{"as_of":"2026-08-14T01:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4e062963411e1dde7eeefb26fae1c33ce2095066914df6411a37ffc29a0c233d","coverage":[{"denominator":20,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T19:58:47.951473Z","state":"measured"},{"denominator":20,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":20,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2411.10156/citation-record","integrity":"/paper/2411.10156/integrity","json":"/paper/2411.10156/citation-record.json","paper":"/paper/2411.10156"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.02524","last_updated":"2024-02-01T22:06:51Z","snapshot_observed_at":"2026-08-13T04:48:46.975482Z","submitted_at":"2024-01-04T20:23:51Z","title":"Comprehensive Exploration of Synthetic Data Generation: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.02524","snapshot_observed_at":"2026-08-12T19:58:47.585475Z","title":"& Foster, I","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.585475Z"},"links":{"cited_paper":"/paper/2401.02524","citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:b99bac7559a093e0a6bef7b9b6926f6731e9e9641c61fd1c652980aab34a0e23","observation_id":"a38cdf63-c465-4abf-baf2-d33fae786eaf","resolution":{"observed_at":"2026-08-12T19:58:47.585475Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.08005","last_updated":"2024-02-12T19:10:13Z","snapshot_observed_at":"2026-08-13T20:26:48.308905Z","submitted_at":"2024-02-12T19:10:13Z","title":"Refined Direct Preference Optimization with Synthetic Data for Behavioral Alignment of LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.08005","snapshot_observed_at":"2026-08-12T19:58:47.666358Z","title":"Refined Direct Preference Optimization with Synthetic Data for Behavioral Alignment of LLMs","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.666358Z"},"links":{"cited_paper":"/paper/2402.08005","citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:ba354033be8c2895efaf7a8afc3320cf1b05ae53cf93a8ce8efe848b7ecbc975","observation_id":"fca1a825-d862-4d0d-8c91-9ec93279f49b","resolution":{"observed_at":"2026-08-12T19:58:47.666358Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.14202","last_updated":"2025-06-04T19:43:17Z","snapshot_observed_at":"2026-08-12T22:40:23.871260Z","submitted_at":"2024-09-21T17:19:29Z","title":"Mining Causality: AI-Assisted Search for Instrumental Variables","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.14202","snapshot_observed_at":"2026-08-12T19:58:47.673280Z","title":"Mining causality: Ai-assisted search for instrumental variables","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.673280Z"},"links":{"cited_paper":"/paper/2409.14202","citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:90b6e99b927ebab56fac2acd8013ee8637f0f9408e47a29b2555e266e2229227","observation_id":"31d7975b-81a9-44e1-8a28-cb607701a29e","resolution":{"observed_at":"2026-08-12T19:58:47.673280Z","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":"2026-08-12T19:58:48.430588Z","title":null,"venue":null,"work_id":"058e60bc-69eb-4d21-bffb-f94f3444af0d","year":2024},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.679341Z"},"links":{"citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:a13120d98687564a66860c8cc8edc394fda1244c82d10264e64cedd77e0ef4b4","observation_id":"9dce9a69-d300-4c35-a3e4-747d61ecbd77","resolution":{"observed_at":"2026-08-12T19:58:48.436219Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:58:48.410432Z","title":"The impact of positional encoding on length generalization in transformers","venue":null,"work_id":"97c8778c-2c90-4de6-a5a3-f322935f97cf","year":2024},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.684943Z"},"links":{"citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:c3775c30ae640f03581a8930d04e1673f8e2ce7cccae991c6453ce22a8bf004c","observation_id":"9f6bfd75-1e16-402c-a9d1-b262aa0a2d6c","resolution":{"observed_at":"2026-08-12T19:58:48.417906Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.07849","last_updated":"2023-10-13T01:31:59Z","snapshot_observed_at":"2026-08-13T05:51:49.087369Z","submitted_at":"2023-10-11T19:51:13Z","title":"Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.07849","snapshot_observed_at":"2026-08-12T19:58:47.691448Z","title":"Illustrating reinforcement learning from human feedback (rlhf)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.691448Z"},"links":{"cited_paper":"/paper/2310.07849","citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:51393ef6b24a76caa0529e2b8cd412c19de2fa9fb10ff726e2b495085082b527","observation_id":"fc768367-397d-4a9b-9cdf-0ebe7876cc3d","resolution":{"observed_at":"2026-08-12T19:58:47.691448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.18346","last_updated":"2024-06-26T13:42:13Z","snapshot_observed_at":"2026-08-12T23:34:28.580464Z","submitted_at":"2024-06-26T13:42:13Z","title":"AI Alignment through Reinforcement Learning from Human Feedback? Contradictions and Limitations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.18346","snapshot_observed_at":"2026-08-12T19:58:47.697708Z","title":"D., Methnani, L., Krause, L., Ericson, P., de Troya, Í","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.697708Z"},"links":{"cited_paper":"/paper/2406.18346","citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:71e67d7c6f095a663ef327e98a5f7de647e1a13ee54a54c7a3dfeabc036d28f5","observation_id":"b81e5a9e-9514-4a86-899f-947146bf6261","resolution":{"observed_at":"2026-08-12T19:58:47.697708Z","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":"2026-08-12T19:58:48.391161Z","title":"Introducing ChatGPT","venue":null,"work_id":"ac3bff73-6747-4017-a6ed-7b3d87f53a5d","year":2022},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.734950Z"},"links":{"citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:0a9e16501f0c378dbacf1e71dedc2f0c6ca15cc2482fc233c602b8ee9eb563d6","observation_id":"703ebaad-58e0-4543-9990-aa7c74b71908","resolution":{"observed_at":"2026-08-12T19:58:48.398274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.12696","last_updated":"2023-10-09T19:20:32Z","snapshot_observed_at":"2026-08-13T11:37:38.861622Z","submitted_at":"2023-05-22T04:07:54Z","title":"Learning Interpretable Style Embeddings via Prompting LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.12696","snapshot_observed_at":"2026-08-12T19:58:47.825691Z","title":"Learning interpretable style embeddings via promptingllms","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.825691Z"},"links":{"cited_paper":"/paper/2305.12696","citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:138ce969b9801dcbc07b15e012d82d6f863de498db4b90210ba99ead46d83e21","observation_id":"ec31b57c-1eb7-4d58-9447-a36bda731daf","resolution":{"observed_at":"2026-08-12T19:58:47.825691Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.01826","last_updated":"2023-10-21T08:33:44Z","snapshot_observed_at":"2026-08-13T10:20:32.173377Z","submitted_at":"2023-09-04T21:30:21Z","title":"One Wide Feedforward is All You Need","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.01826","snapshot_observed_at":"2026-08-12T19:58:47.893812Z","title":"P., Lopes, A","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.893812Z"},"links":{"cited_paper":"/paper/2309.01826","citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:da369ede6f4669336cf380a8ec848db4f87e8c4eafdbfe0a20e7d07526caabf1","observation_id":"dde9ec76-2cda-47f6-9770-032e3eb00795","resolution":{"observed_at":"2026-08-12T19:58:47.893812Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.09410","last_updated":"2025-06-24T19:59:56Z","snapshot_observed_at":"2026-08-13T05:24:21.815980Z","submitted_at":"2023-11-15T22:18:33Z","title":"When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.09410","snapshot_observed_at":"2026-08-12T19:58:47.900343Z","title":"When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.900343Z"},"links":{"cited_paper":"/paper/2311.09410","citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:8f9f986bd170e960a7d55be3befcd15724f262c0608c6f5ec54ab74c889c9953","observation_id":"c2339540-5365-4d65-a87a-20e43ef3ba44","resolution":{"observed_at":"2026-08-12T19:58:47.900343Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.15904","last_updated":"2024-07-22T14:20:53Z","snapshot_observed_at":"2026-08-12T23:17:16.741550Z","submitted_at":"2024-07-22T14:20:53Z","title":"Comprehensive Study on Performance Evaluation and Optimization of Model Compression: Bridging Traditional Deep Learning and Large Language Models","version":1},"cited_work":{"arxiv_id":"2407.15904","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.15904","snapshot_observed_at":"2026-08-12T19:58:48.160336Z","title":"Comprehensive Study on Performance Evaluation and Optimization of Model Compression: Bridging Traditional Deep Learning and Large Language Models","venue":"cs.LG","work_id":"464ac21a-dcdd-4e61-9c3b-afb9b0d53bec","year":2024},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.906264Z"},"links":{"cited_paper":"/paper/2407.15904","citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:04ec4d651aeb7aab638214c38fd6c2ad8e6d348054f29c90973787e99a4c72e2","observation_id":"27fdbac8-7e17-4fd9-b741-239eb7ccd13b","resolution":{"observed_at":"2026-08-12T19:58:48.169542Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13548","last_updated":"2025-05-10T07:10:46Z","snapshot_observed_at":"2026-08-13T05:57:11.276534Z","submitted_at":"2023-10-20T14:46:48Z","title":"Towards Understanding Sycophancy in Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.13548","snapshot_observed_at":"2026-08-12T19:58:47.911786Z","title":"arXiv preprint arXiv:2310.13548,2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.911786Z"},"links":{"cited_paper":"/paper/2310.13548","citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:444c00c6a6921e2b7e4cca935e5df855b9355459921ec454d83961682320bfc4","observation_id":"12148642-819e-4830-9d56-d5f3e2e6fa12","resolution":{"observed_at":"2026-08-12T19:58:47.911786Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.16008","last_updated":"2025-03-14T20:08:08Z","snapshot_observed_at":"2026-08-12T23:16:58.449094Z","submitted_at":"2024-07-22T19:21:55Z","title":"Boosting Reward Model with Preference-Conditional Multi-Aspect Synthetic Data Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.16008","snapshot_observed_at":"2026-08-12T19:58:47.917112Z","title":"and Bendersky, M","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.917112Z"},"links":{"cited_paper":"/paper/2407.16008","citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:f75a83d74b44053c1a37ae717588a2be561a63f1b1140418a6339b2e1c2228b6","observation_id":"15b44040-fb43-4ded-9b4e-719b1ad88df1","resolution":{"observed_at":"2026-08-12T19:58:47.917112Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.06461","last_updated":"2023-02-13T15:41:20Z","snapshot_observed_at":"2026-08-13T12:45:23.702887Z","submitted_at":"2023-02-13T15:41:20Z","title":"A Study on ReLU and Softmax in Transformer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.06461","snapshot_observed_at":"2026-08-12T19:58:47.923221Z","title":"A study on relu and softmax in transformer","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.923221Z"},"links":{"cited_paper":"/paper/2302.06461","citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:cec9ef667795b970e2d37fbde6316a0673a5db971782823596ee8ee62ef1b36c","observation_id":"af48f8ee-5148-48c4-9ebb-66334a4af48b","resolution":{"observed_at":"2026-08-12T19:58:47.923221Z","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":"2026-08-12T19:58:48.369740Z","title":"Multimodal query suggestion with multi-agent reinforcement learning from human feedback","venue":null,"work_id":"dab59407-edb0-4c5f-bd7b-7effe7faeec6","year":2024},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.928849Z"},"links":{"citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:3747f1ba20aa6613612ce4786297d4a4984e61a7ce2a3bd5a16e1e513096f90e","observation_id":"7b3dca00-679a-457c-80b1-3e4a38997490","resolution":{"observed_at":"2026-08-12T19:58:48.375618Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03958","last_updated":"2024-02-15T01:03:13Z","snapshot_observed_at":"2026-08-13T15:17:00.535157Z","submitted_at":"2023-08-07T23:48:36Z","title":"Simple synthetic data reduces sycophancy in large language models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03958","snapshot_observed_at":"2026-08-12T19:58:47.934173Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.934173Z"},"links":{"cited_paper":"/paper/2308.03958","citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:a74ed7822a8b133d120c0cd0b4e9dc98033199f0b479d72828ee9a2d7d9e888a","observation_id":"5a4b64d8-46eb-45c5-9634-7cd4eb8ae2d0","resolution":{"observed_at":"2026-08-12T19:58:47.934173Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.05638","last_updated":"2021-02-10T18:53:11Z","snapshot_observed_at":"2026-08-13T20:16:43.867433Z","submitted_at":"2021-02-10T18:53:11Z","title":"Generating Synthetic Text Data to Evaluate Causal Inference Methods","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.05638","snapshot_observed_at":"2026-08-12T19:58:47.940457Z","title":"Generating synthetic text data to evaluate causal inference methods","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.940457Z"},"links":{"cited_paper":"/paper/2102.05638","citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:28fc4df79a03622c742177b4d75245bcade2300ffdd7d65685281767fc013fc4","observation_id":"8dc49710-fb4e-4022-96ff-73a56496b5ef","resolution":{"observed_at":"2026-08-12T19:58:47.940457Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.10020","last_updated":"2025-03-28T00:06:51Z","snapshot_observed_at":"2026-08-07T08:02:34.857823Z","submitted_at":"2024-01-18T14:43:47Z","title":"Self-Rewarding Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.10020","snapshot_observed_at":"2026-08-12T19:58:47.945748Z","title":"Y., Cho, K., Sukhbaatar, S., Xu, J., and Weston, J","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.945748Z"},"links":{"cited_paper":"/paper/2401.10020","citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:b7180437d70b79ea83c3320b90283cca0739fb2dba309a0b90819c7d79732dd3","observation_id":"b99462d8-8615-48ae-b66a-b9996ef0f6fc","resolution":{"observed_at":"2026-08-12T19:58:47.945748Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.01068","last_updated":"2022-06-21T17:04:40Z","snapshot_observed_at":"2026-08-06T03:13:37.403059Z","submitted_at":"2022-05-02T17:49:50Z","title":"OPT: Open Pre-trained Transformer Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.01068","snapshot_observed_at":"2026-08-12T19:58:47.951473Z","title":"and Zettlemoyer, L","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","version":5},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T19:58:47.951473Z"},"links":{"cited_paper":"/paper/2205.01068","citing_paper":"/paper/2411.10156"},"observation_digest":"sha256:7d16cef155a1a65c29f9be0b78ce260be4cb194638cc8fcf072f23335af778df","observation_id":"5adc2db6-9f1b-497f-81cf-fa92d136831d","resolution":{"observed_at":"2026-08-12T19:58:47.951473Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.10156","last_updated":"2025-03-20T13:29:49Z","latest_version":5,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-13T21:13:55.744822Z","submitted_at":"2024-11-15T12:59:46Z","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention"},"reference_resolution":{"displayed":20,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":16,"verified_exact":0,"verified_fuzzy":3},"total_outbound_references":20},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2411.10156."}