{"as_of":"2026-08-21T17:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:aa06dffc32e8823bec6e252b1cfbb8f678e71a51c1d75f3bab066c285b216117","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T12:05:19.641588Z","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":"2026-08-21T06:32:19.484+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/2504.13993/citation-record","integrity":"/paper/2504.13993/integrity","json":"/paper/2504.13993/citation-record.json","paper":"/paper/2504.13993"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.10403","last_updated":"2023-09-13T20:35:45Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-17T17:46:53Z","title":"PaLM 2 Technical Report","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.10403","snapshot_observed_at":"2026-08-16T12:05:19.503590Z","title":"Palm 2 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.503590Z"},"links":{"cited_paper":"/paper/2305.10403","citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:4c7cfc03022adab10e3c27075c1759c1e26a14026df05dba1e42e65848081690","observation_id":"4766ee3e-aebb-45cb-9cca-e176070e4b11","resolution":{"observed_at":"2026-08-16T12:05:19.503590Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:20.118639Z","title":"Graph of thoughts: Solving elaborate problems with large language models","venue":null,"work_id":"a635d4d7-a84c-4eb1-b4a2-2f1bfee54647","year":2024},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.511988Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:7e65692a313e72ae0bb82757ea16a801572021f6708c3581004bacff97fae77f","observation_id":"9a592711-a094-4e70-96ac-9041c8324f74","resolution":{"observed_at":"2026-08-16T12:05:20.123292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:20.103901Z","title":"Walmart.com","venue":null,"work_id":"88937f6b-b3a1-4c52-9dea-60917f36269e","year":2024},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.516641Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:ad8ef020d24f8efd482b4ac108d6c681392259b17986b67e8d5a2526217f2fb1","observation_id":"781c8f98-57d4-4692-a1f6-6eefa0c1e653","resolution":{"observed_at":"2026-08-16T12:05:20.108576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:20.088852Z","title":"Yake! keyword extraction from single documents using multiple local features","venue":null,"work_id":"a2a46a61-b26e-4d75-8b96-387ef2d55baf","year":2020},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.521508Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:bca0c6e01594b2b7529d6a717a85df901916a6de335088e5d7fc87b2bdd27c55","observation_id":"eadae1d7-25d9-4d06-8c5f-4963c23a5d49","resolution":{"observed_at":"2026-08-16T12:05:20.093529Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:20.074361Z","title":"Complementing human effort in online reviews: A deep learning approach to automatic content generation and review synthesis","venue":null,"work_id":"f5e49dd0-f0fe-4092-80ca-68c55ace9ab5","year":2023},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.526080Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:1a94c9ffec19de75dde2764d746a28091406433abf74b7987c94ebe38b0890d8","observation_id":"1f946053-6c33-4915-a54e-5d2fb928e115","resolution":{"observed_at":"2026-08-16T12:05:20.078930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.14799","last_updated":"2021-05-18T07:04:41Z","snapshot_observed_at":"2026-08-13T22:18:30.189974Z","submitted_at":"2020-06-26T04:52:48Z","title":"Evaluation of Text Generation: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.14799","snapshot_observed_at":"2026-08-16T12:05:19.530785Z","title":"Evaluation of text generation: A survey","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.530785Z"},"links":{"cited_paper":"/paper/2006.14799","citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:7a3837ba12e96c43764252139ca6349b34a377d1467c89ab62a81034e3431388","observation_id":"148fe247-26c9-4a6d-b98c-8aa92bdfcc2f","resolution":{"observed_at":"2026-08-16T12:05:19.530785Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:20.059523Z","title":"Attribute sentiment scoring with online text reviews: Accounting for language structure and missing attributes","venue":null,"work_id":"f93a591a-22e5-4ac6-9092-10309d95fe3a","year":2022},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.536135Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:d47b03d9d455f011f1dddeed0f49df58d28b6dc979dc4ab0bc015dfe38038fdb","observation_id":"e1e7f9ea-5570-4273-a569-a6f9c8e129ca","resolution":{"observed_at":"2026-08-16T12:05:20.064322Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:20.044686Z","title":"Channels of impact: User reviews when quality is dynamic and managers respond","venue":null,"work_id":"7d0ac9f1-001a-4120-8b23-4a9126291528","year":2018},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.540173Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:3744e7ec6d9dfa1a153a822ac8325de0ca8b03ea260f1dad121f47c6f43ad781","observation_id":"bddccf86-040f-45ce-a0a9-70048a90c793","resolution":{"observed_at":"2026-08-16T12:05:20.049799Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:20.029560Z","title":"The effects of online user reviews on movie box office performance: Accounting for sequential rollout and aggregation across local markets","venue":null,"work_id":"0042396f-5e18-46f8-b7fc-543051bf1eed","year":2010},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.544538Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:6ac8bd3a0cab1c44a5215709405eb148c883479b7a07c3d54f2691936f43c59e","observation_id":"c5ed5a96-142e-4daf-b4bc-51dbffbb8f86","resolution":{"observed_at":"2026-08-16T12:05:20.034594Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:19.548773Z","title":"Palm: Scaling language modeling with pathways","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.548773Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:01a24e26bd56353f0523209e953ea66eaadea9d0f4c48d1e6d5971cdc0acfc15","observation_id":"2ceb616f-a726-4d21-80ce-db6d2bda0b7a","resolution":{"observed_at":"2026-08-16T12:05:19.548773Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:20.002677Z","title":"Auto- matic generation of natural language explanations","venue":null,"work_id":"e98efd56-831a-48ef-b2c5-62ec4ddc67c6","year":2018},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.552931Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:cf9cf62f2e1a1a56d851a795991546a52f96e97e633183be77a4d030d3bc1dc7","observation_id":"575c7492-18b7-4d9d-8dab-3bacf295b0d3","resolution":{"observed_at":"2026-08-16T12:05:20.007975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:19.986424Z","title":"Prompt engineering for chatgpt: a quick guide to techniques, tips, and best practices","venue":null,"work_id":"80a5f420-b3a5-48e5-8c90-e2179371951e","year":2023},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.557295Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:4ad7be852e3546a46577bc36e96ca553170b4580027f376ceb5e8678a98eb618","observation_id":"a9735d02-ede4-48ad-bac9-de6d23fba9b5","resolution":{"observed_at":"2026-08-16T12:05:19.991708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:19.970867Z","title":"Automatic generation of product-image sequence in e-commerce","venue":null,"work_id":"247b1cf9-8324-47ac-ae57-f285cca5787d","year":2022},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.561738Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:21989dd89f543d7fd4027673b6330601d2fb0745c36beb07ee12bd1e5456bab8","observation_id":"4d13f3ae-9c7c-4d4a-af92-9b4c7e7aebe3","resolution":{"observed_at":"2026-08-16T12:05:19.975704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:19.954492Z","title":"Conditional text generation for harmonious human- machine interaction","venue":null,"work_id":"c9f23bd8-8f52-455b-bc8a-a9308fce1431","year":2021},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.566013Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:c435d7d35a36f90ccfac0519b4132f8ce97bbdaa9f8c8d8945faa8a45fdbac4c","observation_id":"6f9bd7fa-01e4-4327-a09e-9eed477eed72","resolution":{"observed_at":"2026-08-16T12:05:19.959630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-20T11:47:17.477107Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-16T12:05:19.570383Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.570383Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:efd491e8c01b0d4c2b22acfc460a3e14396a32f15315c01b9d6e5c7c09ef67c6","observation_id":"3872ac65-78f9-4807-b077-22b77c85c5e3","resolution":{"observed_at":"2026-08-16T12:05:19.570383Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:19.939252Z","title":"Proceedings of the 57th annual meeting of the association for computational linguistics","venue":null,"work_id":"11d70217-e04f-4572-b4f4-939e78b1afc5","year":2019},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.575069Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:47d67ee24dad106754940f3b88988b6ab9e96a3d1b12b7f5dfa6a03496f0353c","observation_id":"e1277ffa-0470-4fec-902a-51f50fe9c95a","resolution":{"observed_at":"2026-08-16T12:05:19.943945Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:19.923733Z","title":"Evaluating the output of machine translation systems","venue":null,"work_id":"ce5130ba-b0ca-472e-b767-5e41d7375fba","year":2011},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.579362Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:2358b7c66f526a45f8c4b8a50a42bae8bdbc8b313681478fbc283e6349bac13d","observation_id":"46360d61-b118-4066-ac8d-c24bdf20be66","resolution":{"observed_at":"2026-08-16T12:05:19.929056Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.03829","last_updated":"2022-04-01T15:01:53Z","snapshot_observed_at":"2026-08-16T17:22:50.654935Z","submitted_at":"2022-02-08T12:47:38Z","title":"TimeLMs: Diachronic Language Models from Twitter","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.03829","snapshot_observed_at":"2026-08-16T12:05:19.583559Z","title":"Timelms: Diachronic language models from twitter","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.583559Z"},"links":{"cited_paper":"/paper/2202.03829","citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:3496ec4fd13245ab06678b589536f68c607831fc3a79a855671d01f3b9910462","observation_id":"279cf7a6-75cd-44ba-ab51-aae98c142f07","resolution":{"observed_at":"2026-08-16T12:05:19.583559Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:19.908806Z","title":"More than words: The influence of affective content and linguistic style matches in online reviews on conversion rates","venue":null,"work_id":"e3483ed6-e6f0-4daf-8c73-1cc96ef3c693","year":2013},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.588641Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:e344a3f2995033b49d7cd44234adbf5eb0524c90652b1bc529ed1de57f3e2b02","observation_id":"c6d3c5e5-1984-4564-b447-a33fc4fed2b4","resolution":{"observed_at":"2026-08-16T12:05:19.913704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:19.592777Z","title":"Peft: State-of-the-art parameter- efficient fine-tuning methods","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.592777Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:6d2a6b1cffa6d86c6f00a3b4a40eff224e9e9f6e752871ba2d43393df0d6ea8e","observation_id":"1e1926e3-814b-4422-8272-c8085da4bbe9","resolution":{"observed_at":"2026-08-16T12:05:19.592777Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:19.884763Z","title":"Federal trade commission announces final rule banning fake reviews and testimonials","venue":null,"work_id":"1175fd43-f48e-41c7-bf2c-e785295b9ff2","year":2024},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.597023Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:6138475916450dc9bd219e30b26e8f249f9652367f40e3f3fbe64859caa5e0b3","observation_id":"e7a38a23-85ce-4547-b8b4-b0229046a1f2","resolution":{"observed_at":"2026-08-16T12:05:19.889595Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:19.601470Z","title":"Bleu: a method for automatic evaluation of machine translation","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.601470Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:65d18474104a1d89abb7abbda25f1364a9e2a96c5e9f3ee49e0612af394c78f9","observation_id":"596cbbad-e958-444a-884c-cc502240ccec","resolution":{"observed_at":"2026-08-16T12:05:19.601470Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:19.859732Z","title":"Efficiency of automatic text generators for online review content gener- ation","venue":null,"work_id":"c19afe0c-6002-4880-8553-ba159952b966","year":2023},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.605608Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:daba15582cdd763bcd805ddb005c389b537d65573b2a4980406505c420a094e6","observation_id":"fcae1b46-65ca-40f1-af53-54e3402b06fb","resolution":{"observed_at":"2026-08-16T12:05:19.864624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02745","last_updated":"2016-09-09T11:16:15Z","snapshot_observed_at":"2026-08-21T07:01:19.802070Z","submitted_at":"2016-09-09T11:16:15Z","title":"A Hierarchical Model of Reviews for Aspect-based Sentiment Analysis","version":1},"cited_work":{"arxiv_id":"1609.02745","doi":null,"metadata_source":"pith","pith_arxiv_id":"1609.02745","snapshot_observed_at":"2026-08-16T12:05:19.706365Z","title":"A Hierarchical Model of Reviews for Aspect-based Sentiment Analysis","venue":"cs.CL","work_id":"142517a0-70f7-47f3-8b5f-7593cc8b233b","year":2016},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.609747Z"},"links":{"cited_paper":"/paper/1609.02745","citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:f93512f4a2328377743c4a45e4041af931e2257495fa42e05a9d7ab0fc2a8e40","observation_id":"8e6450c8-252d-4865-8a26-86c0e6f2964c","resolution":{"observed_at":"2026-08-16T12:05:19.713490Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17533","last_updated":"2024-05-27T17:50:25Z","snapshot_observed_at":"2026-08-21T07:01:13.087145Z","submitted_at":"2024-05-27T17:50:25Z","title":"PAE: LLM-based Product Attribute Extraction for E-Commerce Fashion Trends","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17533","snapshot_observed_at":"2026-08-16T12:05:19.614898Z","title":"Pae: Llm-based product attribute extrac- tion for e-commerce fashion trends","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.614898Z"},"links":{"cited_paper":"/paper/2405.17533","citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:e5f1260e13fd220336505169746f99390d79041326d63ef4ca4c43bb942daf14","observation_id":"d668ee45-5dc7-4f49-ab3d-29d2ead1f03a","resolution":{"observed_at":"2026-08-16T12:05:19.614898Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:19.843234Z","title":"Automatic generation of review content in specific domain of social network based on rnn","venue":null,"work_id":"b0da38e6-4fd6-4d4f-a332-42fdc79eb462","year":2018},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.619601Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:69c915f4471de44d5af79138da83c213897a2fe3129ce657de74cdb79e416fdc","observation_id":"f680efef-9c1d-43d4-89c8-9ef6098af2ee","resolution":{"observed_at":"2026-08-16T12:05:19.847777Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-16T12:05:19.623797Z","title":"Llama 2: Open foundation and fine- tuned chat models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.623797Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:6a3297e6e330a916ca947ebaa2855d21eb44ba8371a036193385e5456b2f6850","observation_id":"25301e08-a503-42a8-a43f-244a0660b79b","resolution":{"observed_at":"2026-08-16T12:05:19.623797Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:19.828591Z","title":"Text generation and recall by high-knowledge and low-knowledge individuals","venue":null,"work_id":"af695a25-415d-4dcb-9cd6-1c9490e45831","year":1980},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.628616Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:b04e8cb85425c6ccf007aabba42d4a604f8991a7c403b2cf0416710fa56aa261","observation_id":"2c1f5cad-0dd9-46f4-ac9d-b1cdea6a94a7","resolution":{"observed_at":"2026-08-16T12:05:19.833111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:19.813615Z","title":"Personalized showcases: Generating multi-modal explanations for rec- ommendations","venue":null,"work_id":"3d0ca225-992d-43da-ba69-0686e66eaf22","year":2023},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.632723Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:14d14cf48996735fc09dd9722727e187034a7ce321bca3811fd9bfbdd60f3cdf","observation_id":"450a6d51-fc26-447e-88d6-d96eef7a2a27","resolution":{"observed_at":"2026-08-16T12:05:19.818589Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:19.798343Z","title":"Towards automatic generation of product reviews from aspect-sentiment scores","venue":null,"work_id":"551a2ff1-fadb-40e6-b25e-363e25b99750","year":2017},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.637005Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:7abefafea01669824fbaeafe1080c2e06067e3745064abe844a5f51348df4de3","observation_id":"7b47ee4f-353e-4142-8495-4bf052ed5b89","resolution":{"observed_at":"2026-08-16T12:05:19.803330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:05:19.783325Z","title":"Review response generation in e-commerce platforms with external product information","venue":null,"work_id":"a9bc7b7a-46ec-46d6-9ae6-9f48e05c4001","year":2019},"citing_paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T12:05:19.641588Z"},"links":{"citing_paper":"/paper/2504.13993"},"observation_digest":"sha256:400df2c24a5cf652cd91bbe23392a165522a43f41a83a6bdfe4776c24e2eebed","observation_id":"edaaf299-98fd-4e14-8450-a362cf35f8bc","resolution":{"observed_at":"2026-08-16T12:05:19.788358Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2504.13993","last_updated":"2025-04-18T17:11:38Z","latest_version":1,"primary_category":"cs.IR","snapshot_observed_at":"2026-08-21T07:55:36.903089Z","submitted_at":"2025-04-18T17:11:38Z","title":"CPR: Leveraging LLMs for Topic and Phrase Suggestion to Facilitate Comprehensive Product Reviews"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":1,"verified_fuzzy":21},"total_outbound_references":31},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2504.13993."}