486cec91a4007a881a20250d83861339311db","observation_id":"b55f4d91-cdd6-4021-a825-612084ff9d7a","resolution":{"observed_at":"2026-08-06T18:33:19.442435Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.08307","last_updated":"2020-05-14T21:58:57Z","snapshot_observed_at":"2026-08-07T23:34:22.325786Z","submitted_at":"2020-02-19T17:40:57Z","title":"Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.08307","snapshot_observed_at":"2026-08-06T18:33:19.515978Z","title":"Compressing bert: Studying the effects of weight pruning on transfer learning","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:19.515978Z"},"links":{"cited_paper":"/paper/2002.08307","citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:27db5769ec228a6b26115577cfa70d8c3dbab558d5c7da0e7328079e6650e3c6","observation_id":"dd5655a8-9313-466c-ba0c-fac2b049e18e","resolution":{"observed_at":"2026-08-06T18:33:19.515978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.19985","last_updated":"2024-07-30T17:26:22Z","snapshot_observed_at":"2026-07-06T18:53:18.201717Z","submitted_at":"2024-07-29T13:19:31Z","title":"Mixture of Nested Experts: Adaptive Processing of Visual Tokens","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.19985","snapshot_observed_at":"2026-08-06T18:33:19.618801Z","title":"Mixture of nested experts: Adaptive processing of visual tokens","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:19.618801Z"},"links":{"cited_paper":"/paper/2407.19985","citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:f37c8afb9a73f1caee19813d8f0c706bebbfbc5987985cee1e07800f1623a66a","observation_id":"cee57b3e-aadb-4b6c-a09b-6995499c7d59","resolution":{"observed_at":"2026-08-06T18:33:19.618801Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.02178","last_updated":"2020-04-29T15:46:34Z","snapshot_observed_at":"2026-08-07T23:53:14.045662Z","submitted_at":"2020-04-05T12:29:20Z","title":"FastBERT: a Self-distilling BERT with Adaptive Inference Time","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.02178","snapshot_observed_at":"2026-08-06T18:33:19.702829Z","title":"Fastbert: a self-distilling bert with adaptive inference time","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:19.702829Z"},"links":{"cited_paper":"/paper/2004.02178","citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:20516c7f806a8783993401a50344c005ce89806cf601fc4ef1c02fc170e50a63","observation_id":"a67d989e-02ae-44e7-9317-17564ded0ee2","resolution":{"observed_at":"2026-08-06T18:33:19.702829Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:33:22.083873Z","title":"Faster depth-adaptive transformers","venue":null,"work_id":"e1f7c6cb-b5a6-4cdf-90e5-0df2b0245efd","year":2021},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:19.751026Z"},"links":{"citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:b6ec012dbca185901d885a5d2685ed23773f474767fe49134909a4d682da0b5b","observation_id":"95647168-7130-41b8-b7ef-53db4423b525","resolution":{"observed_at":"2026-08-06T18:33:22.166579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:33:21.822391Z","title":"Ebert: Efficient bert inference with dynamic structured pruning","venue":null,"work_id":"48b2b782-2f55-4bcd-ba86-43b59527d18b","year":2021},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:19.829868Z"},"links":{"citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:075741fa0dde3a8b08ebe88e9a4ccaffb64f0ba39ac344a3206a72fd532032ff","observation_id":"d16d4018-06bf-469c-b2a4-dcab4e02214c","resolution":{"observed_at":"2026-08-06T18:33:21.923462Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00749","last_updated":"2022-04-25T10:38:17Z","snapshot_observed_at":"2026-08-08T18:43:32.200419Z","submitted_at":"2021-04-01T20:01:57Z","title":"Anytime Dense Prediction with Confidence Adaptivity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00749","snapshot_observed_at":"2026-08-06T18:33:19.899681Z","title":"Anytime dense prediction with confidence adaptivity","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:19.899681Z"},"links":{"cited_paper":"/paper/2104.00749","citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:f64aedbbea0786841c5910edde67898427a0645e6c154fd0607525ddf6f2dc2b","observation_id":"5be22ff9-fbb4-4592-98d1-6d273aaad627","resolution":{"observed_at":"2026-08-06T18:33:19.899681Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:33:21.604668Z","title":"On limitations of the transformer architecture","venue":null,"work_id":"b056f09d-91ff-4207-ba68-02b36e411867","year":2024},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:19.970608Z"},"links":{"citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:75cb8d816a0701e3cecd169a0be6570b5f219e4b63056bcf177ee11baf92c271","observation_id":"6467bace-6a83-454b-bf80-d41bd7e7b32b","resolution":{"observed_at":"2026-08-06T18:33:21.734761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.11446","last_updated":"2022-01-21T18:39:38Z","snapshot_observed_at":"2026-08-09T14:52:01.161814Z","submitted_at":"2021-12-08T19:41:47Z","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.11446","snapshot_observed_at":"2026-08-06T18:33:20.036112Z","title":"Scaling language models: Methods, analysis & insights from training gopher","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:20.036112Z"},"links":{"cited_paper":"/paper/2112.11446","citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:2179ecb1fdb7f26f953cac611d2307750a27c18e7a6f64e77eb93815ae0fe8d4","observation_id":"8181068c-b182-440f-8f3c-3b76f1043e29","resolution":{"observed_at":"2026-08-06T18:33:20.036112Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:33:21.401447Z","title":"You need multiple exiting: Dynamic early exiting for accelerating unified vision language model","venue":null,"work_id":"808855d4-5119-4541-8f23-8b479d51cce5","year":2023},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:20.118401Z"},"links":{"citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:2491e86a13963a4b2c33721c4a26889f74d291cd8683d6c430581225b1cea5ee","observation_id":"7960cd81-b139-40c1-b0e7-5b43dcd2710a","resolution":{"observed_at":"2026-08-06T18:33:21.502530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:33:20.189870Z","title":"Branchynet: Fast inference via early exiting from deep neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:20.189870Z"},"links":{"citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:be77ae7d0a897b739423e76fc7a5a258559e1e36540a9de2a5439720dfce3bb1","observation_id":"35ad1247-b75e-4230-8ff2-a47cf72342b0","resolution":{"observed_at":"2026-08-06T18:33:20.189870Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.13690","last_updated":"2024-12-23T17:32:21Z","snapshot_observed_at":"2026-08-05T19:05:54.552558Z","submitted_at":"2024-06-18T07:14:02Z","title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.13690","snapshot_observed_at":"2026-08-06T18:33:20.272894Z","title":"Dart-math: Difficulty- aware rejection tuning for mathematical problem-solving","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:20.272894Z"},"links":{"cited_paper":"/paper/2407.13690","citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:914a131230b362fb5c75df1a06b5af224885658ee4f937b8583ae790f796d9e7","observation_id":"2efbc4f3-9921-4d8b-b746-56bd1faa0354","resolution":{"observed_at":"2026-08-06T18:33:20.272894Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14093","last_updated":"2025-02-12T08:49:34Z","snapshot_observed_at":"2026-08-09T23:59:11.046246Z","submitted_at":"2024-07-19T07:57:48Z","title":"Routing Experts: Learning to Route Dynamic Experts in Multi-modal Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.14093","snapshot_observed_at":"2026-08-06T18:33:20.319719Z","title":"Routing experts: Learning to route dynamic experts in multi-modal large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:20.319719Z"},"links":{"cited_paper":"/paper/2407.14093","citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:e4ced2c5d2453a2c011b835c44cfa4023fda56046577ad1a9c15799580427c07","observation_id":"d772d0ca-3939-40d3-a7f7-1b8394918ccd","resolution":{"observed_at":"2026-08-06T18:33:20.319719Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.12993","last_updated":"2020-04-27T17:58:05Z","snapshot_observed_at":"2026-08-06T01:22:26.725556Z","submitted_at":"2020-04-27T17:58:05Z","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.12993","snapshot_observed_at":"2026-08-06T18:33:20.378873Z","title":"Deebert: Dynamic early exiting for accelerating bert inference","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:20.378873Z"},"links":{"cited_paper":"/paper/2004.12993","citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:5b2f8d1014268b7dc8fab6843023acc5aa0e5897e850c140b25061bd8e9528af","observation_id":"1ad0b72b-8ed4-48f1-8c13-e706fae5e322","resolution":{"observed_at":"2026-08-06T18:33:20.378873Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:33:21.216631Z","title":"Lgvit: Dynamic early exiting for accelerating vision transformer","venue":null,"work_id":"b213af30-c560-4b36-99d4-c68349169193","year":2023},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:20.451573Z"},"links":{"citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:250520fb2524df30587db32fe91d70a58fb3680d07bb215ed3fd60729b4bbc29","observation_id":"c64381ee-1188-4625-8aa4-517ffdd3ffa8","resolution":{"observed_at":"2026-08-06T18:33:21.277639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.12424","last_updated":"2024-03-16T21:10:38Z","snapshot_observed_at":"2026-07-06T16:50:26.807430Z","submitted_at":"2023-11-21T08:32:38Z","title":"Looped Transformers are Better at Learning Learning Algorithms","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.12424","snapshot_observed_at":"2026-08-06T18:33:20.499325Z","title":"Looped transformers are better at learning learning algorithms","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:20.499325Z"},"links":{"cited_paper":"/paper/2311.12424","citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:e83148e5403bfabf9fda38f10d002d10d2d25541736251d95cd474eeb52155b1","observation_id":"d55f31ec-99ae-4bfe-8207-672fe36795e3","resolution":{"observed_at":"2026-08-06T18:33:20.499325Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:33:21.016761Z","title":"Bert loses patience: Fast and robust inference with early exit","venue":null,"work_id":"c4ec2155-46f3-4b22-bcbf-b92aa31d95b1","year":2020},"citing_paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T18:33:20.582143Z"},"links":{"citing_paper":"/paper/2507.07996"},"observation_digest":"sha256:856a93f9ece8398d98f71caea84ba1059a934b8ab55e0c0d6e6c6bcc7b614d66","observation_id":"a8c89171-2c8a-4720-9f14-c6ae96ba4fbd","resolution":{"observed_at":"2026-08-06T18:33:21.105730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.07996","last_updated":"2025-07-10T17:59:53Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T07:07:45.618793Z","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs"},"reference_resolution":{"displayed":26,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":17,"verified_exact":1,"verified_fuzzy":8},"total_outbound_references":26},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 3 inbound Pith citation observations for arXiv:2507.07996."}