{"as_of":"2026-08-08T12:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b1f7c8f2f059ea5b6fcef58fbdd76d92a7497b1881b8bc09cfd44e5155b7e05f","coverage":[{"denominator":53,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":53,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T08:44:52.772336Z","state":"measured"},{"denominator":53,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":53,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2607.21028/citation-record","integrity":"/paper/2607.21028/integrity","json":"/paper/2607.21028/citation-record.json","paper":"/paper/2607.21028"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2010.00904","last_updated":"2021-03-24T07:21:07Z","snapshot_observed_at":"2026-07-06T10:00:53.952758Z","submitted_at":"2020-10-02T10:13:31Z","title":"Autoregressive Entity Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.00904","snapshot_observed_at":"2026-08-01T08:44:48.226677Z","title":"Autoregressive entity retrieval,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:48.226677Z"},"links":{"cited_paper":"/paper/2010.00904","citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:4ff8bc016fcc295709cd4e13c45f86a80fffee56d12d3df10bd7265147b3a795","observation_id":"2c3f1378-3911-460c-ad3e-1dad8ceaa6a8","resolution":{"observed_at":"2026-08-01T08:44:48.226677Z","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":"2026-08-01T08:44:48.307007Z","title":"Recommendation as language processing (rlp): A unified pretrain, personalized prompt & predict paradigm (p5),","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:48.307007Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:60192cb2b528c75470d393759d7253a8011d1ab5fa7ae409150d2037d1e5b049","observation_id":"8614a72c-a25f-4e44-9936-996e3e17e784","resolution":{"observed_at":"2026-08-01T08:44:48.307007Z","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":"2026-08-01T08:44:48.376454Z","title":"Recommender systems with generative retrieval,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:48.376454Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:bbc1d50a596e6644eebe8c24cd00d87c3e76673c23fdb833826414e6b333066d","observation_id":"97294400-2c05-4cc6-8b11-c6a9128d1226","resolution":{"observed_at":"2026-08-01T08:44:48.376454Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.24787","last_updated":"2026-06-11T02:25:51Z","snapshot_observed_at":"2026-08-06T18:07:20.685251Z","submitted_at":"2025-12-31T11:16:24Z","title":"HiGR: Industrial-Scale Hierarchical Generative Slate Recommendation Framework in Tencent","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2512.24787","snapshot_observed_at":"2026-08-01T08:44:48.462180Z","title":"Higr: Efficient generative slate recommendation via hierarchical planning and multi-objective preference alignment,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:48.462180Z"},"links":{"cited_paper":"/paper/2512.24787","citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:7f3f43bb55b5a645ee2cfd1911b1089566fa9c5b8658f02e5433432da31ab3ca","observation_id":"f583d91f-b146-488d-9313-856ebf43343c","resolution":{"observed_at":"2026-08-01T08:44:48.462180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13581","last_updated":"2025-08-15T23:44:20Z","snapshot_observed_at":"2026-08-07T18:06:05.980404Z","submitted_at":"2025-02-19T09:45:29Z","title":"ActionPiece: Contextually Tokenizing Action Sequences for Generative Recommendation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13581","snapshot_observed_at":"2026-08-01T08:44:48.476607Z","title":"Actionpiece: Contextually tokeniz- ing action sequences for generative recommendation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:48.476607Z"},"links":{"cited_paper":"/paper/2502.13581","citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:02519bd2ed586bffad438ac2cdd591892e749d48210263181f05bf8d475dfa9e","observation_id":"2bc7f883-12c8-4984-9b38-fb394daab8e4","resolution":{"observed_at":"2026-08-01T08:44:48.476607Z","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":"2026-08-01T08:44:48.623118Z","title":"Onesug: The unified end-to-end generative framework for e- commerce query suggestion,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:48.623118Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:e2cdfbdeebfae47d8387b318689f47c6bb901794af035ddbc9d70583e86e24fa","observation_id":"72c961c3-408e-4a5b-bdad-a02790397008","resolution":{"observed_at":"2026-08-01T08:44:48.623118Z","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":"2026-08-01T08:44:48.706517Z","title":"Learnable item tokenization for generative recommendation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:48.706517Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:404d5b3c6da5731ee66970ab7b852ca9849f7cb08e87b53644e69bdff3e6c1e9","observation_id":"8ea1226a-7ff5-4286-849a-26d5dadd3f26","resolution":{"observed_at":"2026-08-01T08:44:48.706517Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.02453","last_updated":"2025-03-04T10:00:05Z","snapshot_observed_at":"2026-08-07T17:30:58.972740Z","submitted_at":"2025-03-04T10:00:05Z","title":"Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.02453","snapshot_observed_at":"2026-08-01T08:44:48.801375Z","title":"Sparse meets dense: Unified generative recom- mendations with cascaded sparse-dense representations,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:48.801375Z"},"links":{"cited_paper":"/paper/2503.02453","citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:e9881d3dd9d5f6dd4a0cea151d8ee659758de6da3da7daa63897c1c549841b32","observation_id":"000584a6-15d0-48a1-9393-c653f4de96a3","resolution":{"observed_at":"2026-08-01T08:44:48.801375Z","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":"2026-08-01T08:44:48.906794Z","title":"Order-agnostic identifier for large language model-based generative recommendation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:48.906794Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:f890da8682347c5393446d9a963409da21d8fc01519015dc1f2a762e9e12065d","observation_id":"5347ea11-a10f-4462-a9a4-9cdf915e07b3","resolution":{"observed_at":"2026-08-01T08:44:48.906794Z","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":"2026-08-01T08:44:49.017345Z","title":"Generative recommender with end-to-end learnable item tokenization,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:49.017345Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:8d9337e2da6ceb8c96d94c4ab921d1b4fa4d41d3dd28de6171ec7b8088e2719a","observation_id":"5d687e59-3856-4746-aa10-e1a4a948d417","resolution":{"observed_at":"2026-08-01T08:44:49.017345Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.04405","last_updated":"2025-05-25T06:31:38Z","snapshot_observed_at":"2026-08-08T01:34:17.500720Z","submitted_at":"2025-04-06T08:07:49Z","title":"Universal Item Tokenization for Transferable Generative Recommendation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.04405","snapshot_observed_at":"2026-08-01T08:44:49.132516Z","title":"Universal item tokenization for transferable generative recommendation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:49.132516Z"},"links":{"cited_paper":"/paper/2504.04405","citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:0e3cf1c621d08089a72731ec3a1ff07bb395d59ca5030ce52d268ef1d0ad2d85","observation_id":"bd742ec2-5881-439e-86d4-55b95816e67a","resolution":{"observed_at":"2026-08-01T08:44:49.132516Z","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":"2026-08-01T08:44:49.290002Z","title":"Vqrae: Representation quantization autoencoders for mul- timodal understanding, generation and reconstruction,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:49.290002Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:406f4302a8973f7b6d888a69805032174bb6679f89918078eb46531d3e5e16b7","observation_id":"d74b3d13-503b-44d0-ac0b-ccb9caa11b8b","resolution":{"observed_at":"2026-08-01T08:44:49.290002Z","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":"2026-08-01T08:44:49.444057Z","title":"Neural discrete representation learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:49.444057Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:79a72addb744a1e307fc18dac73d3f7ee27aacb7b34ebc463963db340ae3c84d","observation_id":"c9007dcf-1df9-49b8-93f2-6faae6ecf5bb","resolution":{"observed_at":"2026-08-01T08:44:49.444057Z","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":"2026-08-01T08:44:49.545426Z","title":"Autoregressive image generation using residual quantization,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:49.545426Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:8131dfd805ac9a9bd9ef4f7c4ce3e5f250460b9b8b5553c19634c6fa482649e1","observation_id":"0f2d4fca-3219-4d46-b16e-d147d4fc9124","resolution":{"observed_at":"2026-08-01T08:44:49.545426Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1511.06939","last_updated":"2016-03-29T14:52:58Z","snapshot_observed_at":"2026-07-31T19:00:00.136727Z","submitted_at":"2015-11-21T23:42:59Z","title":"Session-based Recommendations with Recurrent Neural Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.06939","snapshot_observed_at":"2026-08-01T08:44:49.652814Z","title":"Session- based recommendations with recurrent neural networks,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:49.652814Z"},"links":{"cited_paper":"/paper/1511.06939","citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:f0f3d30d0777796a03840bd8fb7e04226ef6d1b8ecd876cc61e120478f0f2e35","observation_id":"e0e4f432-8d1f-41ab-bec4-c323ce3eb525","resolution":{"observed_at":"2026-08-01T08:44:49.652814Z","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":"2026-08-01T08:44:49.759605Z","title":"Personalized top-n sequential recommendation via convolutional sequence embedding,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:49.759605Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:89ba7b6940a3f96ab7c526f7e5c6572f0a12c83369f1dd30edae4d88987875f4","observation_id":"e7bea6a6-de4b-48f8-98cc-483656fbca1b","resolution":{"observed_at":"2026-08-01T08:44:49.759605Z","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":"2026-08-01T08:44:49.866067Z","title":"Self-attentive sequential recommenda- tion,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:49.866067Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:9c3211176aa009f95818790d3180dace65051f1ca1987f28e7eec1c18600295b","observation_id":"efa18801-30cb-4432-9e3e-f104d06cb07a","resolution":{"observed_at":"2026-08-01T08:44:49.866067Z","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":"2026-08-01T08:44:50.055675Z","title":"Bert4rec: Sequential recommendation with bidirectional encoder representations from transformer,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:50.055675Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:807ee936774fa7bc52f04f3e227103dd20d63a9ae9e6ffec173f95969858aba7","observation_id":"f534fb67-9a20-458f-bbf0-6c013334fd94","resolution":{"observed_at":"2026-08-01T08:44:50.055675Z","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":"2026-08-01T08:44:50.220166Z","title":"Feature-level deeper self-attention network for sequential recom- mendation","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:50.220166Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:a79d4f9987b69e794a20133cfaea76c516d43d72e3903b4b4fb13f265ffd1a07","observation_id":"44ffaa0c-e893-4501-a527-5ef75fb829b1","resolution":{"observed_at":"2026-08-01T08:44:50.220166Z","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":"2026-08-01T08:44:50.374427Z","title":"S3-rec: Self-supervised learning for sequential recom- mendation with mutual information maximization,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:50.374427Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:41f6e478cadbcb36dcb72617d3a09828f2fd2dbcd807e8715f4e7b13d4fd7771","observation_id":"4213863e-bd9d-4876-8333-d77dc3f676cb","resolution":{"observed_at":"2026-08-01T08:44:50.374427Z","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":"2026-08-01T08:44:50.488161Z","title":"Diffurec: A diffusion model for sequential recommendation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:50.488161Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:0726d0ceaff5abaafd2b92bdbd921f02f9ebbb59e64031ae4f3d262a7c35671d","observation_id":"4bd5d4f9-35ed-4fb7-8adb-9c8e48874abf","resolution":{"observed_at":"2026-08-01T08:44:50.488161Z","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":"2026-08-01T08:44:50.644827Z","title":"Strec: Sparse transformer for sequential recommendations,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:50.644827Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:d0998463e02cc0f51c383493bd9ab2e28b911898aed39c6d50e23000fa2407b2","observation_id":"7b439541-0ca6-4ae4-aa9e-b66b108a6d1e","resolution":{"observed_at":"2026-08-01T08:44:50.644827Z","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":"2026-08-01T08:44:50.756689Z","title":"Zero-shot recommendation: Towards class semantic relation learning for inferring labels of unseen micro-videos,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:50.756689Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:d812d05ddbd97a1c6ab596026c0edb5bac8b5e0278f1d3a19148b42777cfa242","observation_id":"3362cafa-43f3-4190-a5bd-7675e690938b","resolution":{"observed_at":"2026-08-01T08:44:50.756689Z","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":"2026-08-01T08:44:50.918756Z","title":"Wide & deep learning for recommender systems,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:50.918756Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:f8003ea85ae195a4435dcf3c71824a686bbcdf51ef455273c533860f1f9ba8cd","observation_id":"0b3e1304-1392-49ea-9f9d-522430082f86","resolution":{"observed_at":"2026-08-01T08:44:50.918756Z","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":"2026-08-01T08:44:51.085041Z","title":"Deep neural networks for youtube recommendations,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:51.085041Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:46dd2d28ab4e157045bf1af6fc8dc9db7213f7954a40a521d95bb5436d99d8fb","observation_id":"d51041fe-7653-42dc-ba57-97cc6b696454","resolution":{"observed_at":"2026-08-01T08:44:51.085041Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04247","last_updated":"2017-03-13T04:55:19Z","snapshot_observed_at":"2026-07-06T05:33:25.278531Z","submitted_at":"2017-03-13T04:55:19Z","title":"DeepFM: A Factorization-Machine based Neural Network for CTR Prediction","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.04247","snapshot_observed_at":"2026-08-01T08:44:51.249908Z","title":"Deepfm: a factorization- machine based neural network for ctr prediction,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:51.249908Z"},"links":{"cited_paper":"/paper/1703.04247","citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:3e6bdb556d4d16158e0c7656628c64c2b1cc2399a017d5b313a812e051cccdb1","observation_id":"0ac32eb1-1a5c-45b6-be3e-bd0770472181","resolution":{"observed_at":"2026-08-01T08:44:51.249908Z","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":"2026-08-01T08:44:51.343937Z","title":"One model to rank them all: Unifying online advertising with end-to-end learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:51.343937Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:c8bd79ef239e8ed868e3efbd6ee5a0cf424e2eb02fee28a8f0b9dfb1e27de008","observation_id":"4cc1b5f3-945b-4920-ac0d-281cb108a83b","resolution":{"observed_at":"2026-08-01T08:44:51.343937Z","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":"2026-08-01T08:44:51.448412Z","title":"M6-rec: Generative pretrained language models are open-ended recommender systems,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:51.448412Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:39bd436d5ca2c054fb5f4f19cf2f97cabddc5ef1d834f5f1022b8592261ba123","observation_id":"67bec6e0-4dff-42ed-9c9e-a0d4a8d81821","resolution":{"observed_at":"2026-08-01T08:44:51.448412Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.16924","last_updated":"2024-04-25T17:58:17Z","snapshot_observed_at":"2026-07-06T18:05:46.922400Z","submitted_at":"2024-04-25T17:58:17Z","title":"A Survey of Generative Search and Recommendation in the Era of Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.16924","snapshot_observed_at":"2026-08-01T08:44:51.550618Z","title":"A survey of generative search and recommendation in the era of large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:51.550618Z"},"links":{"cited_paper":"/paper/2404.16924","citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:cad7b8fe70fd5f2a3ca08af0960fda047ac191b26d3a18070ae8f672f6b8ebec","observation_id":"4800448c-89e9-4341-b982-2d23097a5326","resolution":{"observed_at":"2026-08-01T08:44:51.550618Z","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":"2026-08-01T08:44:51.715831Z","title":"A bi-step grounding paradigm for large language mod- els in recommendation systems,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:51.715831Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:e29d6dc6cacc7683fe8864b91646c985181ac8299ee1d12c3610b96756b0b84e","observation_id":"07801bf0-8a53-4c86-8810-7dbefe70cfa1","resolution":{"observed_at":"2026-08-01T08:44:51.715831Z","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":"2026-08-01T08:44:51.780918Z","title":"Reinforced latent reasoning for llm-based recommendation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:51.780918Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:f817b69e3765178435c4ea42c39b6976319e79614696e5ee27a21f20320bcb6a","observation_id":"d13a4fc1-de10-4c6d-9a60-2ae036224e0b","resolution":{"observed_at":"2026-08-01T08:44:51.780918Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.08686","last_updated":"2026-04-26T10:26:29Z","snapshot_observed_at":"2026-08-02T05:43:35.758141Z","submitted_at":"2024-08-16T11:59:01Z","title":"MVIGER: Multi-View Variational Integration of Complementary Knowledge for Generative Recommender","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.08686","snapshot_observed_at":"2026-08-01T08:44:51.879971Z","title":"Mviger: Multi- view variational integration of complementary knowledge for generative recommender,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:51.879971Z"},"links":{"cited_paper":"/paper/2408.08686","citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:74f9bd2feeb28d11415107a5cf391ddf8cae6deac954b90e2d916fe89f00706f","observation_id":"c26a8a2d-d27e-453f-918a-f89b0b1e49b3","resolution":{"observed_at":"2026-08-01T08:44:51.879971Z","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":"2026-08-01T08:44:51.892449Z","title":"How to index item ids for recommendation foundation models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:51.892449Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:f99cfe9deb4deaeb45545c929e1d3228ccfd758190811e4b1620106a18f6f932","observation_id":"54930246-e53e-47eb-a76b-1d88c5f1bf96","resolution":{"observed_at":"2026-08-01T08:44:51.892449Z","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":"2026-08-01T08:44:52.023509Z","title":"Learning to tokenize for generative retrieval,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.023509Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:6611b40c569ad2a1b8913be2715fac15644b640d36157d83d0b5f9d1b11c2fdd","observation_id":"046543a4-5067-493d-b430-5a292c664b13","resolution":{"observed_at":"2026-08-01T08:44:52.023509Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17152","last_updated":"2024-05-06T02:05:45Z","snapshot_observed_at":"2026-08-06T03:48:40.952592Z","submitted_at":"2024-02-27T02:37:37Z","title":"Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17152","snapshot_observed_at":"2026-08-01T08:44:52.127574Z","title":"Actions speak louder than words: Trillion-parameter sequential transducers for generative recommendations,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.127574Z"},"links":{"cited_paper":"/paper/2402.17152","citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:05839cea0bf084c4e599b287c80c62868be8509d2e75b3acbedaae604000f2ef","observation_id":"939f1da2-f677-4472-8a0e-d1c89f67b9b2","resolution":{"observed_at":"2026-08-01T08:44:52.127574Z","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":"2026-08-01T08:44:52.237591Z","title":"Onerec: Unifying retrieve and rank with generative recommender and iterative preference alignment,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.237591Z"},"links":{"cited_paper":"/paper/2502.18965","citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:8656bdbb49464d636d7198cc44552a4d0d61b950d8095bc2eb3221203ff2f1e0","observation_id":"0a815e1b-f14d-4c59-a6e5-93f15c8d668c","resolution":{"observed_at":"2026-08-01T08:44:52.237591Z","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":"2026-08-01T08:44:52.328107Z","title":"Onerec-think: In-text reasoning for generative recommendation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.328107Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:2d38cdcd610a0ba4bee23eac64b399dd88f5dd06c3865ec41c9fa6c9435e9e26","observation_id":"71ccce3a-f753-4542-99bb-e7f90352bd7d","resolution":{"observed_at":"2026-08-01T08:44:52.328107Z","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":"2026-08-01T08:44:52.446572Z","title":"Generating long semantic ids in parallel for recommendation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.446572Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:04efcfb53ed825943003fe2774fcf5e86277fd26fbfa1960c14b92230865a9aa","observation_id":"c84b3536-6d8b-4fa6-91df-2df8fd1c46a7","resolution":{"observed_at":"2026-08-01T08:44:52.446572Z","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":"2026-08-01T08:44:52.552135Z","title":"Drift- aware continual tokenization for generative recommendation,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.552135Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:c4946b0a2965e69cca4754511ce8e976e6099fcc87a899ab5e51756f84671a85","observation_id":"f7132fa6-4d6f-450e-bd95-935ad8665eb1","resolution":{"observed_at":"2026-08-01T08:44:52.552135Z","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":"2026-08-01T08:44:52.690875Z","title":"Delrec: Distilling sequential pattern to enhance llms-based sequential recommendation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.690875Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:46e8fc7e91097f95e03b80ebecce301aabd006bf512c9f7ff9b22fd12e297887","observation_id":"687878e7-2a6d-472f-bbe1-65cd2e8624e2","resolution":{"observed_at":"2026-08-01T08:44:52.690875Z","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":"2026-08-01T08:44:52.741000Z","title":"Reg4rec: Reasoning-enhanced genera- tive model for large-scale recommendation systems,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.741000Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:9537091b40f5765d35b4aad1bac1464b04f4ca93b1bfc97610503fd53d58b0f8","observation_id":"8bd4a505-358d-4b2c-b6c7-a6233fddb2a8","resolution":{"observed_at":"2026-08-01T08:44:52.741000Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.12409","last_updated":"2022-04-22T18:20:48Z","snapshot_observed_at":"2026-08-07T11:26:24.970964Z","submitted_at":"2021-08-27T17:35:06Z","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.12409","snapshot_observed_at":"2026-08-01T08:44:52.743689Z","title":"Train short, test long: Attention with linear biases enables input length extrapolation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.743689Z"},"links":{"cited_paper":"/paper/2108.12409","citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:187e500c7f11dd34c1ae0358dd955f49e54645c7a2fdece7a5549905d1ba40c7","observation_id":"e5ae2cf2-5a2d-4bd8-a012-5379121f2495","resolution":{"observed_at":"2026-08-01T08:44:52.743689Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.05150","last_updated":"2020-12-02T17:52:35Z","snapshot_observed_at":"2026-07-31T17:17:17.205582Z","submitted_at":"2020-04-10T17:54:09Z","title":"Longformer: The Long-Document Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.05150","snapshot_observed_at":"2026-08-01T08:44:52.746303Z","title":"Longformer: The long- document transformer,","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.746303Z"},"links":{"cited_paper":"/paper/2004.05150","citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:45ef418dc99d4066e1133eaeb3b9baefcb612a9b495652bcaa4cade18a81df6d","observation_id":"81961dac-5cc6-4844-804f-35675f66d129","resolution":{"observed_at":"2026-08-01T08:44:52.746303Z","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":"2026-08-01T08:44:52.749126Z","title":"Trie-aware transformers for generative recommendation,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.749126Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:59682c5d40a4015b07d0767c5ef1d9506435d883ed2757f4e067f3071d960ff5","observation_id":"d04ecb06-ec46-451d-a1d2-cb3201852436","resolution":{"observed_at":"2026-08-01T08:44:52.749126Z","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":"2026-08-01T08:44:52.751584Z","title":"Promise: Process reward models unlock test-time scaling laws in generative recommendations,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.751584Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:9f1523c5e08168f2dad5782eed2369dc41d566d9a061277ddd5eaa96424f8088","observation_id":"49743760-7a95-4025-a942-1a6ef6aaa835","resolution":{"observed_at":"2026-08-01T08:44:52.751584Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2603.02730","last_updated":"2026-06-30T11:53:25Z","snapshot_observed_at":"2026-08-03T07:54:57.259920Z","submitted_at":"2026-03-03T08:29:15Z","title":"APAO: Bridging the Training-Inference Gap in Generative Recommendation via Adaptive Prefix-Aware Optimization","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2603.02730","snapshot_observed_at":"2026-08-01T08:44:52.754131Z","title":"Apao: Adaptive prefix- aware optimization for generative recommendation,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.754131Z"},"links":{"cited_paper":"/paper/2603.02730","citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:ec676e8e02bf5b16e6efc163ce8474351df2057aff422d7786e892d4aa7982c6","observation_id":"a075a77f-ba16-409a-be87-294a6b83f1d7","resolution":{"observed_at":"2026-08-01T08:44:52.754131Z","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":"2026-08-01T08:44:52.756981Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.756981Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:e1574e4c16770620bdbe9288e7835f15ae43140a852f087dd976dbd02891aab6","observation_id":"03470179-1e4e-49af-812b-a8e3a5711794","resolution":{"observed_at":"2026-08-01T08:44:52.756981Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.03748","last_updated":"2019-01-22T18:47:12Z","snapshot_observed_at":"2026-07-06T06:49:24.960992Z","submitted_at":"2018-07-10T16:52:11Z","title":"Representation Learning with Contrastive Predictive Coding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.03748","snapshot_observed_at":"2026-08-01T08:44:52.759446Z","title":"Representation learning with contrastive predictive coding,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.759446Z"},"links":{"cited_paper":"/paper/1807.03748","citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:44a49dbee112b4d4e37db791875d6c68d3cbd0e5d9d0ba8875d6df94ba70d640","observation_id":"a22e5943-67bc-4493-8f98-64419705f0dd","resolution":{"observed_at":"2026-08-01T08:44:52.759446Z","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":"2026-08-01T08:44:52.762072Z","title":"Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.762072Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:3eb1c6f6c07ac930710e8783cdb2480cad72a77868bd08f2947439ac8be1405d","observation_id":"cea5f589-a5c9-4b9e-8300-f4ca05c386e0","resolution":{"observed_at":"2026-08-01T08:44:52.762072Z","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":"2026-08-01T08:44:52.764493Z","title":"Hierarchical gating networks for sequential recommendation,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.764493Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:8c252a9c0050cf5d4abc93fbb9ddd1fd329b2a15436fbdceee4de7e20ddb3d92","observation_id":"deda69de-9184-4d45-9194-c23cf331a483","resolution":{"observed_at":"2026-08-01T08:44:52.764493Z","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":"2026-08-01T08:44:52.766912Z","title":"Plum: Adapting pre-trained lan- guage models for industrial-scale generative recommendations,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.766912Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:482b01d0c497fc662aa870c35951e42e914bea188de6ba68f7f75b437b8f7594","observation_id":"ee555f7a-82db-496f-a02e-4f62ee63182f","resolution":{"observed_at":"2026-08-01T08:44:52.766912Z","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":"2026-08-01T08:44:52.769587Z","title":"Inductive representation learning on large graphs,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.769587Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:aeb2d5498d24a73785fcfb0a730ff485c25b1760c402ef31d8a878a4b7409024","observation_id":"97de7ed3-2854-4048-baec-a4c917b30476","resolution":{"observed_at":"2026-08-01T08:44:52.769587Z","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":"2026-08-01T08:44:52.772336Z","title":"Approximate nearest neighbor search under neural similarity metric for large-scale recommendation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-01T08:44:52.772336Z"},"links":{"citing_paper":"/paper/2607.21028"},"observation_digest":"sha256:fda94348a26295d59a55b9cd1e22a6886dfc06a499be06af08f14221181b21cd","observation_id":"00ea743f-f7df-469e-9edf-c97bedd4ee09","resolution":{"observed_at":"2026-08-01T08:44:52.772336Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.21028","last_updated":"2026-07-24T09:38:27Z","latest_version":2,"primary_category":"cs.IR","snapshot_observed_at":"2026-08-07T02:32:27.646297Z","submitted_at":"2026-07-23T08:11:57Z","title":"Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation"},"reference_resolution":{"displayed":53,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":53,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":53},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 53 of 53 outbound references and 0 inbound Pith citation observations for arXiv:2607.21028."}