{"as_of":"2026-08-08T19:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:86260ca38badc2e1d3d839bf671a4b0cedf0b71e46088ee7867f8925b3310cf4","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":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":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":29,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":29,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T18:43:34.269002Z","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":"2026-05-23T18:35:46.085118Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":"2103.10360","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2103.10360 , year=","venue":null,"work_id":"46d7bb97-b94f-4fe6-8291-6d532f004dfa","year":2021},"citing_paper":{"arxiv_id":"2309.10253","last_updated":"2024-06-27T16:01:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-19T02:19:48Z","title":"GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-15T06:25:20.966510Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2309.10253"},"observation_digest":"sha256:c5719176d0037b9668f7dc07f7a63de0dca27d49ec5cb22e124d9bee48416d1b","observation_id":"ee382f04-34f1-4bae-bc18-54fd109ba7e6","resolution":{"observed_at":"2026-05-15T06:25:21.013670Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":"2103.10360","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2103.10360 , year=","venue":null,"work_id":"46d7bb97-b94f-4fe6-8291-6d532f004dfa","year":2021},"citing_paper":{"arxiv_id":"2311.12793","last_updated":"2023-11-28T08:52:50Z","snapshot_observed_at":"2026-08-04T08:17:54.774738Z","submitted_at":"2023-11-21T18:58:11Z","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-13T17:08:12.727773Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2311.12793"},"observation_digest":"sha256:99a076f211a2337f9c83ed4e0707fc65b6cf83d6f629d74b52662fae83f60c14","observation_id":"721dee73-8d36-47e0-ad79-a15ec4e06c07","resolution":{"observed_at":"2026-05-13T17:08:12.821845Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":"2103.10360","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2103.10360 , year=","venue":null,"work_id":"46d7bb97-b94f-4fe6-8291-6d532f004dfa","year":2021},"citing_paper":{"arxiv_id":"2312.16886","last_updated":"2023-12-30T04:59:21Z","snapshot_observed_at":"2026-07-29T22:12:01.108911Z","submitted_at":"2023-12-28T08:21:24Z","title":"MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-16T16:35:37.937462Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2312.16886"},"observation_digest":"sha256:4c75af0d2926377704dd8d578713ccba86bd79ad736eff443d0527c61be25569","observation_id":"0f6e36c1-d041-40e0-a38c-e74bf1b91b45","resolution":{"observed_at":"2026-05-16T16:35:38.059819Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":"2103.10360","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2103.10360 , year=","venue":null,"work_id":"46d7bb97-b94f-4fe6-8291-6d532f004dfa","year":2021},"citing_paper":{"arxiv_id":"2401.15947","last_updated":"2024-12-23T08:05:14Z","snapshot_observed_at":"2026-08-06T02:31:58.372974Z","submitted_at":"2024-01-29T08:13:40Z","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","version":5},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-16T02:33:30.143907Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2401.15947"},"observation_digest":"sha256:fb5673189be8d799f6a9be0b5635fc04af5142191e982b3c84093be739eda5b5","observation_id":"e5e6d3bf-1e68-42f1-af23-7a5a20ad2b4c","resolution":{"observed_at":"2026-05-16T02:33:30.269407Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":"2103.10360","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2103.10360 , year=","venue":null,"work_id":"46d7bb97-b94f-4fe6-8291-6d532f004dfa","year":2021},"citing_paper":{"arxiv_id":"2403.20330","last_updated":"2024-04-09T15:17:50Z","snapshot_observed_at":"2026-08-07T12:15:30.838846Z","submitted_at":"2024-03-29T17:59:34Z","title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-12T19:41:44.263663Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2403.20330"},"observation_digest":"sha256:78b8eb1a0171f4d131a59fe7a13fbf6d5a0ffe10b3e61093ac22a3329fd0b5a2","observation_id":"e415fc6f-9c52-4d37-ad88-4581e49ece8f","resolution":{"observed_at":"2026-05-12T19:41:44.489792Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":"2103.10360","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2103.10360 , year=","venue":null,"work_id":"46d7bb97-b94f-4fe6-8291-6d532f004dfa","year":2021},"citing_paper":{"arxiv_id":"2404.06395","last_updated":"2024-06-03T08:54:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-04-09T15:36:50Z","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-13T18:00:53.389420Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2404.06395"},"observation_digest":"sha256:baa38f3e888c598cff785541c4e6ca81c1c666650c5a9bea567095e564336cf1","observation_id":"548c76d3-7bd6-4735-b652-faf5b02c2518","resolution":{"observed_at":"2026-05-13T18:00:53.454048Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":"2103.10360","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2103.10360 , year=","venue":null,"work_id":"46d7bb97-b94f-4fe6-8291-6d532f004dfa","year":2021},"citing_paper":{"arxiv_id":"2404.14294","last_updated":"2024-07-19T04:47:36Z","snapshot_observed_at":"2026-07-06T18:03:47.096406Z","submitted_at":"2024-04-22T15:53:08Z","title":"A Survey on Efficient Inference for Large Language Models","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-15T02:39:33.007894Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2404.14294"},"observation_digest":"sha256:8913beefd04f404cb38e02dcbd09c992471a49d6175755c0280c54437ffdb8c2","observation_id":"a4a6cfbf-a7a3-4bff-839d-1b2fdc4c28db","resolution":{"observed_at":"2026-05-15T02:39:33.182136Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":"2103.10360","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2103.10360 , year=","venue":null,"work_id":"46d7bb97-b94f-4fe6-8291-6d532f004dfa","year":2021},"citing_paper":{"arxiv_id":"2406.08035","last_updated":"2025-08-09T10:54:59Z","snapshot_observed_at":"2026-08-08T19:38:26.415599Z","submitted_at":"2024-06-12T09:36:52Z","title":"LVBench: An Extreme Long Video Understanding Benchmark","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-19T11:55:30.048525Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2406.08035"},"observation_digest":"sha256:4c2a515e74b136e8ffa2f308eb8dfbbde1a8390d0482c0c0a3c7868bbdcbdcbd","observation_id":"24dbca9a-01d5-49c8-8a2c-69fcd1baa674","resolution":{"observed_at":"2026-05-19T11:55:30.160646Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":"2103.10360","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2103.10360 , year=","venue":null,"work_id":"46d7bb97-b94f-4fe6-8291-6d532f004dfa","year":2021},"citing_paper":{"arxiv_id":"2410.13903","last_updated":"2026-04-27T01:53:46Z","snapshot_observed_at":"2026-07-06T19:35:35.229351Z","submitted_at":"2024-10-16T08:14:24Z","title":"CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-23T18:35:10.313449Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2410.13903"},"observation_digest":"sha256:df232c893094ce839dadca221b6b3d2b0ff25901e8c094fc6d3faab6b11cbbc3","observation_id":"e42fb667-ce82-4385-aaac-c401a0eecee0","resolution":{"observed_at":"2026-05-23T18:35:46.087907Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-08-08T18:43:34.269002Z","title":"Glm: General language model pretraining with autoregressive blank infilling","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.06881","last_updated":"2025-02-08T14:59:06Z","snapshot_observed_at":"2026-08-08T19:26:24.824524Z","submitted_at":"2025-02-08T14:59:06Z","title":"A Comprehensive Review of Protein Language Models","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-08T18:43:34.269002Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2502.06881"},"observation_digest":"sha256:c43e7af626368178171bcfacaa5526ed1d4308e9037fa1741f053a9f5087f450","observation_id":"9fce844a-5f83-4b3e-b875-582be6dd2bcb","resolution":{"observed_at":"2026-08-08T18:43:34.269002Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-08-08T17:10:39.711429Z","title":"Glm: General language model pretraining with autoregressive blank infilling, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.06901","last_updated":"2025-02-09T20:02:05Z","snapshot_observed_at":"2026-08-08T17:00:41.319015Z","submitted_at":"2025-02-09T20:02:05Z","title":"Enabling Autoregressive Models to Fill In Masked Tokens","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-08T17:10:39.711429Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2502.06901"},"observation_digest":"sha256:32ae51767ed747a07d386c8e1c2db6a0eb811e5d946a295742c8bce7996c9061","observation_id":"9a255a77-acb0-4288-bba8-2ddfc9be5f11","resolution":{"observed_at":"2026-08-08T17:10:39.711429Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-08-07T15:09:11.912850Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.16363","last_updated":"2025-05-22T08:16:48Z","snapshot_observed_at":"2026-08-07T15:00:34.424850Z","submitted_at":"2025-05-22T08:16:48Z","title":"AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T15:09:11.912850Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2505.16363"},"observation_digest":"sha256:d95f2b07e0feeb31bbcf642cdee50011b42a3f2efa677818f928f5b25010e624","observation_id":"6b189118-284b-4bc1-9418-c7b4886f4fdf","resolution":{"observed_at":"2026-08-07T15:09:11.912850Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-08-07T14:07:22.407437Z","title":"Glm: General language model pretrain- ing with autoregressive blank infilling","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.19937","last_updated":"2026-06-16T16:14:58Z","snapshot_observed_at":"2026-08-08T15:42:12.589463Z","submitted_at":"2025-05-26T13:02:44Z","title":"ALAS: An Automatic Latent Alignment Score for Audio Language Models","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T14:07:22.407437Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2505.19937"},"observation_digest":"sha256:1d73fe6fc0e4dff3ffc399b56214ae1afdcaef3a28ecefc02e41f0018a6d719c","observation_id":"f34a3591-95b3-4b10-9b4e-d2b3dbe235ee","resolution":{"observed_at":"2026-08-07T14:07:22.407437Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-08-07T12:59:23.709968Z","title":"Glm: General language model pretraining with autoregressive blank infilling.arXiv preprint arXiv:2103.10360, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.23018","last_updated":"2025-06-25T09:38:19Z","snapshot_observed_at":"2026-08-07T12:53:06.465103Z","submitted_at":"2025-05-29T02:56:08Z","title":"EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T12:59:23.709968Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2505.23018"},"observation_digest":"sha256:c9699308b65aae8ac40c3fe3370b23f9a0075cf387797d144d1c4fe6deaf66f4","observation_id":"86ec338a-3e4d-4714-87af-ef129b6f4daa","resolution":{"observed_at":"2026-08-07T12:59:23.709968Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-08-07T05:38:36.638733Z","title":"J., 2021.Pre-trained Models for Natural Language Processing: A Survey","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.08060","last_updated":"2025-06-09T08:37:19Z","snapshot_observed_at":"2026-08-08T00:49:20.316988Z","submitted_at":"2025-06-09T08:37:19Z","title":"Eliciting Fine-Tuned Transformer Capabilities via Inference-Time Techniques","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:36.638733Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2506.08060"},"observation_digest":"sha256:7c1156816bde6ee9b0c284b8294822e97cdd12d0c6d25c329e2a39f8f505bd70","observation_id":"1b50d77b-0a30-4f5b-845d-795734fca848","resolution":{"observed_at":"2026-08-07T05:38:36.638733Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-08-07T00:54:50.590165Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.12496","last_updated":"2025-08-07T16:23:33Z","snapshot_observed_at":"2026-08-07T00:45:30.139296Z","submitted_at":"2025-06-14T13:17:27Z","title":"Improving Factuality for Dialogue Response Generation via Graph-Based Knowledge Augmentation","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T00:54:50.590165Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2506.12496"},"observation_digest":"sha256:832918c4cbecb9b106d1d25c0e2d038f69ed1fcd405366859331e190bb0b8e69","observation_id":"8fc69803-8954-4524-9d1b-ecd2ffca4258","resolution":{"observed_at":"2026-08-07T00:54:50.590165Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-08-07T00:40:51.181853Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.13055","last_updated":"2025-06-16T02:52:44Z","snapshot_observed_at":"2026-08-07T21:24:42.876067Z","submitted_at":"2025-06-16T02:52:44Z","title":"CFBenchmark-MM: Chinese Financial Assistant Benchmark for Multimodal Large Language Model","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T00:40:51.181853Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2506.13055"},"observation_digest":"sha256:5ba31bfcf3312074f56b3e9c1798b474852b4707e5c40278b27c71221c7da8f2","observation_id":"c21edc4c-12b9-433d-8d8a-ee778f72eee5","resolution":{"observed_at":"2026-08-07T00:40:51.181853Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-08-06T21:49:36.349203Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.23431","last_updated":"2025-07-01T04:16:14Z","snapshot_observed_at":"2026-08-08T09:33:45.637036Z","submitted_at":"2025-06-29T23:37:24Z","title":"Pipelined Decoder for Efficient Context-Aware Text Generation","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-06T21:49:36.349203Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2506.23431"},"observation_digest":"sha256:30b8d29d6f0a665d286de3760be78e0b2ec526daeef3a8b6b83899131b500e1a","observation_id":"fbd8aa2e-d2d0-4d0f-a92e-f78e75d01d89","resolution":{"observed_at":"2026-08-06T21:49:36.349203Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-08-06T19:04:59.150177Z","title":"Glm: General language model pretrain- ing with autoregressive blank infilling.arXiv preprint arXiv:2103.10360,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.06539","last_updated":"2025-07-10T02:51:21Z","snapshot_observed_at":"2026-08-06T18:58:27.009693Z","submitted_at":"2025-07-09T04:46:31Z","title":"Large Language Model for Extracting Complex Contract Information in Industrial Scenes","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-06T19:04:59.150177Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2507.06539"},"observation_digest":"sha256:e3290796103583ad66ea29154aa1b0601b8edf0d14ba7e63dc458ff8925f3d4e","observation_id":"a330deb1-288b-476f-afc5-a2056ae8a6b8","resolution":{"observed_at":"2026-08-06T19:04:59.150177Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-08-05T20:05:55.270317Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.11269","last_updated":"2025-08-15T07:08:46Z","snapshot_observed_at":"2026-08-06T23:15:22.967250Z","submitted_at":"2025-08-15T07:08:46Z","title":"Inference performance evaluation for LLMs on edge devices with a novel benchmarking framework and metric","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T20:05:55.270317Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2508.11269"},"observation_digest":"sha256:68c011294188aa389f436ee74affe5cfd2446be81dbdd6d5c6d885d2b08c5f16","observation_id":"8fef53c5-e5d5-4b98-9de7-582cb720414b","resolution":{"observed_at":"2026-08-05T20:05:55.270317Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-08-05T16:17:37.592270Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.18772","last_updated":"2025-08-26T07:55:46Z","snapshot_observed_at":"2026-08-07T08:24:33.804357Z","submitted_at":"2025-08-26T07:55:46Z","title":"Beyond the Textual: Generating Coherent Visual Options for MCQs","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-05T16:17:37.592270Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2508.18772"},"observation_digest":"sha256:ed8959fb3aaad74ca0c11c56c9b4c7911fcb16ee6b5a453a5addb8b9507ec3cd","observation_id":"9f66747f-fd68-420f-9172-2e11e84797c6","resolution":{"observed_at":"2026-08-05T16:17:37.592270Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-08-04T19:32:46.835896Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09226","last_updated":"2025-09-11T07:59:30Z","snapshot_observed_at":"2026-08-06T12:31:34.485569Z","submitted_at":"2025-09-11T07:59:30Z","title":"Constructing a Question-Answering Simulator through the Distillation of LLMs","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T19:32:46.835896Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2509.09226"},"observation_digest":"sha256:d9e17ed8f055de4b6e3714408f602704d799956dfdf0de1f687ef83bc7c7d0a6","observation_id":"c2ee59ea-f2ab-4fd4-87ac-6b3b38bb4ad7","resolution":{"observed_at":"2026-08-04T19:32:46.835896Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":"2103.10360","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2103.10360 , year=","venue":null,"work_id":"46d7bb97-b94f-4fe6-8291-6d532f004dfa","year":2021},"citing_paper":{"arxiv_id":"2604.08299","last_updated":"2026-04-19T12:06:32Z","snapshot_observed_at":"2026-07-06T22:57:26.678728Z","submitted_at":"2026-04-09T14:32:07Z","title":"SeLaR: Selective Latent Reasoning in Large Language Models","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-05-10T18:27:36.132030Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2604.08299"},"observation_digest":"sha256:de2cb17ca3464cd3b7dbc9a90fd8f9d1d7ca9e2f63c98fa26f351f820f1b5654","observation_id":"56f075c2-df61-4176-9343-c614ea78d39c","resolution":{"observed_at":"2026-05-11T00:35:49.846266Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":"2103.10360","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2103.10360 , year=","venue":null,"work_id":"46d7bb97-b94f-4fe6-8291-6d532f004dfa","year":2021},"citing_paper":{"arxiv_id":"2604.14825","last_updated":"2026-04-16T09:55:23Z","snapshot_observed_at":"2026-08-03T15:09:44.220229Z","submitted_at":"2026-04-16T09:55:23Z","title":"Nautilus: An Auto-Scheduling Tensor Compiler for Efficient Tiled GPU Kernels","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-10T10:21:05.219519Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2604.14825"},"observation_digest":"sha256:1445eb0797b3f2024a28d77a51584bccf7c57fadcd5f708144e47241b29d9ea5","observation_id":"2038cddc-4cba-4caa-9889-b900bd0f879d","resolution":{"observed_at":"2026-05-10T10:24:21.488491Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":"2103.10360","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2103.10360 , year=","venue":null,"work_id":"46d7bb97-b94f-4fe6-8291-6d532f004dfa","year":2021},"citing_paper":{"arxiv_id":"2605.05974","last_updated":"2026-05-19T06:13:53Z","snapshot_observed_at":"2026-07-06T23:18:31.432422Z","submitted_at":"2026-05-07T10:19:06Z","title":"PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-05-08T09:24:27.977204Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2605.05974"},"observation_digest":"sha256:ec7ca313ae7bf30e264202db6956dc18cf8378e47dc30de05c2acb8b3808ae13","observation_id":"42d58bbf-0468-4b17-b003-a1c1bf66fe07","resolution":{"observed_at":"2026-05-11T20:21:11.194784Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":"2103.10360","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2103.10360 , year=","venue":null,"work_id":"46d7bb97-b94f-4fe6-8291-6d532f004dfa","year":2021},"citing_paper":{"arxiv_id":"2605.05974","last_updated":"2026-05-19T06:13:53Z","snapshot_observed_at":"2026-07-06T23:18:31.432422Z","submitted_at":"2026-05-07T10:19:06Z","title":"PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-05-20T23:32:48.878074Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2605.05974"},"observation_digest":"sha256:b1b5153baac4bce698f49315234f92b22d2b348c2aba7afa69eb2df49b1fdab9","observation_id":"9f4f2771-024b-4a3b-a192-6187edb0aef7","resolution":{"observed_at":"2026-05-20T23:33:50.542434Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":"2103.10360","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2103.10360 , year=","venue":null,"work_id":"46d7bb97-b94f-4fe6-8291-6d532f004dfa","year":2021},"citing_paper":{"arxiv_id":"2605.08840","last_updated":"2026-05-09T09:49:32Z","snapshot_observed_at":"2026-07-06T23:21:02.177557Z","submitted_at":"2026-05-09T09:49:32Z","title":"ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-12T02:52:33.076123Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2605.08840"},"observation_digest":"sha256:66d6d842868521658c40ce614b506a78dab071935d245d19ae914706ded1b9cc","observation_id":"1c95eb36-10bc-49d6-aadd-7115f0d7f024","resolution":{"observed_at":"2026-05-12T07:26:30.221150Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":"2103.10360","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2103.10360 , year=","venue":null,"work_id":"46d7bb97-b94f-4fe6-8291-6d532f004dfa","year":2021},"citing_paper":{"arxiv_id":"2605.14055","last_updated":"2026-05-13T19:25:56Z","snapshot_observed_at":"2026-08-01T07:49:53.576982Z","submitted_at":"2026-05-13T19:25:56Z","title":"PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts","version":1},"reference_index":95,"source":"arxiv_source","source_observed_at":"2026-05-15T05:25:38.967645Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2605.14055"},"observation_digest":"sha256:036bb9032cf801e2443d74f9587c5105acf3865142bd2d2eff5a72fc355175e5","observation_id":"4787068b-9bbb-47b8-ab4e-e7ae9e99e714","resolution":{"observed_at":"2026-05-15T05:29:48.220645Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.10360","snapshot_observed_at":"2026-08-01T02:14:09.645560Z","title":"arXiv preprint arXiv:2103.10360 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.25527","last_updated":"2026-07-28T10:12:06Z","snapshot_observed_at":"2026-08-07T06:54:02.373541Z","submitted_at":"2026-07-28T10:12:06Z","title":"Argus-Unified: Towards A Compact and Economical Unified Model for Image Understanding and Generation","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-01T02:14:09.645560Z"},"links":{"cited_paper":"/paper/2103.10360","citing_paper":"/paper/2607.25527"},"observation_digest":"sha256:7d37efcd0ca433124c7d4f0e6c91497c642fc51d45599061924d7461d3725f01","observation_id":"917eec41-5b12-456a-a0d7-a0a1828968f7","resolution":{"observed_at":"2026-08-01T02:14:09.645560Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2103.10360/citation-record","integrity":"/paper/2103.10360/integrity","json":"/paper/2103.10360/citation-record.json","paper":"/paper/2103.10360"},"outbound":[],"paper":{"arxiv_id":"2103.10360","last_updated":"2022-03-17T11:49:55Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T10:51:12.871009Z","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 29 inbound Pith citation observations for arXiv:2103.10360."}