{"as_of":"2026-08-15T23:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:455f852d538d4556d4004bbc517ec9460285e122f663a1155c600a95ad4657ed","coverage":[{"denominator":77,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":77,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T20:34:34.911397Z","state":"measured"},{"denominator":77,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":77,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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/2501.08262/citation-record","integrity":"/paper/2501.08262/integrity","json":"/paper/2501.08262/citation-record.json","paper":"/paper/2501.08262"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T20:34:34.621361Z","title":"The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.621361Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:fbc4e71b0fae21d82f447394ca09a4fede91a1b3cf0c0718117d04378b66d4d5","observation_id":"6ed12767-4a90-43ab-9bb2-984b9e06106e","resolution":{"observed_at":"2026-08-10T20:34:34.621361Z","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":"2026-08-10T20:34:34.625590Z","title":"Reducing the Carbon Impact of Generative AI Inference (today and in 2035)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.625590Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:28e4b7db91dedfb67d31d4ab340ad1b1c0a30ca9c6759fea24a5a8984d3f93b0","observation_id":"ca2290f3-1c42-46f5-9d3d-fb8f3af78052","resolution":{"observed_at":"2026-08-10T20:34:34.625590Z","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":"2026-08-10T20:34:34.630333Z","title":"Trends in AI inference energy consumption: Beyond the performance-vs-parameter laws of deep learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.630333Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:8748da350a682620c35ade84c93d331ab8acd208cf00726f89a82169f6da52fd","observation_id":"011a6cb6-1e65-4b12-8c33-fc1c3db98fe7","resolution":{"observed_at":"2026-08-10T20:34:34.630333Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-10T20:34:34.634269Z","title":"Preventing the Immense Increase in the Life-Cycle Energy and Carbon Footprints of LLM-Powered Intelligent Chatbots","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.634269Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:77241ba366d9752cd2263128561a6e475b77f4c1dc7b1e400e51f140febf6509","observation_id":"7edea65b-059d-4aed-854a-6736ceba052b","resolution":{"observed_at":"2026-08-10T20:34:34.634269Z","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":"2026-08-10T20:34:36.416618Z","title":"Triple Bottom Line or Trilemma? Global Tradeoffs Between Prosperity, Inequality, and the Environment","venue":null,"work_id":"a1462e9d-01bc-4a2d-b883-09cb1ca05bea","year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.637938Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:3ca5363e489c27cfd0ed61b779c64879bde17f49f07bb489ba6aae815a4ee66f","observation_id":"19fe13b7-9433-4a43-ad10-0f637d91a288","resolution":{"observed_at":"2026-08-10T20:34:36.420772Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.07864","last_updated":"2023-09-19T08:29:18Z","snapshot_observed_at":"2026-08-09T18:54:02.679174Z","submitted_at":"2023-09-14T17:12:03Z","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.07864","snapshot_observed_at":"2026-08-10T20:34:34.641653Z","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.641653Z"},"links":{"cited_paper":"/paper/2309.07864","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:e8c7e2af81a7a6d20482d7289b69025e439af9be3abef50fbb61ae5a2c5cf3a7","observation_id":"7ba5b097-9ce5-4921-8d0c-d1990246752e","resolution":{"observed_at":"2026-08-10T20:34:34.641653Z","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":"10.1007/s12559-024-10285-1","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T20:34:35.006090Z","title":"Chatgpt needs spade (sustainability, privacy, digital divide, and ethics) evaluation: A review","venue":null,"work_id":"e018aaf4-f3dc-448d-b891-3db0a6702771","year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.645771Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:a88093d907ec63fd111833e0f795b6a0c94a98a6554fc385eb2d9cc56c7fb870","observation_id":"14d19b36-4885-4d1e-8d3a-265de0012fac","resolution":{"observed_at":"2026-08-10T20:34:35.012108Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.14393","last_updated":"2024-01-19T17:33:44Z","snapshot_observed_at":"2026-08-13T10:05:28.717609Z","submitted_at":"2023-09-25T14:50:04Z","title":"LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.14393","snapshot_observed_at":"2026-08-10T20:34:34.649220Z","title":"LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.649220Z"},"links":{"cited_paper":"/paper/2309.14393","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:c65e08d39c05fa8b760e1292001a7ae8ec3255cbfc4c2e54a9ef9f8f939f19b0","observation_id":"b6552209-cf6c-4d1f-b669-10733f97f800","resolution":{"observed_at":"2026-08-10T20:34:34.649220Z","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":"2022.88656","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T20:34:35.910624Z","title":"The AI trilemma: Saving the planet without ruining our jobs","venue":null,"work_id":"eeb9409d-b756-46b1-bbac-ceff250257bd","year":2022},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.652469Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:a1997d42523a6c6b2c1801224004621d052b5901eff319edff61280b4fd82da7","observation_id":"1ffc9da0-9f56-428b-90d5-6c519176bc0a","resolution":{"observed_at":"2026-08-10T20:34:35.916770Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T20:34:36.406211Z","title":"Challenging AI for Sustainability: what ought it mean?","venue":null,"work_id":"fef68e97-3aae-4b6f-80ab-2a5260cff2e2","year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.655180Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:7dd45b3b436515af06c409aaa83c0ea698d803073cd8bed84637122e63d3646c","observation_id":"e652d45e-13c3-4bdb-ae9a-38827231715e","resolution":{"observed_at":"2026-08-10T20:34:36.409621Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T20:34:34.658207Z","title":"Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challenges","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.658207Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:57aa05648c241f110c815a54026e6682243d6d91e9d1fcade3d0ed0c00704b5f","observation_id":"d45719d6-90a4-4cda-8799-b20ea6ff6dac","resolution":{"observed_at":"2026-08-10T20:34:34.658207Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.09700","last_updated":"2019-11-04T20:37:33Z","snapshot_observed_at":"2026-08-13T09:44:21.186377Z","submitted_at":"2019-10-21T23:57:32Z","title":"Quantifying the Carbon Emissions of Machine Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.09700","snapshot_observed_at":"2026-08-10T20:34:34.661206Z","title":"Quantifying the Carbon Emissions of Machine Learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.661206Z"},"links":{"cited_paper":"/paper/1910.09700","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:c212770d0525a6d9d29561ce845b8e4c8be068c0518c9c3c6ba7bcd5948bf2ca","observation_id":"319e6b5c-7cf6-45fe-8cd6-cf64e0cbba4d","resolution":{"observed_at":"2026-08-10T20:34:34.661206Z","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":"2026-08-10T20:34:34.665494Z","title":"Green Algorithms: Quantifying the Carbon Footprint of Computation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.665494Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:67269ee913a2593a82de3e355abe66e19ef949a7dd15952f42cf546e445b042a","observation_id":"8a1a432f-07dc-46df-8e8c-3ee40ab29b97","resolution":{"observed_at":"2026-08-10T20:34:34.665494Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-10T20:34:34.669228Z","title":"Agent design pattern catalogue: A collection of architectural patterns for foundation model based agents","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.669228Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:e6ee906022e8aca6703c6e08ae72809567a4c9633f7d9f2d180ed1aadf79c4b3","observation_id":"5f9059a6-b6dc-4c5b-b5a1-a8fb48a61534","resolution":{"observed_at":"2026-08-10T20:34:34.669228Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-10T20:34:36.396466Z","title":"Enabling Efficient Serverless Inference Serving for LLM (Large Language Model) in the Cloud","venue":null,"work_id":"ce40bc89-dfaa-4731-9c9f-6297aac08e70","year":null},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.672628Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:941a22ac3e6ef1059bd513862aa72f1b4d317a7fe642dc5f23492c996ee95e67","observation_id":"2e25e6ac-5d25-4451-beef-1c61fed7e9a6","resolution":{"observed_at":"2026-08-10T20:34:36.400061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T20:34:34.680053Z","title":"A Joint Study of the Challenges, Opportunities, and Roadmap of MLOps and AIOps: A Systematic Survey","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.680053Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:b0b5e968a5103c5eefabe65ce1422fa8d1bed162cbb6f2c1110b67a8730a9709","observation_id":"ed6c69bb-db38-46c4-91f5-aef296d3cb50","resolution":{"observed_at":"2026-08-10T20:34:34.680053Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.22282","last_updated":"2024-11-02T18:45:22Z","snapshot_observed_at":"2026-08-12T22:12:32.998205Z","submitted_at":"2024-10-29T17:35:46Z","title":"Whose ChatGPT? Unveiling Real-World Educational Inequalities Introduced by Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.22282","snapshot_observed_at":"2026-08-10T20:34:34.683556Z","title":"Whose ChatGPT? Unveiling Real-World Educational Inequalities Introduced by Large Language Models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.683556Z"},"links":{"cited_paper":"/paper/2410.22282","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:59a0a5554510d9cfcef29236120974a961581ce3a1f22563d41f3c15463b3763","observation_id":"f459a632-c227-4b75-82e1-e2c6f1df7f15","resolution":{"observed_at":"2026-08-10T20:34:34.683556Z","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":"2026-08-10T20:34:36.385452Z","title":"Examining Potential Harms of Large Language Models (LLMs) in Africa","venue":null,"work_id":"7a4adedb-2371-4939-a043-a18515b4a350","year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.687462Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:befd30c6e84d083d5cba57c29d484ad93fcb4acd415d14e6cdc5936274784d95","observation_id":"023a573b-e228-40d1-9881-d9e180609e6f","resolution":{"observed_at":"2026-08-10T20:34:36.389269Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.03428","last_updated":"2024-01-07T09:08:24Z","snapshot_observed_at":"2026-08-15T19:05:29.070600Z","submitted_at":"2024-01-07T09:08:24Z","title":"Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.03428","snapshot_observed_at":"2026-08-10T20:34:34.690768Z","title":"Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.690768Z"},"links":{"cited_paper":"/paper/2401.03428","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:573a43e5212e346dc4c99845aeb3a8faac2c89295b6deaf21629992442a67849","observation_id":"c7723032-aacd-4e16-96aa-d6d4b07ffa1b","resolution":{"observed_at":"2026-08-10T20:34:34.690768Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.02716","last_updated":"2024-02-05T04:25:24Z","snapshot_observed_at":"2026-08-15T04:53:46.192738Z","submitted_at":"2024-02-05T04:25:24Z","title":"Understanding the planning of LLM agents: A survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.02716","snapshot_observed_at":"2026-08-10T20:34:34.694621Z","title":"Understanding the planning of LLM agents: A survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.694621Z"},"links":{"cited_paper":"/paper/2402.02716","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:ac1f10f52545ac4668b88aa24c9873671b1a066e775fc5c2e33296aae86ad3c1","observation_id":"eac4d683-4ae5-4fa2-b4a2-8aace6d0e93e","resolution":{"observed_at":"2026-08-10T20:34:34.694621Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.18807","last_updated":"2024-09-24T14:08:11Z","snapshot_observed_at":"2026-08-15T17:19:04.938943Z","submitted_at":"2024-09-24T14:08:11Z","title":"LLM With Tools: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.18807","snapshot_observed_at":"2026-08-10T20:34:34.698760Z","title":"LLM With Tools: A Survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.698760Z"},"links":{"cited_paper":"/paper/2409.18807","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:dbd9247373d264600a46fb702e2a8c48b4c07df2a73516ea5d24912a97b24f31","observation_id":"83724ea0-398c-42cc-9b48-da4dc9574b44","resolution":{"observed_at":"2026-08-10T20:34:34.698760Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.14924","last_updated":"2024-09-23T11:20:20Z","snapshot_observed_at":"2026-08-13T05:59:29.635188Z","submitted_at":"2024-09-23T11:20:20Z","title":"Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.14924","snapshot_observed_at":"2026-08-10T20:34:34.702629Z","title":"Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.702629Z"},"links":{"cited_paper":"/paper/2409.14924","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:532215e0ec9642ef719a265194b402c63219103cf614eefb5081dd57c071d7c3","observation_id":"6693c21f-3d3a-41e2-a69e-eb024695a232","resolution":{"observed_at":"2026-08-10T20:34:34.702629Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.13501","last_updated":"2024-04-21T01:49:46Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-04-21T01:49:46Z","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.13501","snapshot_observed_at":"2026-08-10T20:34:34.705882Z","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.705882Z"},"links":{"cited_paper":"/paper/2404.13501","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:fafdfc8e18ee55a4294a22625e5ce91c995bdaede943579664342f41aea14e78","observation_id":"bf861335-b5ec-4ecd-a815-82274d853c66","resolution":{"observed_at":"2026-08-10T20:34:34.705882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.01219","last_updated":"2025-09-14T09:34:46Z","snapshot_observed_at":"2026-07-06T16:13:46.112815Z","submitted_at":"2023-09-03T16:56:48Z","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.01219","snapshot_observed_at":"2026-08-10T20:34:34.708982Z","title":"Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.708982Z"},"links":{"cited_paper":"/paper/2309.01219","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:5a859fad385fc1901310869b10e4a699d043d26b697d2cb6f208d43bc0bd437e","observation_id":"6662d97c-a6f1-472d-97f4-e9dc6bb259ac","resolution":{"observed_at":"2026-08-10T20:34:34.708982Z","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":"2026-08-10T20:34:34.711948Z","title":"Sustainable LLM Serving: Environmental Implications, Challenges, and Opportunities : Invited Paper","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.711948Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:07bdc8004c416400cb9eec9cc75239dfa1bd9e074294587b224eb5cfb51aef18","observation_id":"7facd701-2489-4c38-bc75-a9fb2a5bad99","resolution":{"observed_at":"2026-08-10T20:34:34.711948Z","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":"2026-08-10T20:34:34.715419Z","title":"From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.715419Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:3146e6e6785cca4355b9a637d4b3c742f539b9e390c16ec3c0b93faa2740367d","observation_id":"0b754b13-5850-414c-87e2-584e39d26df4","resolution":{"observed_at":"2026-08-10T20:34:34.715419Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.04014","last_updated":"2024-07-04T15:45:15Z","snapshot_observed_at":"2026-08-15T19:59:35.719724Z","submitted_at":"2024-07-04T15:45:15Z","title":"Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous Systems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.04014","snapshot_observed_at":"2026-08-10T20:34:34.718781Z","title":"Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous Systems","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.718781Z"},"links":{"cited_paper":"/paper/2407.04014","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:c7820066c478659c98963c091029f5eeaeb22a8f66da556365d0ed4221aaf87a","observation_id":"02a7ef6e-46bd-4a94-8d3d-676a8578f343","resolution":{"observed_at":"2026-08-10T20:34:34.718781Z","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":"2026-08-10T20:34:34.722856Z","title":"Measuring and Improving the Energy Efficiency of Large Language Models Inference","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.722856Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:cdb496547d190516acd35121ea98e6078c8b7bfc64ecbf7b29397dfd166129a8","observation_id":"58097b39-4cb8-4fad-b877-01bc82b3f42a","resolution":{"observed_at":"2026-08-10T20:34:34.722856Z","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":"2026-08-10T20:34:36.374663Z","title":"Learn to Code Sustainably: An Empirical Study on LLM-based Green Code Generation","venue":null,"work_id":"2c867658-423f-46c0-9d92-cd6d482191fd","year":null},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.727346Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:2d22e38256850b8b217d88112b201972878f067e0c9775b9a2264bf9e221b11a","observation_id":"c7d843b0-b7b6-439a-bc3c-b9f571a1fd68","resolution":{"observed_at":"2026-08-10T20:34:36.378378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2023.11726","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T20:34:35.416427Z","title":"Method and evaluations of the effective gain of artificial intelligence models for reducing CO2 emissions","venue":null,"work_id":"1f8cb905-e9b0-46e9-9a9e-b3d5e46ab9c3","year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.734988Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:fb21db02c1ca070c4b0dfe85435a10d802a3b3a7bf92828131e887239ac7bde1","observation_id":"0456b06f-189c-46b4-b374-77d67416a83e","resolution":{"observed_at":"2026-08-10T20:34:35.422218Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.03344","last_updated":"2024-03-05T22:12:01Z","snapshot_observed_at":"2026-08-13T04:02:40.023133Z","submitted_at":"2024-03-05T22:12:01Z","title":"Learn to Code Sustainably: An Empirical Study on LLM-based Green Code Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.03344","snapshot_observed_at":"2026-08-10T20:34:34.731016Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.731016Z"},"links":{"cited_paper":"/paper/2403.03344","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:40234aab040b7181e97505df74d95102235442e51edf72959e77708b10e46289","observation_id":"0bb65b9f-7f94-4bbc-a86e-864d26aea200","resolution":{"observed_at":"2026-08-10T20:34:34.731016Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.08239","last_updated":"2023-08-23T03:37:04Z","snapshot_observed_at":"2026-08-13T10:33:48.015350Z","submitted_at":"2023-08-16T09:15:18Z","title":"MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.08239","snapshot_observed_at":"2026-08-10T20:34:34.743662Z","title":"MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversa- tion","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.743662Z"},"links":{"cited_paper":"/paper/2308.08239","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:f30ccee7a8d0711a3b243d580cb59ada7b355ac01f04a6a9cd1f1e4dfe51416a","observation_id":"1bd1e971-b361-401e-a652-9668edd4b56d","resolution":{"observed_at":"2026-08-10T20:34:34.743662Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01763","last_updated":"2025-06-23T04:05:15Z","snapshot_observed_at":"2026-08-13T04:30:37.947155Z","submitted_at":"2024-01-30T23:35:28Z","title":"When Large Language Models Meet Vector Databases: A Survey","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.01763","snapshot_observed_at":"2026-08-10T20:34:34.739029Z","title":"When Large Language Models Meet Vector Databases: A Survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.739029Z"},"links":{"cited_paper":"/paper/2402.01763","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:32521e8357e764fc8b3ec82713b09f04b475a0ba80ace2ba684eaeb118887269","observation_id":"6d21e547-7f70-4a2d-b510-e5bc727feb89","resolution":{"observed_at":"2026-08-10T20:34:34.739029Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.13343","last_updated":"2025-03-18T02:16:56Z","snapshot_observed_at":"2026-08-15T17:34:48.644809Z","submitted_at":"2023-04-26T07:25:31Z","title":"SCM: Enhancing Large Language Model with Self-Controlled Memory Framework","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.13343","snapshot_observed_at":"2026-08-10T20:34:34.751475Z","title":"Enhancing Large Language Model with Self-Controlled Memory Framework","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.751475Z"},"links":{"cited_paper":"/paper/2304.13343","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:bb49734e5e935c5a894d65109b2baeaea1600f2e5062d9e09e22059019a5c97f","observation_id":"7666a8f5-53e2-464b-b289-10e44943297b","resolution":{"observed_at":"2026-08-10T20:34:34.751475Z","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":"2026-08-10T20:34:36.365365Z","title":"Memorybank: Enhancing large language models with long-term memory","venue":null,"work_id":"67a835e4-1dce-4867-bea4-a6ec0bbde833","year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.747894Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:eab562551dd24f1ab7f2d1de4cc91c1127c14fbd89038aa53ed2e5996cb7c311","observation_id":"61dc5bd5-5ba0-4629-92fe-8eed06bfc916","resolution":{"observed_at":"2026-08-10T20:34:36.368128Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T20:34:34.758756Z","title":"Prompted LLMs as Chatbot Modules for Long Open-domain Conversation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.758756Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:a27b8caa5d2962a39c8503c66cf70ce256f847123ea15ff2b472d852268a163c","observation_id":"144030b8-98f8-4c65-b395-d37026112271","resolution":{"observed_at":"2026-08-10T20:34:34.758756Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08560","last_updated":"2024-02-12T18:59:46Z","snapshot_observed_at":"2026-08-15T11:39:49.280087Z","submitted_at":"2023-10-12T17:51:32Z","title":"MemGPT: Towards LLMs as Operating Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.08560","snapshot_observed_at":"2026-08-10T20:34:34.755264Z","title":"MemGPT: Towards LLMs as Operating Systems","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.755264Z"},"links":{"cited_paper":"/paper/2310.08560","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:0fdbaeb14b38ad69612b5f629a97f085417c70a39247e90ecadf68f29bfa6bff","observation_id":"320c9611-6b5e-47fd-b126-bc3cd6dfc830","resolution":{"observed_at":"2026-08-10T20:34:34.755264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14322","last_updated":"2024-10-24T17:59:20Z","snapshot_observed_at":"2026-08-15T00:58:08.224008Z","submitted_at":"2023-05-23T17:53:38Z","title":"RET-LLM: Towards a General Read-Write Memory for Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14322","snapshot_observed_at":"2026-08-10T20:34:34.765560Z","title":"RET-LLM: Towards a General Read-Write Memory for Large Language Models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.765560Z"},"links":{"cited_paper":"/paper/2305.14322","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:66735c724af9b9e1c4d72f7ce996737b03640ed7f546bc2b030d30907c7cf76b","observation_id":"4bd312a2-feee-4eef-ba08-5f14327aa27d","resolution":{"observed_at":"2026-08-10T20:34:34.765560Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.08719","last_updated":"2023-11-15T06:08:35Z","snapshot_observed_at":"2026-08-13T05:25:04.425955Z","submitted_at":"2023-11-15T06:08:35Z","title":"Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.08719","snapshot_observed_at":"2026-08-10T20:34:34.761782Z","title":"Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.761782Z"},"links":{"cited_paper":"/paper/2311.08719","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:31d0153f4b5167d524a1e789157ff267aeca714a0825bfed6e31fcf1e884007c","observation_id":"4ca3560a-e679-471a-8ea7-518c9d320d39","resolution":{"observed_at":"2026-08-10T20:34:34.761782Z","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":"2026-08-10T20:34:34.774354Z","title":"Retrieve Only When It Needs: Adaptive Retrieval Augmentation for Hallucination Mitigation in Large Language Models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.774354Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:ca4d2318f6965f3b66821d118151de1c8d5a05a7f3f867c615854b5318a7313e","observation_id":"1abb8a49-e585-4b92-b3f6-c0fcbf5aae93","resolution":{"observed_at":"2026-08-10T20:34:34.774354Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.11019","last_updated":"2024-11-19T05:35:02Z","snapshot_observed_at":"2026-08-13T10:51:02.271954Z","submitted_at":"2023-07-20T16:46:10Z","title":"Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.11019","snapshot_observed_at":"2026-08-10T20:34:34.770576Z","title":"Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.770576Z"},"links":{"cited_paper":"/paper/2307.11019","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:f8c6d5067410466c948a8ace989243941a0373024c93f5b18b634c39ad03d3e5","observation_id":"f3bb5253-8cb5-43dc-967d-c12e688bc1d8","resolution":{"observed_at":"2026-08-10T20:34:34.770576Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.10625","last_updated":"2023-04-16T22:08:08Z","snapshot_observed_at":"2026-08-06T09:00:42.886249Z","submitted_at":"2022-05-21T15:34:53Z","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.10625","snapshot_observed_at":"2026-08-10T20:34:34.781911Z","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.781911Z"},"links":{"cited_paper":"/paper/2205.10625","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:d003ff9322fe72535c58b985fa5d1cef0375e3265f63f28b3e7d5df89ee16bbb","observation_id":"082fb69d-73e2-4c2b-8659-1696d488a256","resolution":{"observed_at":"2026-08-10T20:34:34.781911Z","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":"2026-08-10T20:34:34.778452Z","title":"Self-Knowledge Guided Retrieval Augmentation for Large Language Models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.778452Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:8c958fd1059bbae6ee0426fb9876467b8e8c3c36e8f88e3c76121e64a863ffd7","observation_id":"4bedb0e0-5f9d-405f-9ad4-a61bb8ec1396","resolution":{"observed_at":"2026-08-10T20:34:34.778452Z","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":"2026-08-10T20:34:34.789495Z","title":"Measuring and Narrowing the Compositionality Gap in Language Models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.789495Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:8a3cef5ee7fbfa8f8d9dce638470b45f51360f12be5af857298cdfc3f225ab11","observation_id":"ba769112-b3f6-46e7-b678-ceaf188c9c34","resolution":{"observed_at":"2026-08-10T20:34:34.789495Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.11903","last_updated":"2023-01-10T23:07:57Z","snapshot_observed_at":"2026-08-13T07:04:41.220509Z","submitted_at":"2022-01-28T02:33:07Z","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.11903","snapshot_observed_at":"2026-08-10T20:34:34.785884Z","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.785884Z"},"links":{"cited_paper":"/paper/2201.11903","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:ba046b306568809e0c839005625502da6c356f2c8dad228c67dd5da5b53838e0","observation_id":"0c69190a-ee1e-402b-9866-29e52385a654","resolution":{"observed_at":"2026-08-10T20:34:34.785884Z","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":"2026-08-10T20:34:34.797017Z","title":"Precise Zero-Shot Dense Retrieval without Relevance Labels","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.797017Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:e415d43081ebb67e33765e3a7b01ca8c1f6f062bd86482f798bfdf3e708df9fa","observation_id":"e1ce1ad1-4d01-4704-a236-ef5f3a633b7e","resolution":{"observed_at":"2026-08-10T20:34:34.797017Z","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":"2026-08-10T20:34:36.356855Z","title":"LangChain MultiQueryRetriever Documentation","venue":null,"work_id":"7bc894f6-5878-46ce-ae30-b30f2430ffe1","year":2025},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.793105Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:61f381acc513828018f175a2a7eae8078a5ea5d5842dea294750ab7ec8bb8d69","observation_id":"4a797e29-9615-4bd1-abf8-c7775144eb7d","resolution":{"observed_at":"2026-08-10T20:34:36.359662Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T20:34:36.331749Z","title":"Query Rewriting in Retrieval-Augmented Large Language Models","venue":null,"work_id":"8e07b3a3-e46e-40b3-a2ff-04e350b20d20","year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.809574Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:498b7d7f879e082f2db287a5e184fb975094d7cf22baf3a68f90082a86ae6882","observation_id":"e79e50cd-217a-473a-be10-a98b5b15aa22","resolution":{"observed_at":"2026-08-10T20:34:36.336267Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T20:34:36.344029Z","title":"Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models","venue":null,"work_id":"d7bf4547-dad1-435b-b6c4-cf005b6b5a2b","year":null},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.800518Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:9bb064cb7331cdfeee2453ea168f2d4cff370679e3e9f5a2ec34ae6bb042e638","observation_id":"1d1cdbbe-7828-4c5b-a10a-07393c406a86","resolution":{"observed_at":"2026-08-10T20:34:36.348395Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06117","last_updated":"2024-03-12T04:38:27Z","snapshot_observed_at":"2026-08-13T05:53:33.533042Z","submitted_at":"2023-10-09T19:48:55Z","title":"Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06117","snapshot_observed_at":"2026-08-10T20:34:34.805101Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.805101Z"},"links":{"cited_paper":"/paper/2310.06117","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:6feb161cdcec2d5274bec349f74332c6e96091382fe66868f146b4979be95d4f","observation_id":"bf5b6e7c-4bff-4841-b016-059273b2b6d6","resolution":{"observed_at":"2026-08-10T20:34:34.805101Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13243","last_updated":"2023-10-20T02:54:42Z","snapshot_observed_at":"2026-08-13T05:44:55.580860Z","submitted_at":"2023-10-20T02:54:42Z","title":"Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.13243","snapshot_observed_at":"2026-08-10T20:34:34.823733Z","title":"Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.823733Z"},"links":{"cited_paper":"/paper/2310.13243","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:5508a7f986c68c6cb1eca95d709354849e7eb78d89c92067dec829db94b3bd94","observation_id":"61786389-4bef-4217-8090-bac5691b7440","resolution":{"observed_at":"2026-08-10T20:34:34.823733Z","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":"2026-08-10T20:34:36.276494Z","title":"The probabilistic relevance framework: BM25 and beyond","venue":null,"work_id":"d901d9b0-5b9d-4f0a-980a-3238fdfe3544","year":2009},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.813746Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:f8e62e60aae80704b906272c701ce852060781d6f4e420e4b687eb498d9784cb","observation_id":"451c9896-782a-493b-aa73-50c0fa544221","resolution":{"observed_at":"2026-08-10T20:34:36.280227Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T20:34:36.264980Z","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","venue":null,"work_id":"c409bcb6-4d3c-4235-93df-a4445a3fef10","year":null},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.817103Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:b59cd0c51228f25454cdd9df4c36fdb0ac93e1b61fec7060ca535392eceacb94","observation_id":"64478475-c931-4f6d-b632-7855cc94dac4","resolution":{"observed_at":"2026-08-10T20:34:36.268803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T20:34:34.833093Z","title":"Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.833093Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:a3c37e7345a4a6ba466e44c911c123dedeb79b5d449403743d79484af0c56f7a","observation_id":"f54e5bd3-6127-450d-a00a-1b161aa3f809","resolution":{"observed_at":"2026-08-10T20:34:34.833093Z","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":"2026-08-10T20:34:34.837898Z","title":"Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.837898Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:af53759c12f4ace72cf8e83109c2f563d5e8b3a2308e8fcc8b7e7782139c10e8","observation_id":"76faf528-d026-4ae7-987b-6ece6b6d6f36","resolution":{"observed_at":"2026-08-10T20:34:34.837898Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.02156","last_updated":"2023-05-03T14:45:34Z","snapshot_observed_at":"2026-08-13T11:50:02.982514Z","submitted_at":"2023-05-03T14:45:34Z","title":"Zero-Shot Listwise Document Reranking with a Large Language Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.02156","snapshot_observed_at":"2026-08-10T20:34:34.826713Z","title":"Zero-Shot Listwise Document Reranking with a Large Language Model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.826713Z"},"links":{"cited_paper":"/paper/2305.02156","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:bd5b4f8c1026c7b85b703d422ac69f8156bd913d2428d11310106e7995df8669","observation_id":"35e6d91e-2914-4031-8023-f361536eacb8","resolution":{"observed_at":"2026-08-10T20:34:34.826713Z","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":"2026-08-10T20:34:34.829677Z","title":"Improving Passage Retrieval with Zero-Shot Question Generation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.829677Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:150775b15e539406a01889ea2f2ff0ebb57ff7f4967f8d5ba4901fc7853cb4f5","observation_id":"4c11f225-a290-4277-b463-f69255be22ba","resolution":{"observed_at":"2026-08-10T20:34:34.829677Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04408","last_updated":"2023-10-06T17:55:36Z","snapshot_observed_at":"2026-08-13T05:55:15.507166Z","submitted_at":"2023-10-06T17:55:36Z","title":"RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04408","snapshot_observed_at":"2026-08-10T20:34:34.850708Z","title":"RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.850708Z"},"links":{"cited_paper":"/paper/2310.04408","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:9c3af2595ca43384b56230331ec18d545f588240db001f73224111112d129712","observation_id":"9cbf4ebb-ab44-46f3-b3d8-29ae793e77dd","resolution":{"observed_at":"2026-08-10T20:34:34.850708Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06201","last_updated":"2023-10-09T23:03:24Z","snapshot_observed_at":"2026-08-14T02:06:56.363483Z","submitted_at":"2023-10-09T23:03:24Z","title":"Compressing Context to Enhance Inference Efficiency of Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06201","snapshot_observed_at":"2026-08-10T20:34:34.855472Z","title":"Compressing Context to Enhance Inference Efficiency of Large Language Models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.855472Z"},"links":{"cited_paper":"/paper/2310.06201","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:36b687273a9729a134e630e01cd36822198571d2a183c4fcd9985bd533f2da36","observation_id":"b512612a-43a3-4214-a307-fe42a9e6f753","resolution":{"observed_at":"2026-08-10T20:34:34.855472Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.09110","last_updated":"2023-10-01T21:44:23Z","snapshot_observed_at":"2026-08-10T23:10:13.900680Z","submitted_at":"2022-11-16T18:51:34Z","title":"Holistic Evaluation of Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.09110","snapshot_observed_at":"2026-08-10T20:34:34.841850Z","title":"Holistic Evaluation of Language Models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.841850Z"},"links":{"cited_paper":"/paper/2211.09110","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:9faaa605a7ca28e665f91f013a55a3467f55e2bf6d3198738b20544803ab7a02","observation_id":"32469f6b-cb2d-49f3-b768-e031bb9cdc87","resolution":{"observed_at":"2026-08-10T20:34:34.841850Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.18347","last_updated":"2023-10-23T03:12:00Z","snapshot_observed_at":"2026-08-15T11:17:57.401939Z","submitted_at":"2023-10-23T03:12:00Z","title":"PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.18347","snapshot_observed_at":"2026-08-10T20:34:34.846138Z","title":"PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.846138Z"},"links":{"cited_paper":"/paper/2310.18347","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:725778ed8f4233f73fd35358fb70c352067b58a91d31f8d0b06ac5cba634af76","observation_id":"1ff3d861-2558-44ac-9206-302d939099e4","resolution":{"observed_at":"2026-08-10T20:34:34.846138Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.07437","last_updated":"2024-07-03T04:59:32Z","snapshot_observed_at":"2026-08-15T01:32:38.480997Z","submitted_at":"2024-05-13T02:33:25Z","title":"Evaluation of Retrieval-Augmented Generation: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.07437","snapshot_observed_at":"2026-08-10T20:34:34.866124Z","title":"Evaluation of Retrieval-Augmented Generation: A Survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.866124Z"},"links":{"cited_paper":"/paper/2405.07437","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:45b1c76642b308e2bca2397c8e6a9ea17100a14c48adf242c68001e2ae2581dd","observation_id":"25323492-7070-4291-afb8-c02f21d2a884","resolution":{"observed_at":"2026-08-10T20:34:34.866124Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17753","last_updated":"2024-02-27T18:42:31Z","snapshot_observed_at":"2026-08-13T02:36:36.245972Z","submitted_at":"2024-02-27T18:42:31Z","title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17753","snapshot_observed_at":"2026-08-10T20:34:34.871277Z","title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.871277Z"},"links":{"cited_paper":"/paper/2402.17753","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:2a2736cd55665b87ed1a847640f1bf426d60c5aaa0a1ed72ce1977229b7c61a6","observation_id":"e5a88057-0b18-4d5d-b156-6ec7ef58d0e8","resolution":{"observed_at":"2026-08-10T20:34:34.871277Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05736","last_updated":"2023-12-06T17:02:25Z","snapshot_observed_at":"2026-08-15T15:21:44.762068Z","submitted_at":"2023-10-09T14:10:21Z","title":"LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05736","snapshot_observed_at":"2026-08-10T20:34:34.859209Z","title":"LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.859209Z"},"links":{"cited_paper":"/paper/2310.05736","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:285372c4f9c99f2cd326c3bfb66b1149cb291d410eb8bc167ae64f46c3129ea1","observation_id":"8b42b6be-e6f7-43dc-bd46-68648dccc2f4","resolution":{"observed_at":"2026-08-10T20:34:34.859209Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.12968","last_updated":"2024-08-12T04:48:11Z","snapshot_observed_at":"2026-08-13T04:31:57.453646Z","submitted_at":"2024-03-19T17:59:56Z","title":"LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.12968","snapshot_observed_at":"2026-08-10T20:34:34.862327Z","title":"LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compres- sion","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.862327Z"},"links":{"cited_paper":"/paper/2403.12968","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:fcff20663be2177a3cf40dbac6302253662d238644fa190ac26bf568399c0309","observation_id":"9e3aa15e-7e27-4612-83b7-1de9e17b536b","resolution":{"observed_at":"2026-08-10T20:34:34.862327Z","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":"2026-08-10T20:34:36.241673Z","title":"Ai arxiv dataset","venue":null,"work_id":"30d1ba74-d680-4d2f-96ba-1d7a2191cb13","year":2025},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.884573Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:d7d45ea81be5ba68d2fd4d759a32db71f178af02adee02a6dd76d2dd738b3945","observation_id":"6e4b699e-d933-455c-8181-65b2a64d4aef","resolution":{"observed_at":"2026-08-10T20:34:36.245221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.01037","last_updated":"2024-04-01T10:43:52Z","snapshot_observed_at":"2026-08-13T00:40:12.050012Z","submitted_at":"2024-04-01T10:43:52Z","title":"ARAGOG: Advanced RAG Output Grading","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.01037","snapshot_observed_at":"2026-08-10T20:34:34.888336Z","title":"ARAGOG: Advanced RAG Output Grading","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.888336Z"},"links":{"cited_paper":"/paper/2404.01037","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:4616c840d0c80d71465e26b53068ccbcf845eee4861207539866305248770471","observation_id":"5a5c5566-5d98-4666-8e34-3afa3871f474","resolution":{"observed_at":"2026-08-10T20:34:34.888336Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.09600","last_updated":"2018-09-25T17:28:20Z","snapshot_observed_at":"2026-08-11T10:35:06.989614Z","submitted_at":"2018-09-25T17:28:20Z","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.09600","snapshot_observed_at":"2026-08-10T20:34:34.875760Z","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.875760Z"},"links":{"cited_paper":"/paper/1809.09600","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:ed202bb98a68da906da5b9822e1cc5df5177de874395d91007df099aa76d59e8","observation_id":"dc5f26cf-0b79-4a0b-aec4-dd8ee0aeb915","resolution":{"observed_at":"2026-08-10T20:34:34.875760Z","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":"2026-08-10T20:34:36.252648Z","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","venue":null,"work_id":"5f3b6df9-e4fc-4f73-86ef-fd6422518a7c","year":2022},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.880809Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:f8164df52919311807620a49c0ac7b8231bbcdc012d4f50c305aa95112fa05b1","observation_id":"93de9640-b27c-4604-aba5-39bf971a1139","resolution":{"observed_at":"2026-08-10T20:34:36.257073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T20:34:36.202627Z","title":"Powercap Linux Kernel Interface","venue":null,"work_id":"bb4a90da-0a11-42fc-bf0e-563bd13c321f","year":2025},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.901183Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:fbbb3b431e3be19121e5b25052c8defc4df981091f63695680078928a617c1d1","observation_id":"adafa292-fbbf-410e-a5ab-baa49b8263eb","resolution":{"observed_at":"2026-08-10T20:34:36.206539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T20:34:36.191874Z","title":"NVIDIA Management Library (NVML) Python Bindings","venue":null,"work_id":"4c1bd2c9-d619-46be-a7d0-8a0e40a5188c","year":2025},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.904862Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:f6992a0da6789c521180a2730fd9e034f5922cece21c6d376ce347b77e8ee1cb","observation_id":"9bc58800-eace-4097-966d-493b1f166f8b","resolution":{"observed_at":"2026-08-10T20:34:36.195638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T20:34:36.228113Z","title":"\"UpTrain\"","venue":null,"work_id":"9e110579-962d-4704-8205-eb68e6e41b7b","year":2025},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.892252Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:dfdf5d9d5febcc1908005da9a67394586319a6112db4f0c833d7ea6678d377fe","observation_id":"48fd9dea-a5d7-4681-b435-0cbdfd9672ed","resolution":{"observed_at":"2026-08-10T20:34:36.233310Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T20:34:36.214383Z","title":"ROUGE: A Package for Automatic Evaluation of Summaries","venue":null,"work_id":"d0aaff3a-9b0b-45b8-916a-3119fbb54618","year":2004},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.896944Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:5e731f4c8a5366f88f64e844be51f1218b41f2dbd16f1e140ceb20eb5c7ca284","observation_id":"1643050b-4d3f-457a-8ff5-2e881f1be727","resolution":{"observed_at":"2026-08-10T20:34:36.218706Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T20:34:36.180782Z","title":"LlamaIndex","venue":null,"work_id":"7bd199ac-f212-4fc2-8ec9-61a4bd5b3906","year":2022},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.908430Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:954928093bc93dc2745a4b575b5c9d4dee32ea6ba3e0613c8d05b1792fdcc5a9","observation_id":"4c752991-19c4-4520-8fc3-e6c19ac6ca6a","resolution":{"observed_at":"2026-08-10T20:34:36.184635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T20:34:36.168414Z","title":"Searching for best practices in retrieval-augmented generation","venue":null,"work_id":"203801b2-2777-46d1-9b0c-5464d7218e7f","year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.911397Z"},"links":{"citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:eb9f6bca9df4ef8af4f24446d2db593657230f4d462f83c02676dd8b4f5d1b7e","observation_id":"27ba384f-6a1a-4980-aa59-32e4d72d6d50","resolution":{"observed_at":"2026-08-10T20:34:36.172375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.10084","last_updated":"2019-08-27T08:50:17Z","snapshot_observed_at":"2026-08-14T05:02:11.716316Z","submitted_at":"2019-08-27T08:50:17Z","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.10084","snapshot_observed_at":"2026-08-10T20:34:34.820447Z","title":null,"venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.820447Z"},"links":{"cited_paper":"/paper/1908.10084","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:75db7ca97bcb657383c47af15c04d14408258b45606853ed96270f4dd8db7ddf","observation_id":"ae0e295f-dde8-4528-9278-a3c13c4bf4d4","resolution":{"observed_at":"2026-08-10T20:34:34.820447Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.15664","last_updated":"2024-11-23T22:19:37Z","snapshot_observed_at":"2026-08-12T21:41:08.350212Z","submitted_at":"2024-11-23T22:19:37Z","title":"Enabling Efficient Serverless Inference Serving for LLM (Large Language Model) in the Cloud","version":1},"cited_work":{"arxiv_id":"2411.15664","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.15664","snapshot_observed_at":"2026-08-10T20:34:35.675801Z","title":"Enabling Efficient Serverless Inference Serving for LLM (Large Language Model) in the Cloud","venue":"cs.DC","work_id":"85663b51-fd5e-4061-90d6-dbdbfab74213","year":2024},"citing_paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:34.676288Z"},"links":{"cited_paper":"/paper/2411.15664","citing_paper":"/paper/2501.08262"},"observation_digest":"sha256:c0bb84c767b86386d28c05dc30348e3f570f2a37570f67f392a34d4122b50254","observation_id":"36daebe2-8f27-449a-814d-24b40e8aae63","resolution":{"observed_at":"2026-08-10T20:34:35.680096Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.08262","last_updated":"2025-01-14T17:21:16Z","latest_version":1,"primary_category":"cs.CY","snapshot_observed_at":"2026-08-14T19:33:53.600679Z","submitted_at":"2025-01-14T17:21:16Z","title":"Addressing the sustainable AI trilemma: a case study on LLM agents and RAG"},"reference_resolution":{"displayed":77,"state_counts":{"malformed_identifier":6,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":49,"verified_exact":2,"verified_fuzzy":18},"total_outbound_references":77},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 77 of 77 outbound references and 0 inbound Pith citation observations for arXiv:2501.08262."}