{"as_of":"2026-08-09T13:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:678a4220940b86d3378fbf0503778d40b4d40af96fda90663d5e8a27abb60fd3","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":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":31,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T16:50:04.000236Z","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":"2026-06-30T00:24:05.122539Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-08-08T16:50:04.000236Z","title":"arXiv preprint arXiv:2108.04468 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.06097","last_updated":"2025-02-11T14:44:47Z","snapshot_observed_at":"2026-08-09T06:42:16.049083Z","submitted_at":"2025-02-10T02:06:17Z","title":"NLGR: Utilizing Neighbor Lists for Generative Rerank in Personalized Recommendation Systems","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-08T16:50:04.000236Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2502.06097"},"observation_digest":"sha256:becbadfd9c16e7d83ed43d839d536f26e9f60d5cafe36be10824c4b6420034b1","observation_id":"ba147a25-a8b5-4527-ae06-0d8e5abef0ae","resolution":{"observed_at":"2026-08-08T16:50:04.000236Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-08-07T21:47:11.316288Z","title":"arXiv preprint arXiv:2108.04468 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.09375","last_updated":"2025-02-13T14:44:15Z","snapshot_observed_at":"2026-08-08T20:01:01.807975Z","submitted_at":"2025-02-13T14:44:15Z","title":"FARM: Frequency-Aware Model for Cross-Domain Live-Streaming Recommendation","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T21:47:11.316288Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2502.09375"},"observation_digest":"sha256:56d98b7ab59076c63363037a028add4d1e08c7a6473fef32e01999247bbeffe4","observation_id":"bca9696d-5095-4f0e-b3a7-a9512309044f","resolution":{"observed_at":"2026-08-07T21:47:11.316288Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-08-07T19:15:10.900201Z","title":"arXiv preprint arXiv:2108.04468 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10157","last_updated":"2025-02-18T02:41:53Z","snapshot_observed_at":"2026-08-09T09:33:39.181377Z","submitted_at":"2025-02-14T13:36:20Z","title":"SessionRec: Next Session Prediction Paradigm For Generative Sequential Recommendation","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T19:15:10.900201Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2502.10157"},"observation_digest":"sha256:638f67e750902dd159593bdd77fde128f4897ae16a335e263e4f7712cdd6ecf3","observation_id":"915268a1-12c0-4826-a55a-128a24959d7b","resolution":{"observed_at":"2026-08-07T19:15:10.900201Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-08-07T15:03:15.784979Z","title":"arXiv preprint arXiv:2108.04468 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.16752","last_updated":"2025-08-18T11:53:56Z","snapshot_observed_at":"2026-08-09T03:01:38.812813Z","submitted_at":"2025-05-22T14:58:53Z","title":"Action is All You Need: Dual-Flow Generative Ranking Network for Recommendation","version":3},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T15:03:15.784979Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2505.16752"},"observation_digest":"sha256:ebc90a145789574300f070aea74c875fbfa79d74810728932d2c680e4b28c689","observation_id":"ec8074fb-0b01-447a-a843-fada861b856a","resolution":{"observed_at":"2026-08-07T15:03:15.784979Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-08-07T14:33:03.077344Z","title":"arXiv preprint arXiv:2108.04468 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.18654","last_updated":"2025-08-22T05:21:30Z","snapshot_observed_at":"2026-08-07T14:25:55.714627Z","submitted_at":"2025-05-24T11:47:28Z","title":"MTGR: Industrial-Scale Generative Recommendation Framework in Meituan","version":4},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T14:33:03.077344Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2505.18654"},"observation_digest":"sha256:abacf4639dfe37b89df406bd433e49bcf0c4eaaa2a7efb19590853ea664bd562","observation_id":"77db7895-b3d4-41e4-b72a-653b9f804dac","resolution":{"observed_at":"2026-08-07T14:33:03.077344Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-08-06T19:36:33.508433Z","title":"arXiv preprint arXiv:2108.04468 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.05142","last_updated":"2025-07-07T15:51:27Z","snapshot_observed_at":"2026-08-06T21:44:22.156482Z","submitted_at":"2025-07-07T15:51:27Z","title":"GIST: Cross-Domain Click-Through Rate Prediction via Guided Content-Behavior Distillation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T19:36:33.508433Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2507.05142"},"observation_digest":"sha256:96ef8ef3a6da20b440858a5292a9981a4b27fcde5638f7b20b6432fb0603778c","observation_id":"50f90f1a-e569-4c5a-ba7e-c0aedd6ff7c8","resolution":{"observed_at":"2026-08-06T19:36:33.508433Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-08-06T19:09:02.003110Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.06503","last_updated":"2025-07-10T06:49:21Z","snapshot_observed_at":"2026-08-06T18:59:58.868086Z","submitted_at":"2025-07-09T03:02:23Z","title":"USD: A User-Intent-Driven Sampling and Dual-Debiasing Framework for Large-Scale Homepage Recommendations","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T19:09:02.003110Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2507.06503"},"observation_digest":"sha256:8b519033c72c3ee970a239f9d1f827439e91612a57e979aeff3b4f6f573bd631","observation_id":"0481efd0-2f52-400b-97e7-18eaf18e2e03","resolution":{"observed_at":"2026-08-06T19:09:02.003110Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-08-06T19:06:00.493347Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.06507","last_updated":"2025-07-14T07:46:11Z","snapshot_observed_at":"2026-08-08T04:13:41.618907Z","submitted_at":"2025-07-09T03:13:08Z","title":"GR-LLMs: Recent Advances in Generative Recommendation Based on Large Language Models","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-06T19:06:00.493347Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2507.06507"},"observation_digest":"sha256:c6dbab5a72764818c7aad786c0d4359186ae9440f754f4862e926f695390ccf8","observation_id":"158ac1d0-5472-4e85-b3b1-f9ebeb822078","resolution":{"observed_at":"2026-08-06T19:06:00.493347Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-08-06T17:43:31.888745Z","title":"CoRR abs/2108.04468 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10097","last_updated":"2025-07-14T09:32:26Z","snapshot_observed_at":"2026-08-07T08:53:09.970200Z","submitted_at":"2025-07-14T09:32:26Z","title":"User Long-Term Multi-Interest Retrieval Model for Recommendation","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-06T17:43:31.888745Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2507.10097"},"observation_digest":"sha256:00c1daf53cb263d9eb5f884951293f38497cc236e6b9713445ef2e3c3142c31f","observation_id":"e8e5496a-dd59-4ae1-9739-3bcd739e76b1","resolution":{"observed_at":"2026-08-06T17:43:31.888745Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-08-05T18:35:38.169452Z","title":"arXiv preprint arXiv:2108.04468 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.14515","last_updated":"2025-08-20T08:22:02Z","snapshot_observed_at":"2026-08-09T06:44:39.508456Z","submitted_at":"2025-08-20T08:22:02Z","title":"MISS: Multi-Modal Tree Indexing and Searching with Lifelong Sequential Behavior for Retrieval Recommendation","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-05T18:35:38.169452Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2508.14515"},"observation_digest":"sha256:da6cdaf3af897e5404e629f4337686e7430110ce98a66bd80a510d241587d4e8","observation_id":"9dd1b9fd-6740-4b2f-9fc0-36e9e5ec8326","resolution":{"observed_at":"2026-08-05T18:35:38.169452Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-08-05T14:23:21.615487Z","title":"arXiv preprint arXiv:2108.04468 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.21460","last_updated":"2025-08-29T09:46:16Z","snapshot_observed_at":"2026-08-09T06:44:43.611426Z","submitted_at":"2025-08-29T09:46:16Z","title":"Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Prediction","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-05T14:23:21.615487Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2508.21460"},"observation_digest":"sha256:636abf587147b392ee2d04978183796e1a3fe7ca071f76eb145ce498c2271495","observation_id":"cce69d37-93be-417f-a8d3-c2360aedd815","resolution":{"observed_at":"2026-08-05T14:23:21.615487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-08-05T12:54:20.639587Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.01184","last_updated":"2025-09-01T07:08:44Z","snapshot_observed_at":"2026-08-08T23:10:34.743249Z","submitted_at":"2025-09-01T07:08:44Z","title":"MARS: Modality-Aligned Retrieval for Sequence Augmented CTR Prediction","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T12:54:20.639587Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2509.01184"},"observation_digest":"sha256:f2377b3dc963c94967c1ff7de9a5924bda169aa6f1c758fabc81492be1c05a88","observation_id":"54a2f965-ce52-4df9-a471-27310673a4d6","resolution":{"observed_at":"2026-08-05T12:54:20.639587Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":"2108.04468","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-06-30T00:24:05.122539Z","title":"arXiv preprint arXiv:2108.04468(2021)","venue":null,"work_id":"01c79691-2a73-4ce2-9d21-c68702877449","year":2021},"citing_paper":{"arxiv_id":"2510.11066","last_updated":"2026-04-16T06:14:22Z","snapshot_observed_at":"2026-07-06T22:32:27.698678Z","submitted_at":"2025-10-13T07:06:26Z","title":"Decoupled Multimodal Fusion for User Interest Modeling in Click-Through Rate Prediction","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-18T08:09:48.310568Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2510.11066"},"observation_digest":"sha256:4fa6586812c22f14ff8a45e51cf71af3f89705b9709fd4b3b668a19c809d17c2","observation_id":"6cafd1bf-7335-435a-b782-f00c3333512b","resolution":{"observed_at":"2026-05-18T08:11:06.793738Z","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":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-08-03T04:15:14.584660Z","title":"arXiv preprint arXiv:2108.04468(2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.05663","last_updated":"2026-07-23T06:54:14Z","snapshot_observed_at":"2026-08-05T02:21:43.354379Z","submitted_at":"2026-02-05T13:48:33Z","title":"Coarse-to-Fine Long-term Interest Modeling for Generative Recommendation","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-03T04:15:14.584660Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2602.05663"},"observation_digest":"sha256:fba7e34ae314c5b1f0a63626000fadacc4e9ab2072e8823cf4adf88f44c74ec9","observation_id":"3543d52d-b09f-4eb2-b9c9-0a6f5aab73a4","resolution":{"observed_at":"2026-08-03T04:15:14.584660Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-08-02T23:22:46.994267Z","title":"arXiv preprint arXiv:2108.04468 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.14110","last_updated":"2026-07-02T03:27:35Z","snapshot_observed_at":"2026-08-07T15:33:08.491030Z","submitted_at":"2026-02-15T11:53:30Z","title":"MixFormer: Co-Scaling Up Dense and Sequence in Industrial Recommenders","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-02T23:22:46.994267Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2602.14110"},"observation_digest":"sha256:27abf360c3012eebfe809f989bb26b5f88fe503ce885a3981b4df751b388fc5d","observation_id":"d5a9be4a-d27d-4fa1-a33d-b34316e17992","resolution":{"observed_at":"2026-08-02T23:22:46.994267Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":"2108.04468","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-06-30T00:24:05.122539Z","title":"arXiv preprint arXiv:2108.04468(2021)","venue":null,"work_id":"01c79691-2a73-4ce2-9d21-c68702877449","year":2021},"citing_paper":{"arxiv_id":"2604.05314","last_updated":"2026-04-07T01:35:20Z","snapshot_observed_at":"2026-08-08T13:33:57.885923Z","submitted_at":"2026-04-07T01:35:20Z","title":"Next-Scale Generative Reranking: A Tree-based Generative Rerank Method at Meituan","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-10T19:55:30.019335Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2604.05314"},"observation_digest":"sha256:5840bf9d730976300812e9f19625ff15fd9c4deeb92a6885d0410478827311ed","observation_id":"0d6842ea-bdd6-45e8-b341-ee408928ba68","resolution":{"observed_at":"2026-05-10T22:20:49.338598Z","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":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":"2108.04468","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-06-30T00:24:05.122539Z","title":"arXiv preprint arXiv:2108.04468(2021)","venue":null,"work_id":"01c79691-2a73-4ce2-9d21-c68702877449","year":2021},"citing_paper":{"arxiv_id":"2604.12298","last_updated":"2026-04-14T05:14:05Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:14:05Z","title":"Deep Situation-Aware Interaction Network for Click-Through Rate Prediction","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-10T15:35:44.770946Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2604.12298"},"observation_digest":"sha256:90950e90233d55f12794780c18921b7d99517011cc57a90ce65e8314d9ebe9a1","observation_id":"cc88bc86-c77e-4639-b79a-30d6f8b4e293","resolution":{"observed_at":"2026-05-11T10:11:04.364938Z","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":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":"2108.04468","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-06-30T00:24:05.122539Z","title":"arXiv preprint arXiv:2108.04468(2021)","venue":null,"work_id":"01c79691-2a73-4ce2-9d21-c68702877449","year":2021},"citing_paper":{"arxiv_id":"2604.15650","last_updated":"2026-07-16T11:34:49Z","snapshot_observed_at":"2026-08-02T16:11:27.280878Z","submitted_at":"2026-04-17T02:47:31Z","title":"Sample Is Feature: Beyond Item-Level, Toward Sample-Level Tokens for Unified Large Recommender Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-10T08:16:26.087500Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2604.15650"},"observation_digest":"sha256:a232f026afe37304faa15ffdd390cf333d927c655f2636f4cfd9deb50a21060e","observation_id":"c90fe6b1-6289-4f74-9192-69430052885e","resolution":{"observed_at":"2026-05-10T08:17:37.071954Z","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":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":"2108.04468","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-06-30T00:24:05.122539Z","title":"arXiv preprint arXiv:2108.04468(2021)","venue":null,"work_id":"01c79691-2a73-4ce2-9d21-c68702877449","year":2021},"citing_paper":{"arxiv_id":"2604.15650","last_updated":"2026-07-16T11:34:49Z","snapshot_observed_at":"2026-08-02T16:11:27.280878Z","submitted_at":"2026-04-17T02:47:31Z","title":"Sample Is Feature: Beyond Item-Level, Toward Sample-Level Tokens for Unified Large Recommender Models","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-25T06:44:59.047526Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2604.15650"},"observation_digest":"sha256:6c3174c968f085ac290d2d5b9fce5733043532bc74bf88520f23bc91b290fb30","observation_id":"dc8ca78e-cee2-4da5-b889-1877ae448305","resolution":{"observed_at":"2026-05-25T06:45:25.696009Z","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":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-08-02T16:11:28.483675Z","title":"arXiv preprint arXiv:2108.04468(2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2604.15650","last_updated":"2026-07-16T11:34:49Z","snapshot_observed_at":"2026-08-02T16:11:27.280878Z","submitted_at":"2026-04-17T02:47:31Z","title":"Sample Is Feature: Beyond Item-Level, Toward Sample-Level Tokens for Unified Large Recommender Models","version":3},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:28.483675Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2604.15650"},"observation_digest":"sha256:9645cbd80c7ad4b058baae37cb5eb8f9a93f37733fa6302475769169ac809f2c","observation_id":"7b9f3f1d-a3d2-4811-af84-85036ff0ce67","resolution":{"observed_at":"2026-08-02T16:11:28.483675Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":"2108.04468","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-06-30T00:24:05.122539Z","title":"arXiv preprint arXiv:2108.04468(2021)","venue":null,"work_id":"01c79691-2a73-4ce2-9d21-c68702877449","year":2021},"citing_paper":{"arxiv_id":"2604.19269","last_updated":"2026-04-21T09:35:30Z","snapshot_observed_at":"2026-07-06T23:05:58.167533Z","submitted_at":"2026-04-21T09:35:30Z","title":"CS3: Efficient Online Capability Synergy for Two-Tower Recommendation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-10T02:16:58.617774Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2604.19269"},"observation_digest":"sha256:342d0d3e4b5cebf6605373dbc7efe443566ae10e12bad7fa6bdf55d20bd4849f","observation_id":"0b93a3c1-578e-410a-aa92-9fd97ed3dcc1","resolution":{"observed_at":"2026-05-11T13:11:03.573225Z","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":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":"2108.04468","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-06-30T00:24:05.122539Z","title":"arXiv preprint arXiv:2108.04468(2021)","venue":null,"work_id":"01c79691-2a73-4ce2-9d21-c68702877449","year":2021},"citing_paper":{"arxiv_id":"2604.23810","last_updated":"2026-04-26T17:18:02Z","snapshot_observed_at":"2026-07-06T23:09:58.193241Z","submitted_at":"2026-04-26T17:18:02Z","title":"Similar Users-Augmented Interest Network","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-08T05:16:51.731038Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2604.23810"},"observation_digest":"sha256:7dfb6014d68574eb2ad101a79a6a261617631233b8df0047bbb78873d2866cd5","observation_id":"823fbd66-d630-4467-9f68-501c9e0460fb","resolution":{"observed_at":"2026-05-11T21:31:15.293118Z","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":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":"2108.04468","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-06-30T00:24:05.122539Z","title":"arXiv preprint arXiv:2108.04468(2021)","venue":null,"work_id":"01c79691-2a73-4ce2-9d21-c68702877449","year":2021},"citing_paper":{"arxiv_id":"2604.24806","last_updated":"2026-06-10T23:46:17Z","snapshot_observed_at":"2026-08-02T11:43:55.030778Z","submitted_at":"2026-04-27T06:41:39Z","title":"Versioned Late Materialization for Ultra-Long Sequence Training in Recommendation Systems at Scale","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-08T02:02:49.319567Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2604.24806"},"observation_digest":"sha256:56d7829db72160882f0ded318cc6688ad534f185c74bdefb80b45e25e7be65a3","observation_id":"85004598-c44e-4c91-bc23-553e1ca9dd5f","resolution":{"observed_at":"2026-05-11T23:01:15.089410Z","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":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":"2108.04468","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-06-30T00:24:05.122539Z","title":"arXiv preprint arXiv:2108.04468(2021)","venue":null,"work_id":"01c79691-2a73-4ce2-9d21-c68702877449","year":2021},"citing_paper":{"arxiv_id":"2605.09040","last_updated":"2026-05-18T07:00:17Z","snapshot_observed_at":"2026-07-06T23:21:11.475005Z","submitted_at":"2026-05-09T16:26:48Z","title":"UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-12T01:51:47.215030Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2605.09040"},"observation_digest":"sha256:bc9782d9a1f563c51737b871ff17dd43d136119d7d09c4bdc979a803635bd9fd","observation_id":"4c59516e-8bba-4ee6-946d-57c430ee210d","resolution":{"observed_at":"2026-05-12T07:46:51.562104Z","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":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":"2108.04468","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-06-30T00:24:05.122539Z","title":"arXiv preprint arXiv:2108.04468(2021)","venue":null,"work_id":"01c79691-2a73-4ce2-9d21-c68702877449","year":2021},"citing_paper":{"arxiv_id":"2605.09040","last_updated":"2026-05-18T07:00:17Z","snapshot_observed_at":"2026-07-06T23:21:11.475005Z","submitted_at":"2026-05-09T16:26:48Z","title":"UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-14T21:04:43.102584Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2605.09040"},"observation_digest":"sha256:ce46643db2b9a74450cb28107496996542fed9256323a8b72e33609afee6d133","observation_id":"9f366dc7-3683-46ea-9b6e-09ad04dac7dd","resolution":{"observed_at":"2026-05-14T21:19:28.784665Z","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":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":"2108.04468","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-06-30T00:24:05.122539Z","title":"arXiv preprint arXiv:2108.04468(2021)","venue":null,"work_id":"01c79691-2a73-4ce2-9d21-c68702877449","year":2021},"citing_paper":{"arxiv_id":"2605.09040","last_updated":"2026-05-18T07:00:17Z","snapshot_observed_at":"2026-07-06T23:21:11.475005Z","submitted_at":"2026-05-09T16:26:48Z","title":"UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-20T22:27:34.442931Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2605.09040"},"observation_digest":"sha256:b7f7809617424e1d67327dad64d1431290dd397c88c467531fe74593d5f9db54","observation_id":"62ae54bd-4c7f-47d7-87d1-e992eba93116","resolution":{"observed_at":"2026-05-20T22:29:09.124495Z","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":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":"2108.04468","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-06-30T00:24:05.122539Z","title":"arXiv preprint arXiv:2108.04468(2021)","venue":null,"work_id":"01c79691-2a73-4ce2-9d21-c68702877449","year":2021},"citing_paper":{"arxiv_id":"2605.15905","last_updated":"2026-05-15T12:42:54Z","snapshot_observed_at":"2026-08-01T01:47:15.183830Z","submitted_at":"2026-05-15T12:42:54Z","title":"Generative Long-term User Interest Modeling for Click-Through Rate Prediction","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-19T22:19:59.483142Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2605.15905"},"observation_digest":"sha256:6b40c1ef8b0d02bd90e8217e8ed6a2396e6bbee4a814459ce1847af19e3b1d56","observation_id":"00292a81-bf21-4055-a10b-d155066e6292","resolution":{"observed_at":"2026-05-19T22:22:49.422962Z","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":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":"2108.04468","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-06-30T00:24:05.122539Z","title":"arXiv preprint arXiv:2108.04468(2021)","venue":null,"work_id":"01c79691-2a73-4ce2-9d21-c68702877449","year":2021},"citing_paper":{"arxiv_id":"2605.25583","last_updated":"2026-06-11T02:35:04Z","snapshot_observed_at":"2026-08-07T04:29:35.559179Z","submitted_at":"2026-05-25T08:33:11Z","title":"LENS: A Staged Design for Interaction Granularity in Sequential CTR Prediction","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-29T20:43:03.477109Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2605.25583"},"observation_digest":"sha256:e886c6903c051fea0e0eeed0203d7915701b608f3be1284ccd99de4f9b769c3a","observation_id":"5b2fa5b7-a6ae-49cb-86d1-c465122c6a9a","resolution":{"observed_at":"2026-06-29T20:43:58.738881Z","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":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":"2108.04468","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-06-30T00:24:05.122539Z","title":"arXiv preprint arXiv:2108.04468(2021)","venue":null,"work_id":"01c79691-2a73-4ce2-9d21-c68702877449","year":2021},"citing_paper":{"arxiv_id":"2605.25726","last_updated":"2026-05-25T11:33:27Z","snapshot_observed_at":"2026-08-03T08:30:33.680262Z","submitted_at":"2026-05-25T11:33:27Z","title":"SIREN: Unified Multi-Granularity Semantic Interaction for Multi-Modal Lifelong User Interest Modeling","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-29T20:20:28.690751Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2605.25726"},"observation_digest":"sha256:53d907008cf8fd222a56323e0440e58681637b4131289b633f23767d7afa65e5","observation_id":"680aa805-eca2-4e47-bc8f-dd3028345e78","resolution":{"observed_at":"2026-06-30T00:24:05.123759Z","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":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-07-31T22:39:50.040235Z","title":"End-to-end user behavior retrieval in click-through rateprediction model.arXiv preprint arXiv:2108.04468, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.27944","last_updated":"2026-07-30T09:52:18Z","snapshot_observed_at":"2026-08-06T09:27:54.547816Z","submitted_at":"2026-07-30T09:52:18Z","title":"Interpretable Representation via LLM-Driven Generative Disentanglement for Local-Life Service Recommendation","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-07-31T22:39:50.040235Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2607.27944"},"observation_digest":"sha256:0cbffd6e00d89903d9c4bce06587a40635fa5967b4ffd46bb04e880c5539e320","observation_id":"71028136-a383-4e37-a7b7-58d7fd6fb468","resolution":{"observed_at":"2026-07-31T22:39:50.040235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04468","snapshot_observed_at":"2026-08-05T14:42:08.281081Z","title":"arXiv preprint arXiv:2108.04468(2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.03692","last_updated":"2026-08-04T13:59:44Z","snapshot_observed_at":"2026-08-08T17:47:06.665965Z","submitted_at":"2026-08-04T13:59:44Z","title":"SITA: Semantic Interest Tokens for Target-Aware Compression in Long-Sequence Recommendation","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-05T14:42:08.281081Z"},"links":{"cited_paper":"/paper/2108.04468","citing_paper":"/paper/2608.03692"},"observation_digest":"sha256:5b288ea36f89adff475f8c2a3242f41c6901fe5f68054fd26775c41c77353b80","observation_id":"a43d59e8-4c9d-4a6e-a846-bd1d6d916809","resolution":{"observed_at":"2026-08-05T14:42:08.281081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2108.04468/citation-record","integrity":"/paper/2108.04468/integrity","json":"/paper/2108.04468/citation-record.json","paper":"/paper/2108.04468"},"outbound":[],"paper":{"arxiv_id":"2108.04468","last_updated":"2021-08-10T06:28:29Z","latest_version":1,"primary_category":"cs.IR","snapshot_observed_at":"2026-08-05T17:19:23.533620Z","submitted_at":"2021-08-10T06:28:29Z","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model"},"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 31 inbound Pith citation observations for arXiv:2108.04468."}