{"as_of":"2026-08-09T11:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d16e2c6f228eae1df75d8ae8e579787a20c3475d1c780cdadeee3ccc08277050","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":15,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":15,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":15,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":15,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T04:08:51.973560Z","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":"2026-05-22T05:34:40.061507Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.14622","last_updated":"2024-07-19T18:38:25Z","snapshot_observed_at":"2026-07-06T18:49:16.284410Z","submitted_at":"2024-07-19T18:38:25Z","title":"BOND: Aligning LLMs with Best-of-N Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.14622","snapshot_observed_at":"2026-08-09T04:08:51.973560Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.03699","last_updated":"2025-07-23T21:26:26Z","snapshot_observed_at":"2026-08-09T04:26:07.182723Z","submitted_at":"2025-02-06T01:22:06Z","title":"LLM Alignment as Retriever Optimization: An Information Retrieval Perspective","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T04:08:51.973560Z"},"links":{"cited_paper":"/paper/2407.14622","citing_paper":"/paper/2502.03699"},"observation_digest":"sha256:b62499087792ed952e5c8caa6daf8bed373954a8efc576b738e87b91a4001f20","observation_id":"780ebc08-f491-4ed6-803c-edc08895bff9","resolution":{"observed_at":"2026-08-09T04:08:51.973560Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14622","last_updated":"2024-07-19T18:38:25Z","snapshot_observed_at":"2026-07-06T18:49:16.284410Z","submitted_at":"2024-07-19T18:38:25Z","title":"BOND: Aligning LLMs with Best-of-N Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.14622","snapshot_observed_at":"2026-08-08T14:27:51.057910Z","title":"Bond: Aligning llms with best-of-n distillation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06781","last_updated":"2025-02-10T18:57:29Z","snapshot_observed_at":"2026-08-08T14:18:42.353169Z","submitted_at":"2025-02-10T18:57:29Z","title":"Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-08T14:27:51.057910Z"},"links":{"cited_paper":"/paper/2407.14622","citing_paper":"/paper/2502.06781"},"observation_digest":"sha256:97af6db259d0034e16e8503fa2b0fdee84bcb78e95673e57e918ccd2e3c38e30","observation_id":"1d2dd4b9-7af2-4202-8fcf-f2333aee9d00","resolution":{"observed_at":"2026-08-08T14:27:51.057910Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14622","last_updated":"2024-07-19T18:38:25Z","snapshot_observed_at":"2026-07-06T18:49:16.284410Z","submitted_at":"2024-07-19T18:38:25Z","title":"BOND: Aligning LLMs with Best-of-N Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.14622","snapshot_observed_at":"2026-08-06T19:28:57.750523Z","title":"Bond: Aligning llms with best-of-n distillation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.05913","last_updated":"2025-07-08T11:59:48Z","snapshot_observed_at":"2026-08-09T02:51:17.508221Z","submitted_at":"2025-07-08T11:59:48Z","title":"Best-of-N through the Smoothing Lens: KL Divergence and Regret Analysis","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-06T19:28:57.750523Z"},"links":{"cited_paper":"/paper/2407.14622","citing_paper":"/paper/2507.05913"},"observation_digest":"sha256:02c5235f9abcdb7932d422fa8f2192997e4d59389a2b794bd2871a960e5f0437","observation_id":"1082371d-7dc0-4884-9d76-215b731ec668","resolution":{"observed_at":"2026-08-06T19:28:57.750523Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14622","last_updated":"2024-07-19T18:38:25Z","snapshot_observed_at":"2026-07-06T18:49:16.284410Z","submitted_at":"2024-07-19T18:38:25Z","title":"BOND: Aligning LLMs with Best-of-N Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.14622","snapshot_observed_at":"2026-08-05T12:25:28.468096Z","title":"Bond: Aligning llms with best-of-n distillation, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.01649","last_updated":"2025-09-01T17:49:14Z","snapshot_observed_at":"2026-08-09T09:23:31.144023Z","submitted_at":"2025-09-01T17:49:14Z","title":"Distilled Pretraining: A modern lens of Data, In-Context Learning and Test-Time Scaling","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-05T12:25:28.468096Z"},"links":{"cited_paper":"/paper/2407.14622","citing_paper":"/paper/2509.01649"},"observation_digest":"sha256:015cc250e14fee277a4c5f0ccaa9bd541a9a945a6aab54c638c00865ff248ec8","observation_id":"f223f575-148c-4056-abc9-c696b265925b","resolution":{"observed_at":"2026-08-05T12:25:28.468096Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14622","last_updated":"2024-07-19T18:38:25Z","snapshot_observed_at":"2026-07-06T18:49:16.284410Z","submitted_at":"2024-07-19T18:38:25Z","title":"BOND: Aligning LLMs with Best-of-N Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.14622","snapshot_observed_at":"2026-08-02T22:14:34.612031Z","title":"G., Dadashi, R., Hussenot, L., Ferret, J., Vieillard, N., Ram \\'e , A., Shariari, B., Perrin, S., Friesen, A., Cideron, G., et al","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.17658","last_updated":"2026-08-05T21:24:03Z","snapshot_observed_at":"2026-08-09T11:09:59.772157Z","submitted_at":"2026-02-19T18:59:03Z","title":"MARS: Margin and Semantic-Aware Data Augmentation for Reward Modeling","version":3},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-02T22:14:34.612031Z"},"links":{"cited_paper":"/paper/2407.14622","citing_paper":"/paper/2602.17658"},"observation_digest":"sha256:444760ab4df7a105807432b87283fb7eb762a491e93b0a27004ec1bd1702bb1d","observation_id":"e97f17ef-17f8-4c86-891e-fbc183b4af29","resolution":{"observed_at":"2026-08-02T22:14:34.612031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14622","last_updated":"2024-07-19T18:38:25Z","snapshot_observed_at":"2026-07-06T18:49:16.284410Z","submitted_at":"2024-07-19T18:38:25Z","title":"BOND: Aligning LLMs with Best-of-N Distillation","version":1},"cited_work":{"arxiv_id":"2407.14622","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.14622","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2407.14622 , year=","venue":null,"work_id":"84bf26bc-d5a4-47e5-a7d5-21469177f44b","year":2024},"citing_paper":{"arxiv_id":"2604.20623","last_updated":"2026-04-22T14:38:41Z","snapshot_observed_at":"2026-07-31T18:27:34.438640Z","submitted_at":"2026-04-22T14:38:41Z","title":"RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-N Ranking","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-10T00:05:26.906011Z"},"links":{"cited_paper":"/paper/2407.14622","citing_paper":"/paper/2604.20623"},"observation_digest":"sha256:7559dcb81a806e29dc755d847b7396512a9f4314263a42931b422dac7d6a6793","observation_id":"aa5be20c-b583-401a-913e-5192ab466c45","resolution":{"observed_at":"2026-05-10T00:24:47.504664Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14622","last_updated":"2024-07-19T18:38:25Z","snapshot_observed_at":"2026-07-06T18:49:16.284410Z","submitted_at":"2024-07-19T18:38:25Z","title":"BOND: Aligning LLMs with Best-of-N Distillation","version":1},"cited_work":{"arxiv_id":"2407.14622","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.14622","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2407.14622 , year=","venue":null,"work_id":"84bf26bc-d5a4-47e5-a7d5-21469177f44b","year":2024},"citing_paper":{"arxiv_id":"2605.01194","last_updated":"2026-05-02T02:13:11Z","snapshot_observed_at":"2026-07-06T23:14:29.125042Z","submitted_at":"2026-05-02T02:13:11Z","title":"VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-09T15:10:16.533927Z"},"links":{"cited_paper":"/paper/2407.14622","citing_paper":"/paper/2605.01194"},"observation_digest":"sha256:74f798359766f2a0e9023d5b930a2c0f7fd4acc73fa0398769bc4b60502cd655","observation_id":"26e0b32c-8c25-41ba-8d73-2fc514b0e68d","resolution":{"observed_at":"2026-05-11T16:46:06.371041Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14622","last_updated":"2024-07-19T18:38:25Z","snapshot_observed_at":"2026-07-06T18:49:16.284410Z","submitted_at":"2024-07-19T18:38:25Z","title":"BOND: Aligning LLMs with Best-of-N Distillation","version":1},"cited_work":{"arxiv_id":"2407.14622","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.14622","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2407.14622 , year=","venue":null,"work_id":"84bf26bc-d5a4-47e5-a7d5-21469177f44b","year":2024},"citing_paper":{"arxiv_id":"2605.04559","last_updated":"2026-05-06T07:02:57Z","snapshot_observed_at":"2026-08-09T10:25:25.665012Z","submitted_at":"2026-05-06T07:02:57Z","title":"Beyond Static Best-of-N: Bayesian List-wise Alignment for LLM-based Recommendation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-08T17:06:18.050592Z"},"links":{"cited_paper":"/paper/2407.14622","citing_paper":"/paper/2605.04559"},"observation_digest":"sha256:edde301124542192ca2831bde16e98b976b0495ab4376971bda35809dfa2e435","observation_id":"5a69ec2c-8e14-4ad1-8c1a-244016933dbc","resolution":{"observed_at":"2026-05-11T17:51:06.553605Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14622","last_updated":"2024-07-19T18:38:25Z","snapshot_observed_at":"2026-07-06T18:49:16.284410Z","submitted_at":"2024-07-19T18:38:25Z","title":"BOND: Aligning LLMs with Best-of-N Distillation","version":1},"cited_work":{"arxiv_id":"2407.14622","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.14622","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2407.14622 , year=","venue":null,"work_id":"84bf26bc-d5a4-47e5-a7d5-21469177f44b","year":2024},"citing_paper":{"arxiv_id":"2605.07105","last_updated":"2026-05-08T01:32:22Z","snapshot_observed_at":"2026-07-06T23:19:30.387067Z","submitted_at":"2026-05-08T01:32:22Z","title":"Theoretical Limits of Language Model Alignment","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-11T01:18:37.614335Z"},"links":{"cited_paper":"/paper/2407.14622","citing_paper":"/paper/2605.07105"},"observation_digest":"sha256:3f013ee16f62cdc64bc8d6e13ffb236f6332bfe14f70689348b63671c37b2e25","observation_id":"4bad8517-7725-47b9-9692-6a7977849f3a","resolution":{"observed_at":"2026-05-11T04:30:57.150653Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14622","last_updated":"2024-07-19T18:38:25Z","snapshot_observed_at":"2026-07-06T18:49:16.284410Z","submitted_at":"2024-07-19T18:38:25Z","title":"BOND: Aligning LLMs with Best-of-N Distillation","version":1},"cited_work":{"arxiv_id":"2407.14622","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.14622","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2407.14622 , year=","venue":null,"work_id":"84bf26bc-d5a4-47e5-a7d5-21469177f44b","year":2024},"citing_paper":{"arxiv_id":"2605.17295","last_updated":"2026-05-17T07:14:44Z","snapshot_observed_at":"2026-08-05T14:05:32.700721Z","submitted_at":"2026-05-17T07:14:44Z","title":"DISA: Offline Importance Sampling for Distribution-Matching LLM-RL","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-05-20T15:11:43.235574Z"},"links":{"cited_paper":"/paper/2407.14622","citing_paper":"/paper/2605.17295"},"observation_digest":"sha256:806cf103af7157b5d2a390f38385628a714172bf517e2b5ad965725557b3999e","observation_id":"e0407e19-face-4ffb-9554-062912a861f0","resolution":{"observed_at":"2026-05-20T15:13:24.873415Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14622","last_updated":"2024-07-19T18:38:25Z","snapshot_observed_at":"2026-07-06T18:49:16.284410Z","submitted_at":"2024-07-19T18:38:25Z","title":"BOND: Aligning LLMs with Best-of-N Distillation","version":1},"cited_work":{"arxiv_id":"2407.14622","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.14622","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2407.14622 , year=","venue":null,"work_id":"84bf26bc-d5a4-47e5-a7d5-21469177f44b","year":2024},"citing_paper":{"arxiv_id":"2605.22389","last_updated":"2026-05-21T12:21:41Z","snapshot_observed_at":"2026-07-06T23:32:44.699825Z","submitted_at":"2026-05-21T12:21:41Z","title":"Unified Data Selection for LLM Reasoning","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-05-22T05:33:20.930156Z"},"links":{"cited_paper":"/paper/2407.14622","citing_paper":"/paper/2605.22389"},"observation_digest":"sha256:4990befcfa5388045a06d71705f4bca62e535a0dd2627167d9e1261154c54f55","observation_id":"753a7dca-5e71-47ea-aa42-414e710f19b3","resolution":{"observed_at":"2026-05-22T05:34:40.064535Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14622","last_updated":"2024-07-19T18:38:25Z","snapshot_observed_at":"2026-07-06T18:49:16.284410Z","submitted_at":"2024-07-19T18:38:25Z","title":"BOND: Aligning LLMs with Best-of-N Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.14622","snapshot_observed_at":"2026-07-11T13:53:36.775836Z","title":"arXiv preprint arXiv:2407.14622 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.04763","last_updated":"2026-07-26T14:17:18Z","snapshot_observed_at":"2026-08-02T10:24:43.977557Z","submitted_at":"2026-07-06T07:56:53Z","title":"Multi-Turn On-Policy Distillation with Prefix Replay","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-07-11T13:53:36.775836Z"},"links":{"cited_paper":"/paper/2407.14622","citing_paper":"/paper/2607.04763"},"observation_digest":"sha256:83eecd1a120429e6abbf1ab39f0da8d7d03d01117a50ad5259c58147407ae4ca","observation_id":"a997f7ca-4d3b-41f8-87f2-94fe8a34aa3c","resolution":{"observed_at":"2026-07-11T13:53:36.775836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14622","last_updated":"2024-07-19T18:38:25Z","snapshot_observed_at":"2026-07-06T18:49:16.284410Z","submitted_at":"2024-07-19T18:38:25Z","title":"BOND: Aligning LLMs with Best-of-N Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.14622","snapshot_observed_at":"2026-08-02T08:40:38.041034Z","title":"arXiv preprint arXiv:2407.14622 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.04763","last_updated":"2026-07-26T14:17:18Z","snapshot_observed_at":"2026-08-02T10:24:43.977557Z","submitted_at":"2026-07-06T07:56:53Z","title":"Multi-Turn On-Policy Distillation with Prefix Replay","version":3},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-02T08:40:38.041034Z"},"links":{"cited_paper":"/paper/2407.14622","citing_paper":"/paper/2607.04763"},"observation_digest":"sha256:eaa854018368bd60f8fb28613ca3977d21ecc56d31733a939935492f51482dd5","observation_id":"d7d425d7-542b-4f87-8f9f-41bd278ad717","resolution":{"observed_at":"2026-08-02T08:40:38.041034Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14622","last_updated":"2024-07-19T18:38:25Z","snapshot_observed_at":"2026-07-06T18:49:16.284410Z","submitted_at":"2024-07-19T18:38:25Z","title":"BOND: Aligning LLMs with Best-of-N Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.14622","snapshot_observed_at":"2026-07-13T00:53:20.749426Z","title":"Bond: Aligning llms with best-of-n distillation.arXiv preprint arXiv:2407.14622, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.09029","last_updated":"2026-07-10T01:31:02Z","snapshot_observed_at":"2026-08-05T04:46:01.445537Z","submitted_at":"2026-07-10T01:31:02Z","title":"MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-13T00:53:20.749426Z"},"links":{"cited_paper":"/paper/2407.14622","citing_paper":"/paper/2607.09029"},"observation_digest":"sha256:4e842ed122202559343802f54383cc275d3e281f275aa183c5ac73ff4b45a446","observation_id":"2de83db1-ff94-4a75-a2ac-32f6c971f8a2","resolution":{"observed_at":"2026-07-13T00:53:20.749426Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14622","last_updated":"2024-07-19T18:38:25Z","snapshot_observed_at":"2026-07-06T18:49:16.284410Z","submitted_at":"2024-07-19T18:38:25Z","title":"BOND: Aligning LLMs with Best-of-N Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.14622","snapshot_observed_at":"2026-07-14T06:44:16.198117Z","title":"BOND : Aligning LLMs with best-of- N distillation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.11146","last_updated":"2026-07-13T06:37:42Z","snapshot_observed_at":"2026-08-04T11:23:41.061756Z","submitted_at":"2026-07-13T06:37:42Z","title":"Rank-Conditioned Sample Reuse for the Plackett--Luce Best-of-$K$ Objective","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-07-14T06:44:16.198117Z"},"links":{"cited_paper":"/paper/2407.14622","citing_paper":"/paper/2607.11146"},"observation_digest":"sha256:19d3a818c2edcbac2655ec00783f559e77ce3e5a57fd49f4dee4813d90f2edaa","observation_id":"4cb0ef76-f7d2-4d3b-9c00-9b632553fef5","resolution":{"observed_at":"2026-07-14T06:44:16.198117Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2407.14622/citation-record","integrity":"/paper/2407.14622/integrity","json":"/paper/2407.14622/citation-record.json","paper":"/paper/2407.14622"},"outbound":[],"paper":{"arxiv_id":"2407.14622","last_updated":"2024-07-19T18:38:25Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T18:49:16.284410Z","submitted_at":"2024-07-19T18:38:25Z","title":"BOND: Aligning LLMs with Best-of-N Distillation"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 15 inbound Pith citation observations for arXiv:2407.14622."}