{"as_of":"2026-08-17T05:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:93cc89b176201813533e8d7caab4efbef2a141084fa7d5563765b2425a60ef18","coverage":[{"denominator":30,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":30,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:22:31.573595Z","state":"measured"},{"denominator":32,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":32,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T07:31:30.002413Z","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":"2026-05-15T07:43:11.730902Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"cited_work":{"arxiv_id":"2507.17728","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.17728","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Megrez2 technical report","venue":null,"work_id":"653a7e93-c6eb-48c6-bbd0-9ea1d461887a","year":2025},"citing_paper":{"arxiv_id":"2510.25741","last_updated":"2026-07-01T23:25:58Z","snapshot_observed_at":"2026-08-13T23:04:32.343355Z","submitted_at":"2025-10-29T17:45:42Z","title":"Scaling Latent Reasoning via Looped Language Models","version":4},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-15T07:43:11.620446Z"},"links":{"cited_paper":"/paper/2507.17728","citing_paper":"/paper/2510.25741"},"observation_digest":"sha256:b278cdf72a33aa2585bb2cb269b269f73840c14662b60d8bf512a4c24cc34341","observation_id":"d2458f03-1b65-42e4-b243-d34a5dbec593","resolution":{"observed_at":"2026-05-15T07:43:11.733057Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.17728","snapshot_observed_at":"2026-08-04T07:31:30.002413Z","title":"Megrez2 technical report.arXiv preprint arXiv:2507.17728, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.25741","last_updated":"2026-07-01T23:25:58Z","snapshot_observed_at":"2026-08-13T23:04:32.343355Z","submitted_at":"2025-10-29T17:45:42Z","title":"Scaling Latent Reasoning via Looped Language Models","version":5},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T07:31:30.002413Z"},"links":{"cited_paper":"/paper/2507.17728","citing_paper":"/paper/2510.25741"},"observation_digest":"sha256:043bf85a57d66e8a9cf044dfbef755e4e2bee783c926c4745418c416f4b7c312","observation_id":"664b41ab-d79e-41f6-b34f-f8b47399cc55","resolution":{"observed_at":"2026-08-04T07:31:30.002413Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2507.17728/citation-record","integrity":"/paper/2507.17728/integrity","json":"/paper/2507.17728/citation-record.json","paper":"/paper/2507.17728"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.01743","last_updated":"2025-03-07T09:05:58Z","snapshot_observed_at":"2026-08-15T22:57:45.773661Z","submitted_at":"2025-03-03T17:05:52Z","title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.01743","snapshot_observed_at":"2026-08-15T18:22:31.423242Z","title":"Phi-4-mini technical report: Compact yet powerful multimodal language models via mixture-of-loras","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.423242Z"},"links":{"cited_paper":"/paper/2503.01743","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:34d84f90801fc77d4f790e4bf5d63d0cef0cc6c4ce74efb19e58a65d2f52affb","observation_id":"7408cc4d-dd1a-4f3e-b390-6d6a56c17984","resolution":{"observed_at":"2026-08-15T18:22:31.423242Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-17T03:30:12.735656Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-15T18:22:31.429139Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.429139Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:76021db065c67759c956ccc6fbcbbe704a8affe98a41cfad5f4f845d71fbfd15","observation_id":"b24c8a24-0c9a-49a1-907f-8ca01019e7ed","resolution":{"observed_at":"2026-08-15T18:22:31.429139Z","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":"2026-08-15T18:22:32.125054Z","title":"https://github.com/MoonshotAI/Kimi-K2","venue":null,"work_id":"bb414301-b9be-43ea-881e-1390d6575b9c","year":2025},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.433760Z"},"links":{"citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:459003b992cffce40de3c19bc8aa0693523b51fd682d92e125697c2a9bb70eed","observation_id":"c18bebae-ee4b-4059-8dd5-6ceabad935ef","resolution":{"observed_at":"2026-08-15T18:22:32.129952Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.07732","last_updated":"2021-08-16T03:57:30Z","snapshot_observed_at":"2026-08-15T17:40:38.050939Z","submitted_at":"2021-08-16T03:57:30Z","title":"Program Synthesis with Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.07732","snapshot_observed_at":"2026-08-15T18:22:31.439223Z","title":"Program synthesis with large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.439223Z"},"links":{"cited_paper":"/paper/2108.07732","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:74156899df0fbe72d54d17458907a269ffffb186f84114ccb7c4941947feae2a","observation_id":"a6aabc3e-5c8f-4be6-b691-6b9ef877773a","resolution":{"observed_at":"2026-08-15T18:22:31.439223Z","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":"2026-08-15T18:22:32.109290Z","title":"Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design","venue":null,"work_id":"594d07ae-c2d8-4b8e-86f1-8a142f5398c2","year":2024},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.444259Z"},"links":{"citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:10a99df431dad2bd93cc3d1b6ffd1db0befd889cd259152d0679f0398fe51766","observation_id":"5a04d115-6d1a-4161-b026-49befda38162","resolution":{"observed_at":"2026-08-15T18:22:32.114717Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.03374","last_updated":"2021-07-14T17:16:02Z","snapshot_observed_at":"2026-08-08T11:58:24.516369Z","submitted_at":"2021-07-07T17:41:24Z","title":"Evaluating Large Language Models Trained on Code","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.03374","snapshot_observed_at":"2026-08-15T18:22:31.448585Z","title":"Evaluating Large Language Models Trained on Code","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.448585Z"},"links":{"cited_paper":"/paper/2107.03374","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:af100a2a953cf8de33e0ade70ef47069ffdf55f24a71057837fef369c3f661f0","observation_id":"89f26a69-0768-4100-9501-a3cf1553bea4","resolution":{"observed_at":"2026-08-15T18:22:31.448585Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-14T02:43:01.480086Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-15T18:22:31.453786Z","title":"Training Verifiers to Solve Math Word Problems","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.453786Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:c494286b9f1e224a5141602b97e0b5896000c30f52d6d36d50b319b2ff3b7abb","observation_id":"ee2a01a2-7b50-4815-8f52-a9b4fc306acb","resolution":{"observed_at":"2026-08-15T18:22:31.453786Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.06066","last_updated":"2024-01-11T17:31:42Z","snapshot_observed_at":"2026-08-13T15:18:04.411100Z","submitted_at":"2024-01-11T17:31:42Z","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.06066","snapshot_observed_at":"2026-08-15T18:22:31.458015Z","title":"Deepseekmoe: Towards ultimate expert specialization in mixture-of-experts language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.458015Z"},"links":{"cited_paper":"/paper/2401.06066","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:232bbe2e2d8b1f5d1e3e16c71df2b48b3671b6140360abaaa89dd1e6a8bfa63e","observation_id":"e88677d7-12a3-459c-88f7-bd0812465610","resolution":{"observed_at":"2026-08-15T18:22:31.458015Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.17238","last_updated":"2023-12-28T18:58:13Z","snapshot_observed_at":"2026-08-16T14:31:04.390700Z","submitted_at":"2023-12-28T18:58:13Z","title":"Fast Inference of Mixture-of-Experts Language Models with Offloading","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.17238","snapshot_observed_at":"2026-08-15T18:22:31.462458Z","title":"Fast inference of mixture-of-experts language models with offloading","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.462458Z"},"links":{"cited_paper":"/paper/2312.17238","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:8991741aed16401e806018e061475e082a79bc9e00308caaff5c7b0fc9e273d6","observation_id":"bda07f25-80c4-4669-9b8e-bc1e5e3ed92b","resolution":{"observed_at":"2026-08-15T18:22:31.462458Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-08-15T12:33:55.451951Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-15T18:22:31.466907Z","title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.466907Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:e3675461602d2de8d41f5b08f813c1a60c2553d8cdec85656577409abf73c594","observation_id":"2cebd7bb-92c4-4e2e-9c69-7bb59dd7489d","resolution":{"observed_at":"2026-08-15T18:22:31.466907Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.03874","last_updated":"2021-11-08T21:30:18Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-03-05T18:59:39Z","title":"Measuring Mathematical Problem Solving With the MATH Dataset","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.03874","snapshot_observed_at":"2026-08-15T18:22:31.471074Z","title":"Measuring mathematical problem solving with the math dataset","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.471074Z"},"links":{"cited_paper":"/paper/2103.03874","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:1e0ee70f0e400b85a7a4f84826163b510ff059309f6acd2e9c90ba00a34e16a0","observation_id":"88f33b04-ed93-4b17-a853-c7e168c88766","resolution":{"observed_at":"2026-08-15T18:22:31.471074Z","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":"2026-08-15T18:22:32.092854Z","title":"C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models","venue":null,"work_id":"a498235f-45f9-4886-8e77-05a372cb8602","year":2024},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.476293Z"},"links":{"citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:0f3dac116df510eac9663ce7ce1c14cc1abcafd83b96f5ebf0a1a719f848956c","observation_id":"e0d5a180-a44d-4c07-8ebd-2ee400ca10bd","resolution":{"observed_at":"2026-08-15T18:22:32.098712Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:22:32.074932Z","title":"Pre-gated moe: An algorithm-system co-design for fast and scalable mixture-of-expert inference","venue":null,"work_id":"b7aee03a-8436-4358-9702-9349ea8ddbff","year":2024},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.483727Z"},"links":{"citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:ca4cc1a0bb104af5a510568acdba8cf76163384e00f25867bad48af849d7a73a","observation_id":"ae1f1fdb-6c18-4bdc-9e89-27077b32701a","resolution":{"observed_at":"2026-08-15T18:22:32.080637Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.19786","last_updated":"2025-03-25T15:52:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-03-25T15:52:34Z","title":"Gemma 3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.19786","snapshot_observed_at":"2026-08-15T18:22:31.489869Z","title":"Gemma 3 Technical Report","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.489869Z"},"links":{"cited_paper":"/paper/2503.19786","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:5a8cb20bc9ff653bfd18b7210c65721e0f6b977623db78cd85285560d6447053","observation_id":"1a48f460-0aec-47f7-b8ab-f84b9ef3929f","resolution":{"observed_at":"2026-08-15T18:22:31.489869Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.15803","last_updated":"2025-02-19T06:14:14Z","snapshot_observed_at":"2026-08-16T12:57:06.482972Z","submitted_at":"2025-02-19T06:14:14Z","title":"Megrez-Omni Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.15803","snapshot_observed_at":"2026-08-15T18:22:31.495411Z","title":"Megrez-omni technical report","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.495411Z"},"links":{"cited_paper":"/paper/2502.15803","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:f012b99f2a815704607522a97e2d50b59f841ec59d7722d5732559594fffcd25","observation_id":"61cf7f48-7b74-4b88-b97c-389fd402cc26","resolution":{"observed_at":"2026-08-15T18:22:31.495411Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.04434","last_updated":"2024-06-19T06:04:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-05-07T15:56:43Z","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.04434","snapshot_observed_at":"2026-08-15T18:22:31.500853Z","title":"Deepseek-v2: A strong, economical, and efficient mixture-of-experts language model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.500853Z"},"links":{"cited_paper":"/paper/2405.04434","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:3c5bd23db6eb142a75256694cfc5b24d3a0e2fb62f865a8328d2de7ab0f5f6ce","observation_id":"607186a0-6097-44fd-aa0d-8d349315e6d4","resolution":{"observed_at":"2026-08-15T18:22:31.500853Z","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":"2026-08-15T18:22:32.057925Z","title":"https://ai","venue":null,"work_id":"cb47273f-38db-42f5-a530-363d67e0be77","year":2025},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.506223Z"},"links":{"citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:37967e6c3dd6cbbc6ea6fb9149602ada8831de6d1d71d5c67ee2dd4c7c3e0398","observation_id":"d261e4ae-c571-471f-9d59-1acb1440e4a6","resolution":{"observed_at":"2026-08-15T18:22:32.062735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:22:32.042256Z","title":"OpenAI blog post","venue":null,"work_id":"2860943e-f15b-4a40-9b7e-99ce78626c01","year":2024},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.511618Z"},"links":{"citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:8c9f6a611d77e4f0a4c05600f4f1904122bb954b0c5d6a0ef22a505e8a2a07de","observation_id":"aa1a5e49-3bb0-42d2-8705-1de0005d8fca","resolution":{"observed_at":"2026-08-15T18:22:32.047015Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:22:32.026546Z","title":"2025.URL: https://openai.com/index/introducing-o3- and-o4-mini/","venue":null,"work_id":"1d030e03-4b19-48a3-a67c-a20367fbd771","year":2025},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.517751Z"},"links":{"citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:86b7438e91b171d4b5668ad2ea754d58bc62365f557db2eefb45dbb839f26010","observation_id":"4488eef3-f5e7-4545-97b3-215ca830edb3","resolution":{"observed_at":"2026-08-15T18:22:32.031128Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1506.02438","last_updated":"2018-10-20T18:55:07Z","snapshot_observed_at":"2026-08-15T05:06:05.489107Z","submitted_at":"2015-06-08T11:12:48Z","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.02438","snapshot_observed_at":"2026-08-15T18:22:31.523116Z","title":"High-dimensional continu- ous control using generalized advantage estimation","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.523116Z"},"links":{"cited_paper":"/paper/1506.02438","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:4b49cb98be08858b7c6bc0697da05ee92b55cd2c5c0a5a8b72008d8201fd1287","observation_id":"f35391cf-7bfe-43bf-a253-bf9f8bbb173f","resolution":{"observed_at":"2026-08-15T18:22:31.523116Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03300","last_updated":"2024-04-27T15:25:53Z","snapshot_observed_at":"2026-08-06T14:58:42.911363Z","submitted_at":"2024-02-05T18:55:32Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-08-15T18:22:31.528917Z","title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.528917Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:4a4ca122d52d69db4bbe8c7b1d82bb38c4aa6a1c26358dc753977c32728fec55","observation_id":"de308f28-18c9-4fb6-8c1f-053ba5cbd31a","resolution":{"observed_at":"2026-08-15T18:22:31.528917Z","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":"2026-08-15T18:22:32.009577Z","title":"Roformer: Enhanced trans- former with rotary position embedding","venue":null,"work_id":"8c4955f9-9536-4b29-8b43-4cda22e9b062","year":2024},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.534150Z"},"links":{"citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:25026c213c1b78c2bcb5e52f18bae31d623f8a0cd0ece691e571e700e7541fb2","observation_id":"ca65bfeb-c9ee-44ad-a050-c73e7e285444","resolution":{"observed_at":"2026-08-15T18:22:32.015811Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:22:31.989993Z","title":"Dai, Anja Hauth, Katie Millican, et al.Gemini: A Family of Highly Capable Multimodal Models","venue":null,"work_id":"920d377b-33b1-4c86-a43d-6ccfa5fcd073","year":null},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.538958Z"},"links":{"citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:962d0b3116ac69cd734ec2795ebacf8031d00c749ebf8c0df23851ba459591d5","observation_id":"ec23250f-0d0f-4bb3-912b-6e14fbf2daae","resolution":{"observed_at":"2026-08-15T18:22:31.996187Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15664","last_updated":"2024-08-28T09:31:09Z","snapshot_observed_at":"2026-08-15T04:59:51.918109Z","submitted_at":"2024-08-28T09:31:09Z","title":"Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.15664","snapshot_observed_at":"2026-08-15T18:22:31.548915Z","title":"Auxiliary-loss-free load balancing strategy for mixture-of-experts","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.548915Z"},"links":{"cited_paper":"/paper/2408.15664","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:250e474a878f7793026fb3f2c1bd9d4f4cbf9a53cf231e8581e6648b84978617","observation_id":"5d0f71e9-6386-4161-b27c-bf74e4006ed6","resolution":{"observed_at":"2026-08-15T18:22:31.548915Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.01574","last_updated":"2024-11-06T02:54:00Z","snapshot_observed_at":"2026-08-06T00:29:17.674418Z","submitted_at":"2024-06-03T17:53:00Z","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.01574","snapshot_observed_at":"2026-08-15T18:22:31.553751Z","title":"Mmlu-pro: A more robust and challenging multi-task language understand- ing benchmark, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.553751Z"},"links":{"cited_paper":"/paper/2406.01574","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:c9e72921a9124c78086b52203451f6050df8a17c690d060e28518ae9cfc70938","observation_id":"7aa166cd-942a-413e-97d1-7b772eefca7c","resolution":{"observed_at":"2026-08-15T18:22:31.553751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.06563","last_updated":"2024-06-03T03:58:41Z","snapshot_observed_at":"2026-08-16T13:46:54.450188Z","submitted_at":"2024-06-03T03:58:41Z","title":"Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.06563","snapshot_observed_at":"2026-08-15T18:22:31.558747Z","title":"Skywork-moe: A deep dive into training techniques for mixture-of-experts language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.558747Z"},"links":{"cited_paper":"/paper/2406.06563","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:ccb1c6b929c6f549bc6985ad04fbf2c6b5b1f8f7c073836ad81abe7b3a3c54fc","observation_id":"d4d98c11-b027-47a4-9f96-0e925258a363","resolution":{"observed_at":"2026-08-15T18:22:31.558747Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-08-15T18:22:31.563892Z","title":"Qwen3 Technical Report","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.563892Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:873ea8b14fcb1c3ffdef7d07c7a076e23ecb220a8f37b8cbba7e157be1a0c384","observation_id":"5b44c9ab-69f7-4b8c-bf3a-d6efd81fb4b7","resolution":{"observed_at":"2026-08-15T18:22:31.563892Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-08-15T18:22:31.568825Z","title":"Qwen2.5 Technical Report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.568825Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:d7fdf1bf771a4698df3bdaba8250bb473f3e8cb5caadae158a416994bc05418b","observation_id":"b79c4425-af2a-4cf3-adf0-0a47d0a5bc1f","resolution":{"observed_at":"2026-08-15T18:22:31.568825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07911","last_updated":"2023-11-14T05:13:55Z","snapshot_observed_at":"2026-07-06T16:47:08.877195Z","submitted_at":"2023-11-14T05:13:55Z","title":"Instruction-Following Evaluation for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07911","snapshot_observed_at":"2026-08-15T18:22:31.573595Z","title":"Instruction-following evaluation for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.573595Z"},"links":{"cited_paper":"/paper/2311.07911","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:e405c64e271d5066aa9213ae080a98905e08c5546815bbf4e67aced1086b54c1","observation_id":"53b9c0dd-613e-4c51-9e7c-d8f74f8c8806","resolution":{"observed_at":"2026-08-15T18:22:31.573595Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-08-15T18:22:31.543753Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-15T18:22:31.543753Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2507.17728"},"observation_digest":"sha256:03a88d4977a15cd5863682f94a0d9f99f7f96f3696cf76b0919d908246d3083f","observation_id":"2aae55a4-2ece-49fa-86a2-ce8e4f371296","resolution":{"observed_at":"2026-08-15T18:22:31.543753Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.17728","last_updated":"2025-07-23T17:43:07Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-15T18:15:44.419651Z","submitted_at":"2025-07-23T17:43:07Z","title":"Megrez2 Technical Report"},"reference_resolution":{"displayed":30,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":0,"verified_fuzzy":9},"total_outbound_references":30},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 2 inbound Pith citation observations for arXiv:2507.17728."}