{"as_of":"2026-08-09T18:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:784c7257bb00e62d5e9843b8b7bed010318286e563ab4ac65970b707fe5bd9f8","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":18,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":18,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":18,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":18,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T22:14:07.969295Z","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":"2026-07-02T20:17:22.260897Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":"2305.05065","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-07-02T20:17:22.260897Z","title":"Recommender systems with generative retrieval","venue":null,"work_id":"947e6125-3994-4f1e-a097-8d899f6f5f78","year":2023},"citing_paper":{"arxiv_id":"2312.10997","last_updated":"2024-03-27T09:16:57Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-18T07:47:33Z","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","version":5},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-24T05:10:25.171044Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2312.10997"},"observation_digest":"sha256:bb10d8c4e341fef35f3a6132e0302f8e2b0f4b98557804e8b8623764b71ab4b2","observation_id":"b339dcdf-fcea-441a-8897-bbf1a2ef43a0","resolution":{"observed_at":"2026-05-24T05:13:57.093164Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-08-06T22:14:07.969295Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.22262","last_updated":"2025-06-27T14:30:12Z","snapshot_observed_at":"2026-08-06T22:05:24.047262Z","submitted_at":"2025-06-27T14:30:12Z","title":"JointRank: Rank Large Set with Single Pass","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T22:14:07.969295Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2506.22262"},"observation_digest":"sha256:c55134ac1df29d2e7f5bc41e60282b387e5d81fb1e2da8de79092ea558f582f6","observation_id":"6ae0cedc-76be-4de8-a368-ac279ad96c53","resolution":{"observed_at":"2026-08-06T22:14:07.969295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-08-02T20:42:42.844104Z","title":"Keshavan, Trung Hieu Vu, Lukasz Heldt, Lichan Hong, Yi Tay, Vinh Q","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.22647","last_updated":"2026-07-20T21:24:06Z","snapshot_observed_at":"2026-08-08T21:20:44.155178Z","submitted_at":"2026-02-26T06:00:56Z","title":"Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T20:42:42.844104Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2602.22647"},"observation_digest":"sha256:bee445c903f6fd7e56f0a883c7296adafc4d34aa632a7077a37b07dfa0b446ba","observation_id":"29616544-2490-4612-9a12-a5e7ea4ec85c","resolution":{"observed_at":"2026-08-02T20:42:42.844104Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":"2305.05065","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-07-02T20:17:22.260897Z","title":"Recommender systems with generative retrieval","venue":null,"work_id":"947e6125-3994-4f1e-a097-8d899f6f5f78","year":2023},"citing_paper":{"arxiv_id":"2604.10471","last_updated":"2026-04-12T05:51:35Z","snapshot_observed_at":"2026-07-06T22:59:05.519456Z","submitted_at":"2026-04-12T05:51:35Z","title":"SID-Coord: Coordinating Semantic IDs for ID-based Ranking in Short-Video Search","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-10T16:21:14.663436Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2604.10471"},"observation_digest":"sha256:32f1f75e1445e48497319ee63ecc134c24d586fa6ec76d8aae2bec5d68b0b20e","observation_id":"620be13b-26ca-450f-b9a7-96faac83f766","resolution":{"observed_at":"2026-05-11T09:00:59.327720Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":"2305.05065","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-07-02T20:17:22.260897Z","title":"Recommender systems with generative retrieval","venue":null,"work_id":"947e6125-3994-4f1e-a097-8d899f6f5f78","year":2023},"citing_paper":{"arxiv_id":"2605.05096","last_updated":"2026-05-06T16:33:13Z","snapshot_observed_at":"2026-08-01T14:30:19.540929Z","submitted_at":"2026-05-06T16:33:13Z","title":"CapsID: Soft-Routed Variable-Length Semantic IDs for Generative Recommendation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-08T15:54:53.821143Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2605.05096"},"observation_digest":"sha256:7794b3cd451b18e23897bb4080c46cc6429e72ebacc90bccf134b9f022784c40","observation_id":"bfc7b78b-19a1-4016-a716-b0167c00a808","resolution":{"observed_at":"2026-05-11T18:26:12.707789Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":"2305.05065","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-07-02T20:17:22.260897Z","title":"Recommender systems with generative retrieval","venue":null,"work_id":"947e6125-3994-4f1e-a097-8d899f6f5f78","year":2023},"citing_paper":{"arxiv_id":"2605.11553","last_updated":"2026-05-12T05:35:00Z","snapshot_observed_at":"2026-08-04T08:21:56.364054Z","submitted_at":"2026-05-12T05:35:00Z","title":"TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-13T01:40:04.856714Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2605.11553"},"observation_digest":"sha256:d9457f9bae5b6028c7f12492e1fd2f404041be252fedea4c1dc9b5c7feae5d9c","observation_id":"c9bf3527-f3b1-4c34-a39a-3bae21a10da8","resolution":{"observed_at":"2026-05-13T01:42:03.658122Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":"2305.05065","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-07-02T20:17:22.260897Z","title":"Recommender systems with generative retrieval","venue":null,"work_id":"947e6125-3994-4f1e-a097-8d899f6f5f78","year":2023},"citing_paper":{"arxiv_id":"2605.17779","last_updated":"2026-05-18T02:57:19Z","snapshot_observed_at":"2026-07-06T23:28:45.646975Z","submitted_at":"2026-05-18T02:57:19Z","title":"Learning Variable-Length Tokenization for Generative Recommendation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-20T12:00:37.247231Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2605.17779"},"observation_digest":"sha256:284ca54d13bb2a9c47bf9dac707ca830c35a209f831041d52e1a6c6c7e6f82ab","observation_id":"d93d1b5d-55de-43c0-8191-961144c08544","resolution":{"observed_at":"2026-05-20T12:03:15.107625Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":"2305.05065","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-07-02T20:17:22.260897Z","title":"Recommender systems with generative retrieval","venue":null,"work_id":"947e6125-3994-4f1e-a097-8d899f6f5f78","year":2023},"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":12,"source":"pdf_text","source_observed_at":"2026-06-29T10:27:47.543575Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2605.27856"},"observation_digest":"sha256:9a5b0d80450e7ebee004c563080fe3d39d71965fe6a41437413be0fbc6a592b2","observation_id":"e74b4bf1-07af-46e3-9f8b-087e4f893d25","resolution":{"observed_at":"2026-06-29T13:23:28.691081Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":"2305.05065","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-07-02T20:17:22.260897Z","title":"Recommender systems with generative retrieval","venue":null,"work_id":"947e6125-3994-4f1e-a097-8d899f6f5f78","year":2023},"citing_paper":{"arxiv_id":"2606.03221","last_updated":"2026-06-02T06:31:15Z","snapshot_observed_at":"2026-08-02T14:56:40.298857Z","submitted_at":"2026-06-02T06:31:15Z","title":"VirtualMLE: A Virtual ML Engineer that Optimizes Sequential Recommenders","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-28T08:34:32.266593Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2606.03221"},"observation_digest":"sha256:8bd3afde710f68324fad338cb31977188c1b516a3be6ed2c35e6f1a097a1899f","observation_id":"412d14f5-5376-4710-81f5-80f74ad1b54a","resolution":{"observed_at":"2026-07-02T05:06:39.824419Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":"2305.05065","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-07-02T20:17:22.260897Z","title":"Recommender systems with generative retrieval","venue":null,"work_id":"947e6125-3994-4f1e-a097-8d899f6f5f78","year":2023},"citing_paper":{"arxiv_id":"2606.07317","last_updated":"2026-06-08T08:58:58Z","snapshot_observed_at":"2026-08-03T01:41:20.836170Z","submitted_at":"2026-06-05T14:37:02Z","title":"Gated Bidirectional Linear Attention for Generative Retrieval","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-27T20:38:01.086990Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2606.07317"},"observation_digest":"sha256:75dbf0dae4cc7635bbcc431df12b61c28c24a7ff052a7d1bf29ab8130d6346f1","observation_id":"055a0c11-175d-48a4-89ba-41f8d442e6ab","resolution":{"observed_at":"2026-07-02T20:17:22.262268Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-07-12T06:51:24.908954Z","title":"Keshavan, Trung Vu, Lukasz Heldt, Lichan Hong, Yi Tay, Vinh Q","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.02818","last_updated":"2026-07-27T07:35:55Z","snapshot_observed_at":"2026-08-07T09:19:50.796252Z","submitted_at":"2026-07-02T23:13:36Z","title":"Session-Level Optimization for Large-Scale Retrieval using REINFORCE with Multi-Step Off-Policy Correction","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-12T06:51:24.908954Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2607.02818"},"observation_digest":"sha256:b8713c761c2aebc7792e6999d1a363384f2708f47bec58776cef8832875ee71d","observation_id":"5da09078-a3ea-4841-a1f9-4d878c299403","resolution":{"observed_at":"2026-07-12T06:51:24.908954Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-08-02T08:59:05.476742Z","title":"Keshavan, Trung Vu, Lukasz Heldt, Lichan Hong, Yi Tay, Vinh Q","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.02818","last_updated":"2026-07-27T07:35:55Z","snapshot_observed_at":"2026-08-07T09:19:50.796252Z","submitted_at":"2026-07-02T23:13:36Z","title":"Session-Level Optimization for Large-Scale Retrieval using REINFORCE with Multi-Step Off-Policy Correction","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T08:59:05.476742Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2607.02818"},"observation_digest":"sha256:44d6075664cfe739514f5043fd78300ada32afd76fcc4f91e9b019166e7aae69","observation_id":"7ab6e48a-651e-482b-b457-69918942bd4a","resolution":{"observed_at":"2026-08-02T08:59:05.476742Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-07-14T14:54:14.248741Z","title":"Keshavan, Trung Vu, Lukasz Heldt, Lichan Hong, Yi Tay, Vinh Q","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.09877","last_updated":"2026-07-10T18:10:01Z","snapshot_observed_at":"2026-08-08T11:45:07.937317Z","submitted_at":"2026-07-10T18:10:01Z","title":"Serving the Long Tail: Training-Free LLM Candidate Generation for Vacation Rental Marketplaces","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-14T14:54:14.248741Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2607.09877"},"observation_digest":"sha256:b9d4d79135783b845cff21035f0b7ba48a2e32c9201cbfaad8e5d3f1808351a3","observation_id":"d7943141-aaf2-4211-9d66-ff957acb7f8a","resolution":{"observed_at":"2026-07-14T14:54:14.248741Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-07-14T01:13:45.038679Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.09988","last_updated":"2026-07-22T17:27:17Z","snapshot_observed_at":"2026-08-07T17:41:38.659566Z","submitted_at":"2026-07-10T21:28:43Z","title":"An LLM-powered Agentic Recommendation System for Connected TV Content Discovery","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-14T01:13:45.038679Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2607.09988"},"observation_digest":"sha256:4d7e812fa8f48a141c295054a457b1b66bf368688e19484b141f821e302a4360","observation_id":"147f2092-a84d-4448-874d-f2a3a904ac5a","resolution":{"observed_at":"2026-07-14T01:13:45.038679Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-08-02T07:33:13.096097Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.09988","last_updated":"2026-07-22T17:27:17Z","snapshot_observed_at":"2026-08-07T17:41:38.659566Z","submitted_at":"2026-07-10T21:28:43Z","title":"An LLM-powered Agentic Recommendation System for Connected TV Content Discovery","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T07:33:13.096097Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2607.09988"},"observation_digest":"sha256:7acf8b3470b440eb109ce40b7f257bd1d4cbb9aa194fc4372a2728e132cf442f","observation_id":"457d54b1-024b-4c3a-b1ef-0dbf57c57234","resolution":{"observed_at":"2026-08-02T07:33:13.096097Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-08-01T03:52:37.036195Z","title":"Keshavan, Trung Vu, Lukasz Heldt, Lichan Hong, Yi Tay, Vinh Q","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23038","last_updated":"2026-07-25T04:45:04Z","snapshot_observed_at":"2026-08-09T06:58:05.909605Z","submitted_at":"2026-07-25T04:45:04Z","title":"EGR: Embedding-Native Generative Retrieval with a Shared LLM","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T03:52:37.036195Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2607.23038"},"observation_digest":"sha256:2b089a5dfd6f99494ec1f64a1e61462e26a1ca47c9b39dfe5c510d9a3bf4e512","observation_id":"5aa10e0b-f6b2-46df-9e9b-70cc55bb83ec","resolution":{"observed_at":"2026-08-01T03:52:37.036195Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-07-31T23:18:21.999500Z","title":"Keshavan, Trung Vu, Lukasz Heldt, Lichan Hong, Yi Tay, Vinh Q","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24015","last_updated":"2026-07-27T05:25:50Z","snapshot_observed_at":"2026-08-06T18:06:46.075056Z","submitted_at":"2026-07-27T05:25:50Z","title":"Mosaic: A Fleet of User Embedding Specialists for Recommendation at Meta","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:21.999500Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2607.24015"},"observation_digest":"sha256:c1896c31579576c5a42d6fcb1a405fe1727a4120df52bbd0699a46342e0f63a8","observation_id":"f610840e-8c45-4fd3-986e-3fdb189571aa","resolution":{"observed_at":"2026-07-31T23:18:21.999500Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-08-05T00:28:22.604793Z","title":"Tran, Jonah Samost, Maciej Kula, Ed H","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.00750","last_updated":"2026-08-01T16:33:15Z","snapshot_observed_at":"2026-08-06T23:19:16.536876Z","submitted_at":"2026-08-01T16:33:15Z","title":"Hierarchical Residual Policy Optimization for Generative Recommendations","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T00:28:22.604793Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2608.00750"},"observation_digest":"sha256:91aa71e5e29d1b6f89769ed13fc469a5d8530a410e72ddd90a141854b25fdf26","observation_id":"a1e39e40-449c-4cc3-8937-6319bb528cfd","resolution":{"observed_at":"2026-08-05T00:28:22.604793Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2305.05065/citation-record","integrity":"/paper/2305.05065/integrity","json":"/paper/2305.05065/citation-record.json","paper":"/paper/2305.05065"},"outbound":[],"paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","latest_version":3,"primary_category":"cs.IR","snapshot_observed_at":"2026-07-06T15:24:49.798924Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 18 inbound Pith citation observations for arXiv:2305.05065."}