{"as_of":"2026-08-07T08:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1cec3d441830e76bfd8451aa26a9b03c91263389c708e6ddb1195c51ea36a1a1","coverage":[{"denominator":15,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":15,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T11:16:05.365085Z","state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":16,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":16,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T01:29:05.737247Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-01T11:45:46.931017Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"cited_work":{"arxiv_id":"2507.22879","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.22879","snapshot_observed_at":"2026-07-01T11:45:46.931017Z","title":"Recgpt technical report","venue":null,"work_id":"c6b37433-a4db-4a7c-bf81-505a66bc21a2","year":2025},"citing_paper":{"arxiv_id":"2602.10445","last_updated":"2026-05-21T03:19:32Z","snapshot_observed_at":"2026-07-06T22:45:25.047172Z","submitted_at":"2026-02-11T02:38:26Z","title":"End-to-End Semantic ID Generation for Generative Advertisement Recommendation","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-22T11:51:53.936922Z"},"links":{"cited_paper":"/paper/2507.22879","citing_paper":"/paper/2602.10445"},"observation_digest":"sha256:1aa4e16866665a0f8790e5ff1f40ac5debe0d6af551b3c63aafebf9d74197b4e","observation_id":"dbe74e58-6933-45c8-a279-8bafc97037fb","resolution":{"observed_at":"2026-05-22T11:54:51.369089Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"cited_work":{"arxiv_id":"2507.22879","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.22879","snapshot_observed_at":"2026-07-01T11:45:46.931017Z","title":"Recgpt technical report","venue":null,"work_id":"c6b37433-a4db-4a7c-bf81-505a66bc21a2","year":2025},"citing_paper":{"arxiv_id":"2604.20861","last_updated":"2026-06-01T16:16:21Z","snapshot_observed_at":"2026-08-03T01:24:12.519049Z","submitted_at":"2026-03-03T13:36:22Z","title":"Deep Interest Mining for Intent-Enriched Semantic IDs in Multimodal Generative Recommendation","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-15T17:01:07.245161Z"},"links":{"cited_paper":"/paper/2507.22879","citing_paper":"/paper/2604.20861"},"observation_digest":"sha256:467292036ba0f6c485e370fbc88a8c19e6c2ffb8ce4da8381cbdc91601f369b1","observation_id":"a539da48-e0ed-4135-9830-3dff778ca73d","resolution":{"observed_at":"2026-05-15T17:01:18.545449Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.22879","snapshot_observed_at":"2026-08-02T19:15:42.538475Z","title":"Recgpt technical report,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.20861","last_updated":"2026-06-01T16:16:21Z","snapshot_observed_at":"2026-08-03T01:24:12.519049Z","submitted_at":"2026-03-03T13:36:22Z","title":"Deep Interest Mining for Intent-Enriched Semantic IDs in Multimodal Generative Recommendation","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T19:15:42.538475Z"},"links":{"cited_paper":"/paper/2507.22879","citing_paper":"/paper/2604.20861"},"observation_digest":"sha256:66a090411efd252e1028fe662cee5f5edef5811fae5c402827ca5b43b3e8ea99","observation_id":"cf07e376-531f-4c49-abf0-784ccb87d738","resolution":{"observed_at":"2026-08-02T19:15:42.538475Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"cited_work":{"arxiv_id":"2507.22879","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.22879","snapshot_observed_at":"2026-07-01T11:45:46.931017Z","title":"Recgpt technical report","venue":null,"work_id":"c6b37433-a4db-4a7c-bf81-505a66bc21a2","year":2025},"citing_paper":{"arxiv_id":"2605.04726","last_updated":"2026-05-06T10:20:44Z","snapshot_observed_at":"2026-08-05T04:29:09.220775Z","submitted_at":"2026-05-06T10:20:44Z","title":"RecGPT-Mobile: On-Device Large Language Models for User Intent Understanding in Taobao Feed Recommendation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-08T16:28:47.356432Z"},"links":{"cited_paper":"/paper/2507.22879","citing_paper":"/paper/2605.04726"},"observation_digest":"sha256:2b093a6f2149d2f13bfc65f36cfd30337f0e73fecc03fcf837b9b049d7af84f9","observation_id":"1761e97c-cfcd-4b4d-b7ff-cc560670e9bd","resolution":{"observed_at":"2026-05-11T18:11:06.350122Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"cited_work":{"arxiv_id":"2507.22879","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.22879","snapshot_observed_at":"2026-07-01T11:45:46.931017Z","title":"Recgpt technical report","venue":null,"work_id":"c6b37433-a4db-4a7c-bf81-505a66bc21a2","year":2025},"citing_paper":{"arxiv_id":"2605.05249","last_updated":"2026-06-02T17:05:24Z","snapshot_observed_at":"2026-07-06T23:17:52.987860Z","submitted_at":"2026-05-05T11:42:14Z","title":"TriAlignGR: Triangular Multitask Alignment with Multimodal Deep Interest Mining for Generative Recommendation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-08T18:46:08.393219Z"},"links":{"cited_paper":"/paper/2507.22879","citing_paper":"/paper/2605.05249"},"observation_digest":"sha256:9b162b725d946ba35f477038aa18a2d62a1c43ac9397d829ce9f427667d44024","observation_id":"e6cd1214-0fe8-4794-8ce5-b8f8a7c16e8c","resolution":{"observed_at":"2026-05-09T06:10:43.279029Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"cited_work":{"arxiv_id":"2507.22879","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.22879","snapshot_observed_at":"2026-07-01T11:45:46.931017Z","title":"Recgpt technical report","venue":null,"work_id":"c6b37433-a4db-4a7c-bf81-505a66bc21a2","year":2025},"citing_paper":{"arxiv_id":"2605.05249","last_updated":"2026-06-02T17:05:24Z","snapshot_observed_at":"2026-07-06T23:17:52.987860Z","submitted_at":"2026-05-05T11:42:14Z","title":"TriAlignGR: Triangular Multitask Alignment with Multimodal Deep Interest Mining for Generative Recommendation","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-20T23:50:47.510019Z"},"links":{"cited_paper":"/paper/2507.22879","citing_paper":"/paper/2605.05249"},"observation_digest":"sha256:13274e645061105f002797aa9a573feede28bb0d1995561170ba7f532688b8f1","observation_id":"c3dab975-0f7c-4b71-994e-c28666930dce","resolution":{"observed_at":"2026-05-20T23:53:51.776646Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"cited_work":{"arxiv_id":"2507.22879","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.22879","snapshot_observed_at":"2026-07-01T11:45:46.931017Z","title":"Recgpt technical report","venue":null,"work_id":"c6b37433-a4db-4a7c-bf81-505a66bc21a2","year":2025},"citing_paper":{"arxiv_id":"2605.05249","last_updated":"2026-06-02T17:05:24Z","snapshot_observed_at":"2026-07-06T23:17:52.987860Z","submitted_at":"2026-05-05T11:42:14Z","title":"TriAlignGR: Triangular Multitask Alignment with Multimodal Deep Interest Mining for Generative Recommendation","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-01T00:12:24.019383Z"},"links":{"cited_paper":"/paper/2507.22879","citing_paper":"/paper/2605.05249"},"observation_digest":"sha256:63180c7c7caf28f476a23ac60178f688254adf0c183c8a74d10d43316e71d5cf","observation_id":"5e5f76cb-45d9-4905-a91b-c76f7e0e2c20","resolution":{"observed_at":"2026-07-01T00:15:09.176885Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"cited_work":{"arxiv_id":"2507.22879","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.22879","snapshot_observed_at":"2026-07-01T11:45:46.931017Z","title":"Recgpt technical report","venue":null,"work_id":"c6b37433-a4db-4a7c-bf81-505a66bc21a2","year":2025},"citing_paper":{"arxiv_id":"2605.05803","last_updated":"2026-07-29T07:00:12Z","snapshot_observed_at":"2026-08-02T14:47:53.212183Z","submitted_at":"2026-05-07T07:41:19Z","title":"UniVA: Unified Value Alignment for Generative Recommendation in Online Advertising at Tencent","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-08T06:06:49.422159Z"},"links":{"cited_paper":"/paper/2507.22879","citing_paper":"/paper/2605.05803"},"observation_digest":"sha256:f26c2286af9b015b3502e87a95e079f0ca83dc550ee5bf1ae49b7c66889293c4","observation_id":"c2eaf12f-2a03-490b-b76b-633412618814","resolution":{"observed_at":"2026-05-11T21:16:26.110422Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.22879","snapshot_observed_at":"2026-08-02T14:47:55.623805Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.05803","last_updated":"2026-07-29T07:00:12Z","snapshot_observed_at":"2026-08-02T14:47:53.212183Z","submitted_at":"2026-05-07T07:41:19Z","title":"UniVA: Unified Value Alignment for Generative Recommendation in Online Advertising at Tencent","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T14:47:55.623805Z"},"links":{"cited_paper":"/paper/2507.22879","citing_paper":"/paper/2605.05803"},"observation_digest":"sha256:68bb621552ed59cc5378fa2b31caa78e1277f7e063ed5d29954146bc9c41b8e9","observation_id":"6bfb5df0-0b2b-451d-b2e7-c3b76388936e","resolution":{"observed_at":"2026-08-02T14:47:55.623805Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"cited_work":{"arxiv_id":"2507.22879","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.22879","snapshot_observed_at":"2026-07-01T11:45:46.931017Z","title":"Recgpt technical report","venue":null,"work_id":"c6b37433-a4db-4a7c-bf81-505a66bc21a2","year":2025},"citing_paper":{"arxiv_id":"2605.07129","last_updated":"2026-05-08T02:07:30Z","snapshot_observed_at":"2026-07-06T23:19:30.387067Z","submitted_at":"2026-05-08T02:07:30Z","title":"RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-11T02:36:35.809350Z"},"links":{"cited_paper":"/paper/2507.22879","citing_paper":"/paper/2605.07129"},"observation_digest":"sha256:5e4b9d248a0e0366c0f777a5bd91dc0d69b1e9af207bdf3b7aaf9ca259a080e4","observation_id":"c82946dd-0c45-4680-8c8f-d9ef25c2b6cb","resolution":{"observed_at":"2026-05-11T03:10:53.888963Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"cited_work":{"arxiv_id":"2507.22879","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.22879","snapshot_observed_at":"2026-07-01T11:45:46.931017Z","title":"Recgpt technical report","venue":null,"work_id":"c6b37433-a4db-4a7c-bf81-505a66bc21a2","year":2025},"citing_paper":{"arxiv_id":"2605.27856","last_updated":"2026-05-27T02:19:40Z","snapshot_observed_at":"2026-08-01T09:00:55.835956Z","submitted_at":"2026-05-27T02:19:40Z","title":"Fine-Tuned LLM as a Complementary Predictor Improving Ads System","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-29T10:27:47.543575Z"},"links":{"cited_paper":"/paper/2507.22879","citing_paper":"/paper/2605.27856"},"observation_digest":"sha256:d38e1667d58d2e9ed4980d7e2cc0a240d7f65f096ef78dac10326daef2cfbfa1","observation_id":"4643fff0-c3ea-488c-8d70-ea594e228ded","resolution":{"observed_at":"2026-06-29T13:23:28.734184Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"cited_work":{"arxiv_id":"2507.22879","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.22879","snapshot_observed_at":"2026-07-01T11:45:46.931017Z","title":"Recgpt technical report","venue":null,"work_id":"c6b37433-a4db-4a7c-bf81-505a66bc21a2","year":2025},"citing_paper":{"arxiv_id":"2606.31693","last_updated":"2026-07-15T17:49:58Z","snapshot_observed_at":"2026-08-02T09:18:56.324957Z","submitted_at":"2026-06-30T14:05:28Z","title":"ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-01T03:56:46.899707Z"},"links":{"cited_paper":"/paper/2507.22879","citing_paper":"/paper/2606.31693"},"observation_digest":"sha256:29cfed9ee68f99866066dd6ae6f3a3d93e99ca6b8d1859dabbad8af910b8a5d9","observation_id":"92d8e531-0873-40e9-88b3-9089d893fc36","resolution":{"observed_at":"2026-07-01T11:45:46.932546Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.22879","snapshot_observed_at":"2026-08-02T09:19:02.243348Z","title":"Recgpt technical report.arXiv preprint arXiv:2507.22879, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.31693","last_updated":"2026-07-15T17:49:58Z","snapshot_observed_at":"2026-08-02T09:18:56.324957Z","submitted_at":"2026-06-30T14:05:28Z","title":"ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T09:19:02.243348Z"},"links":{"cited_paper":"/paper/2507.22879","citing_paper":"/paper/2606.31693"},"observation_digest":"sha256:4afa6fea82286687f264efd01b6bbaa9e4b2a3a9bade9da720bf5e77aac20c07","observation_id":"d1accd12-3e32-422e-b37f-f4e2c9fb224e","resolution":{"observed_at":"2026-08-02T09:19:02.243348Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.22879","snapshot_observed_at":"2026-08-01T22:32:08.011090Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15730","last_updated":"2026-07-17T08:10:37Z","snapshot_observed_at":"2026-08-06T21:48:33.894820Z","submitted_at":"2026-07-17T08:10:37Z","title":"RECAP: Feedback-Driven Streaming Semantic User Profiles for Short-Video Recommendation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T22:32:08.011090Z"},"links":{"cited_paper":"/paper/2507.22879","citing_paper":"/paper/2607.15730"},"observation_digest":"sha256:1e5a24210a8ad88083fa871a06c35ac78b088480fad3e54507756bc3328be829","observation_id":"2e799aab-d462-43d2-aba5-8b96e08d57cf","resolution":{"observed_at":"2026-08-01T22:32:08.011090Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.22879","snapshot_observed_at":"2026-08-01T05:55:13.735634Z","title":"Recgpt technical report.arXiv preprint arXiv:2507.22879, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.22082","last_updated":"2026-07-24T08:31:25Z","snapshot_observed_at":"2026-08-05T13:21:08.429880Z","submitted_at":"2026-07-24T08:31:25Z","title":"When Language Models Meet NeuroGraphs: Exploring Enhanced Agentic LLM Framework Towards Brain Network Analysis","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-01T05:55:13.735634Z"},"links":{"cited_paper":"/paper/2507.22879","citing_paper":"/paper/2607.22082"},"observation_digest":"sha256:24c62b7ba44455328a6afc1e5eb7c13aa927a1f4964c992f2df13c8f75666241","observation_id":"24fbce6e-3601-4a53-9cc7-eb2115760de6","resolution":{"observed_at":"2026-08-01T05:55:13.735634Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.22879","snapshot_observed_at":"2026-08-03T01:29:05.737247Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28895","last_updated":"2026-07-30T23:27:14Z","snapshot_observed_at":"2026-08-05T23:12:05.550717Z","submitted_at":"2026-07-30T23:27:14Z","title":"LLM-Based Generative Retrieval for Snapchat Content Recommendation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T01:29:05.737247Z"},"links":{"cited_paper":"/paper/2507.22879","citing_paper":"/paper/2607.28895"},"observation_digest":"sha256:bcbb42facc2898694c0c2e7d3abfa961cee82f2961e1074c3db9b5909f01837b","observation_id":"9ff71233-cd3d-48fa-a7d4-ec5d605ed51a","resolution":{"observed_at":"2026-08-03T01:29:05.737247Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2507.22879/citation-record","integrity":"/paper/2507.22879/integrity","json":"/paper/2507.22879/citation-record.json","paper":"/paper/2507.22879"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.15594","last_updated":"2025-10-19T10:32:43Z","snapshot_observed_at":"2026-08-02T10:23:50.881300Z","submitted_at":"2024-11-23T16:03:35Z","title":"A Survey on LLM-as-a-Judge","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.15594","snapshot_observed_at":"2026-08-06T11:16:04.555321Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T11:16:04.555321Z"},"links":{"cited_paper":"/paper/2411.15594","citing_paper":"/paper/2507.22879"},"observation_digest":"sha256:0e9d551c59331e9759ea644849ac11998995bc25b87f274e096da8eca7cd479b","observation_id":"7834452f-5152-44db-831f-4a254758c9b2","resolution":{"observed_at":"2026-08-06T11:16:04.555321Z","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":"2026-07-06T02:11:23.670680Z","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":"2026-08-06T11:16:04.642557Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T11:16:04.642557Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2507.22879"},"observation_digest":"sha256:571cd1d8b44eb17d9823631cfea2480defe25f160733477abe1dd44309c8f9e1","observation_id":"c602718c-a7a9-44ff-8fd5-886685af0d26","resolution":{"observed_at":"2026-08-06T11:16:04.642557Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06452","last_updated":"2024-02-19T14:39:07Z","snapshot_observed_at":"2026-07-29T18:39:02.141391Z","submitted_at":"2023-10-10T09:25:44Z","title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06452","snapshot_observed_at":"2026-08-06T11:16:04.694338Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T11:16:04.694338Z"},"links":{"cited_paper":"/paper/2310.06452","citing_paper":"/paper/2507.22879"},"observation_digest":"sha256:7751ad948a2a59c5d30535b31c15a25efe8ebb2338dbe59a4a622c9b0437792d","observation_id":"1e80e756-06d2-4fc0-942c-2348326119eb","resolution":{"observed_at":"2026-08-06T11:16:04.694338Z","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":"2026-08-06T11:16:05.758442Z","title":null,"venue":null,"work_id":"d5e3d355-d472-4de6-a2c6-ae0151afea48","year":2021},"citing_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T11:16:04.761177Z"},"links":{"citing_paper":"/paper/2507.22879"},"observation_digest":"sha256:b557064d035e6a53b8aad014f5df0555339d7a1b75d59b4a9db29129f17d20ab","observation_id":"69389ba1-530c-41c8-ac76-cd77989d4bf5","resolution":{"observed_at":"2026-08-06T11:16:05.830479Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.11239","last_updated":"2024-10-02T11:07:14Z","snapshot_observed_at":"2026-08-03T08:44:22.056144Z","submitted_at":"2024-09-17T14:40:02Z","title":"LLM-as-a-Judge & Reward Model: What They Can and Cannot Do","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.11239","snapshot_observed_at":"2026-08-06T11:16:04.989126Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T11:16:04.989126Z"},"links":{"cited_paper":"/paper/2409.11239","citing_paper":"/paper/2507.22879"},"observation_digest":"sha256:2e66e6909372a85d60dc981c7fc99ae4cc7b0a4fc92101e5ea014cef182b2629","observation_id":"853d0677-3c55-4a9a-a6d4-051914be2033","resolution":{"observed_at":"2026-08-06T11:16:04.989126Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.06122","last_updated":"2025-06-06T14:33:56Z","snapshot_observed_at":"2026-08-07T05:57:51.651716Z","submitted_at":"2025-06-06T14:33:56Z","title":"Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.06122","snapshot_observed_at":"2026-08-06T11:16:05.122488Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T11:16:05.122488Z"},"links":{"cited_paper":"/paper/2506.06122","citing_paper":"/paper/2507.22879"},"observation_digest":"sha256:19350237c7996f35da785a231f8f62ccf4836e5bf28d92941fa469d84802ef8b","observation_id":"c1576350-4c9a-4f54-bcae-7fcecb8cd1d3","resolution":{"observed_at":"2026-08-06T11:16:05.122488Z","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":"2026-08-06T11:16:05.204069Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T11:16:05.204069Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2507.22879"},"observation_digest":"sha256:0515e1366ba46ff955772b0e7c6ef557003d4628eb4df74b079ed65532f97861","observation_id":"3937cac2-4572-4f58-ba6d-c01b67824eb3","resolution":{"observed_at":"2026-08-06T11:16:05.204069Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.15217","last_updated":"2023-09-11T17:25:24Z","snapshot_observed_at":"2026-08-03T19:11:09.671782Z","submitted_at":"2023-07-27T22:29:25Z","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.15217","snapshot_observed_at":"2026-08-06T11:16:04.349891Z","title":"Casper, X","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-06T11:16:04.349891Z"},"links":{"cited_paper":"/paper/2307.15217","citing_paper":"/paper/2507.22879"},"observation_digest":"sha256:452f93049cf19e824d5d73f6a76cc4e4d41079846425f0603ab4c39fd02414bd","observation_id":"e8b2e8f2-8d63-476c-91d6-e9393a28425a","resolution":{"observed_at":"2026-08-06T11:16:04.349891Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.18223","last_updated":"2026-03-18T05:34:39Z","snapshot_observed_at":"2026-08-06T23:27:24.356320Z","submitted_at":"2023-03-31T17:28:46Z","title":"A Survey of Large Language Models","version":19},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.18223","snapshot_observed_at":"2026-08-06T11:16:05.365085Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-06T11:16:05.365085Z"},"links":{"cited_paper":"/paper/2303.18223","citing_paper":"/paper/2507.22879"},"observation_digest":"sha256:8126dd981d7e8283f9affd4576cd69b35014719babf64f509a67a769313dc571","observation_id":"0cf8f86f-a7d1-4d19-a680-31338f82a45f","resolution":{"observed_at":"2026-08-06T11:16:05.365085Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.12509","last_updated":"2025-02-18T15:24:25Z","snapshot_observed_at":"2026-08-01T23:28:04.240794Z","submitted_at":"2024-12-17T03:37:31Z","title":"Can You Trust LLM Judgments? Reliability of LLM-as-a-Judge","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.12509","snapshot_observed_at":"2026-08-06T11:16:04.910071Z","title":"Schroeder and Z","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-06T11:16:04.910071Z"},"links":{"cited_paper":"/paper/2412.12509","citing_paper":"/paper/2507.22879"},"observation_digest":"sha256:0a836c0f23e2653bbd8b6418700f43eae274745fb03fd5aa8175bc51c0a9d694","observation_id":"89508a75-c5c4-4b99-a2e0-b798d2b9cdeb","resolution":{"observed_at":"2026-08-06T11:16:04.910071Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T11:16:04.841256Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-06T11:16:04.841256Z"},"links":{"citing_paper":"/paper/2507.22879"},"observation_digest":"sha256:90a764e03334e51d80dd78c4d8be968eb4e0445bb5bd0c76a0a8ac0e263ade9c","observation_id":"8f51d3cb-f1b7-47e0-bc17-ef198a5105ab","resolution":{"observed_at":"2026-08-06T11:16:04.841256Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.14147","last_updated":"2025-08-07T00:57:22Z","snapshot_observed_at":"2026-07-06T21:11:49.094540Z","submitted_at":"2025-04-19T02:46:10Z","title":"Explainable Recommendation with Simulated Human Feedback","version":2},"cited_work":{"arxiv_id":"2504.14147","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.14147","snapshot_observed_at":"2026-08-06T11:16:05.481909Z","title":"Explainable Recommendation with Simulated Human Feedback","venue":"cs.IR","work_id":"39731834-ec2d-4cb6-9ef9-974498c7f5c4","year":2025},"citing_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-06T11:16:05.069230Z"},"links":{"cited_paper":"/paper/2504.14147","citing_paper":"/paper/2507.22879"},"observation_digest":"sha256:dcf75c9e7b93edef0a76bea2b60f9f13fc524c882f05778e876e46baeefc4c8b","observation_id":"658553b0-eaa9-4430-b6b3-3e4263d9a86d","resolution":{"observed_at":"2026-08-06T11:16:05.546442Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.16712","last_updated":"2025-06-20T03:10:52Z","snapshot_observed_at":"2026-08-06T23:36:00.053152Z","submitted_at":"2025-06-20T03:10:52Z","title":"ReasonGRM: Enhancing Generative Reward Models through Large Reasoning Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.16712","snapshot_observed_at":"2026-08-06T11:16:04.410798Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-06T11:16:04.410798Z"},"links":{"cited_paper":"/paper/2506.16712","citing_paper":"/paper/2507.22879"},"observation_digest":"sha256:4fc4644f4ac82d5bd8ebe6726b207fce7bc9d537fe9232734c3e01d3a3e8801a","observation_id":"78fd9cf5-fe74-41da-8608-823498e8de66","resolution":{"observed_at":"2026-08-06T11:16:04.410798Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.18965","last_updated":"2025-02-26T09:25:10Z","snapshot_observed_at":"2026-07-06T20:42:55.911327Z","submitted_at":"2025-02-26T09:25:10Z","title":"OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.18965","snapshot_observed_at":"2026-08-06T11:16:04.464301Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-06T11:16:04.464301Z"},"links":{"cited_paper":"/paper/2502.18965","citing_paper":"/paper/2507.22879"},"observation_digest":"sha256:e62f36396ec4bf02370ab1ed5c5aa0227aace81bd6f287eabf331ac766c60d36","observation_id":"5b80af6a-a94c-4a6f-823f-b5ec635b7628","resolution":{"observed_at":"2026-08-06T11:16:04.464301Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.02736","last_updated":"2024-10-04T03:57:47Z","snapshot_observed_at":"2026-08-01T08:21:19.528254Z","submitted_at":"2024-10-03T17:53:30Z","title":"Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.02736","snapshot_observed_at":"2026-08-06T11:16:05.269040Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-06T11:16:05.269040Z"},"links":{"cited_paper":"/paper/2410.02736","citing_paper":"/paper/2507.22879"},"observation_digest":"sha256:25a68549a9bc642e062ce53311f53cdef5cd61cec741b0263c9f24a9b5c1e5c5","observation_id":"15550386-8982-4554-9c6c-a04763a0b231","resolution":{"observed_at":"2026-08-06T11:16:05.269040Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.22879","last_updated":"2025-07-31T16:54:43Z","latest_version":2,"primary_category":"cs.IR","snapshot_observed_at":"2026-08-06T11:16:02.241906Z","submitted_at":"2025-07-30T17:55:06Z","title":"RecGPT Technical Report"},"reference_resolution":{"displayed":15,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":15},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 16 inbound Pith citation observations for arXiv:2507.22879."}