{"as_of":"2026-08-19T14:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:47346a0ab7e9d405a0b534f93d5200629f217c9250443a1b9062949c936eabb0","coverage":[{"denominator":41,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":41,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T16:30:01.098178Z","state":"measured"},{"denominator":42,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":42,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T12:54:39.977138Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.05273","snapshot_observed_at":"2026-08-04T12:54:39.977138Z","title":"Greener deep reinforcement learning: Analysis of energy and carbon efficiency across atari benchmarks.arXiv preprint arXiv:2509.05273,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.01764","last_updated":"2026-07-06T14:44:27Z","snapshot_observed_at":"2026-08-16T02:40:24.328294Z","submitted_at":"2025-10-02T07:56:47Z","title":"Octax: Accelerated CHIP-8 Arcade Environments for Reinforcement Learning in JAX","version":3},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-04T12:54:39.977138Z"},"links":{"cited_paper":"/paper/2509.05273","citing_paper":"/paper/2510.01764"},"observation_digest":"sha256:bee4a658eeccbf84a2192d44bcacc15ddfdc37f02dc0ac2a1ef9cd067527e137","observation_id":"4e397cfd-af6e-4aaf-8632-5bc7c902f2af","resolution":{"observed_at":"2026-08-04T12:54:39.977138Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2509.05273/citation-record","integrity":"/paper/2509.05273/integrity","json":"/paper/2509.05273/citation-record.json","paper":"/paper/2509.05273"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:30:01.974354Z","title":"Monthly energy review december 2024,","venue":null,"work_id":"0342ab7d-b5ae-418c-9faf-c02d67f5762a","year":2024},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.898407Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:88c6149156d829e549dbf340888072bf78ae148e2095475519b4bf9c0dacf960","observation_id":"161420a3-d065-4b67-88b2-b955a61e42b1","resolution":{"observed_at":"2026-08-15T16:30:01.980697Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:30:01.956354Z","title":"The real climate and transformative impact of ICT: A critique of estimates, trends, and regulations,","venue":null,"work_id":"a080bebe-2c75-4fc7-b105-50a8b01fd24d","year":null},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.903549Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:d1356246c8c56bae5fec8619d13b9f00bb3f84cf08fff5fd884e145302eeba6c","observation_id":"66b2c8e6-20f9-438f-9d49-c17943831d49","resolution":{"observed_at":"2026-08-15T16:30:01.961388Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:30:00.912804Z","title":"Powering intelligence: Analyzing artificial intelligence and data center energy consumption,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.912804Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:54e25bc7dd47c5532eb37a02beaf3f882788b547713055f2d62fdd3a0ecbf4b7","observation_id":"85317a72-580a-4210-b77a-44e9a829c126","resolution":{"observed_at":"2026-08-15T16:30:00.912804Z","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":"2026-08-15T16:30:01.938217Z","title":"llama-models/models/llama3 1/MODEL CARD.md at main - meta-llama/llama-models,","venue":null,"work_id":"1b0cc1f7-48a7-45ab-a67b-b07fa542671b","year":2024},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.917760Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:934fcfe34ee5fd3f3a6a5f55f1ad40560b2b4b0c94a3c872011f589570b03273","observation_id":"e1ac4900-a525-4871-8ea4-328643460e04","resolution":{"observed_at":"2026-08-15T16:30:01.944034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:30:01.920812Z","title":"llama-models/models/llama3 3/MODEL CARD.md at main - meta-llama/llama-models,","venue":null,"work_id":"ffdc5551-561b-4c04-b3b0-fc2660c2409d","year":2024},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.922955Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:317c2ce210919ddbd6ba9219dfa962ae93325854967068a4b1d5e80301e64512","observation_id":"e6217dc0-60ce-4ca2-afda-8630aefebc55","resolution":{"observed_at":"2026-08-15T16:30:01.925888Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.02001","last_updated":"2022-11-03T17:13:48Z","snapshot_observed_at":"2026-08-16T16:18:47.880774Z","submitted_at":"2022-11-03T17:13:48Z","title":"Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.02001","snapshot_observed_at":"2026-08-15T16:30:00.927799Z","title":"Estimating the carbon footprint of bloom, a 176b parameter language model,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.927799Z"},"links":{"cited_paper":"/paper/2211.02001","citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:eb7455237e03bc6e03209ce17743d8cd0b25a82a865737b6c4091b14e797df8d","observation_id":"ba1c7a40-002f-4280-81b9-46e92353c42c","resolution":{"observed_at":"2026-08-15T16:30:00.927799Z","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":"2026-08-15T16:30:01.902205Z","title":"Google 2024 sustainability report,","venue":null,"work_id":"8a105b7c-3268-4b80-a8b2-f84672760c0d","year":2024},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.933270Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:f122022523daa3e7fd7757e877d203d5772d36a4cd3f54fb9a28ffae4a30170e","observation_id":"08a81d08-1310-4ca5-9d2f-081973aa8748","resolution":{"observed_at":"2026-08-15T16:30:01.907984Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:30:01.861994Z","title":"Ai index report — stanford human-centered artificial intelligence","venue":null,"work_id":"cd877429-0622-433d-9313-d73292f3631a","year":null},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.942783Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:63d4aab86de47c6d5b4efe967bed49fdf4483084a76661aeaa969d4346c230b1","observation_id":"38f0d3a1-21c2-4117-90c8-ce7275ef4844","resolution":{"observed_at":"2026-08-15T16:30:01.868937Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:30:01.842846Z","title":"A single modern AI GPU consumes up to 3.7 MWh of power per year — GPUs sold last year alone consumed more power than 1.3 million homes — tomshardware.com,","venue":null,"work_id":"e0ff7808-279e-4284-aad4-109a2279a7b6","year":2024},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.947754Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:67b54875b445639a5a3ed6d948d8cc2985ac917321d1b4fe800aa040cc58ea23","observation_id":"e011fd23-89b5-40ca-a144-ffa46a80bbd1","resolution":{"observed_at":"2026-08-15T16:30:01.848837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:30:01.822021Z","title":"Energy and policy con- siderations for modern deep learning research,","venue":null,"work_id":"1069b3de-d349-425e-b409-15ca7db5482d","year":2020},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.952500Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:4a927f971c05219b6c232d39fe7d1ae22d467f724f48c791adf2195601c710b4","observation_id":"1c60c831-65dd-4c43-9b48-a3a97977512c","resolution":{"observed_at":"2026-08-15T16:30:01.827676Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:30:00.957102Z","title":"The carbon footprint of machine learning training will plateau, then shrink,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.957102Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:793e06b4d3ca9e6835e95b4e23c1dbf02d770eb42638fff0ae56165459fc461f","observation_id":"5759d967-1937-405e-854a-b082a2dcd36d","resolution":{"observed_at":"2026-08-15T16:30:00.957102Z","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":"2026-08-15T16:30:00.962007Z","title":"Green ai,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.962007Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:cddba366d1fe6b133b478d2d6dfdc9a230bb22324f46ea13ec2dc83141d03b60","observation_id":"abf5fdf8-0cd8-4bc8-9f79-ebb7f946e486","resolution":{"observed_at":"2026-08-15T16:30:00.962007Z","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":"2026-08-15T16:30:00.966662Z","title":"Sustainable ai: Environmental implications, challenges and opportunities,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.966662Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:2443d50a1c0a93124d00aa5b6778b73bbf5ffd192c9efb1d8e6ab96b8679aa29","observation_id":"3a1d98db-c2ef-4600-a296-8b7b29acfb4b","resolution":{"observed_at":"2026-08-15T16:30:00.966662Z","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":"2026-08-15T16:30:00.971647Z","title":"Deep reinforcement learning that matters,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.971647Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:e87f3b5801c07c7922a1b47838cd1e4334eeeaf775fd9d4828878532473b582e","observation_id":"c3c4b086-d606-4ad3-b6b8-f652e36736b9","resolution":{"observed_at":"2026-08-15T16:30:00.971647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.12729","last_updated":"2020-05-25T16:24:59Z","snapshot_observed_at":"2026-08-17T14:39:44.168275Z","submitted_at":"2020-05-25T16:24:59Z","title":"Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.12729","snapshot_observed_at":"2026-08-15T16:30:00.976208Z","title":"Implementation matters in deep policy gradients: A case study on ppo and trpo,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.976208Z"},"links":{"cited_paper":"/paper/2005.12729","citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:6287e2e4f89556567b763714d992a784509b99463ea8f3352231890a26db5b20","observation_id":"3cc5cde8-e828-4b8c-a869-f4ff5772a7b0","resolution":{"observed_at":"2026-08-15T16:30:00.976208Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.04133","last_updated":"2017-08-10T19:20:15Z","snapshot_observed_at":"2026-08-15T03:09:17.358218Z","submitted_at":"2017-08-10T19:20:15Z","title":"Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.04133","snapshot_observed_at":"2026-08-15T16:30:00.981104Z","title":"Reproducibil- ity of benchmarked deep reinforcement learning tasks for continuous control,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.981104Z"},"links":{"cited_paper":"/paper/1708.04133","citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:a4bec6457c024a45555bea2af578c1203c05bd06dce1a1f28b98d71213a066b9","observation_id":"5bb043ef-4271-4b76-afb1-dafe3ef4141e","resolution":{"observed_at":"2026-08-15T16:30:00.981104Z","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":"2026-08-15T16:30:00.986260Z","title":"Towards the systematic reporting of the energy and carbon footprints of machine learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.986260Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:cddc776c94e392de8499bd80ac37d4a3e3c36f16095000f5737efa503da14c5e","observation_id":"1c5d4941-910f-4d4f-987a-e5d5afdfea08","resolution":{"observed_at":"2026-08-15T16:30:00.986260Z","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":"2026-08-15T16:30:00.991146Z","title":"Human-level control through deep reinforcement learning,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.991146Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:b65cfac1dc8a9dd69375d918566714878a8c2252ea0c65fb8ecafad082e6a9f0","observation_id":"ad4ee1dc-c20b-4e71-8612-edd7f2a369d6","resolution":{"observed_at":"2026-08-15T16:30:00.991146Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10044","last_updated":"2017-10-27T09:35:26Z","snapshot_observed_at":"2026-08-16T09:49:58.616556Z","submitted_at":"2017-10-27T09:35:26Z","title":"Distributional Reinforcement Learning with Quantile Regression","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10044","snapshot_observed_at":"2026-08-15T16:30:00.995891Z","title":"Distributional reinforcement learning with quantile regression,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.995891Z"},"links":{"cited_paper":"/paper/1710.10044","citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:6bc8c501195db84cf47c76874bdc3b2a4878c0fc0a74232c21d1991d371c4c91","observation_id":"92441e72-15ac-4b71-93a3-87b3eff1b203","resolution":{"observed_at":"2026-08-15T16:30:00.995891Z","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":"2026-08-15T16:30:01.001106Z","title":"Asynchronous methods for deep reinforcement learning,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.001106Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:ff0a1c5384d8a240b4daaf2cd7a8fa55e20162396a32a5d2a09691d739b053b5","observation_id":"221bd5f0-7364-4e3e-96d3-4b625299d41e","resolution":{"observed_at":"2026-08-15T16:30:01.001106Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-08-15T20:26:32.102285Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-08-15T16:30:01.005707Z","title":"Proximal policy optimization algorithms,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.005707Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:8c82f94e086e87fe9c6b414f66c03efc3fa0c991ebf701e02928290f35a6798e","observation_id":"d2f1efab-26a2-4436-ac46-39e462839132","resolution":{"observed_at":"2026-08-15T16:30:01.005707Z","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":"2026-08-15T16:30:01.723631Z","title":"Trust region policy optimization,","venue":null,"work_id":"08fbb9dd-caaf-4794-96a5-3dfbc7b116e9","year":2015},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.010646Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:ea0d90a42452f75ebf9763b0201324a9f0856a65c4f2871852a92352dda86793","observation_id":"c406e096-6109-4a6b-ba30-5f6d536f7f40","resolution":{"observed_at":"2026-08-15T16:30:01.728893Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:30:01.706827Z","title":"Simple random search of static linear policies is competitive for reinforcement learning,","venue":null,"work_id":"9a71eaee-b173-4bcf-a0e6-ceaa5cee9a54","year":2018},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.015154Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:64614b8bf5ae066cdce6422392279b2856dbc05566e0ebaf67d3453e047aac8e","observation_id":"a597a9e5-4c22-4670-9346-1975e3cc2596","resolution":{"observed_at":"2026-08-15T16:30:01.712116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:30:01.020335Z","title":"Impala: Scalable dis- tributed deep-rl with importance weighted actor-learner architectures,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.020335Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:708e1d33d2038f665d5fa5333b16b2555aba66505082b1b142e78333b9a83f94","observation_id":"c0ecb4d1-f142-4ec6-995d-9332cc7273d9","resolution":{"observed_at":"2026-08-15T16:30:01.020335Z","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":"2026-08-15T16:30:01.665228Z","title":"Phasic policy gradient,","venue":null,"work_id":"a08fb7dd-78ba-43e6-a753-d3678c3c5785","year":2021},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.025163Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:ab538a3b55cd232db99ba078c326f81a719a9b94abfae0a860129fd7a6a410cd","observation_id":"3aa9e5d2-c41b-4eb8-a5ab-83ba0a4718e5","resolution":{"observed_at":"2026-08-15T16:30:01.674484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1509.06461","last_updated":"2015-12-08T21:19:16Z","snapshot_observed_at":"2026-08-14T22:31:25.126692Z","submitted_at":"2015-09-22T04:40:22Z","title":"Deep Reinforcement Learning with Double Q-learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1509.06461","snapshot_observed_at":"2026-08-15T16:30:01.030143Z","title":"Deep reinforcement learning with double q-learning,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.030143Z"},"links":{"cited_paper":"/paper/1509.06461","citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:caad6f5bfa3e2f00b563cc8ee9cf5cfb0c509ee034fdc017fbcf2cf7b89cd9a8","observation_id":"200fd7e1-0ec5-4cf4-98ce-5aaa7990c6d4","resolution":{"observed_at":"2026-08-15T16:30:01.030143Z","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":"2026-08-15T16:30:01.643180Z","title":"Gdm-net: Gas distribution mapping with a mobile robot using deep reinforcement learning and gaussian process regression,","venue":null,"work_id":"adbf5530-c738-4250-92d9-d2755088107b","year":2024},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.035330Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:a36f270e3ffbaa4bab96c7fad0d1a95bff30adc18569cfbc7b19120ff96538f1","observation_id":"7b691eeb-ba93-4846-b0bc-fe55b14e3dd3","resolution":{"observed_at":"2026-08-15T16:30:01.649156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:30:01.620991Z","title":"Deep reinforcement learning for autonomous driving: A survey,","venue":null,"work_id":"7f559020-78ac-4468-83f4-64eb1ceedf62","year":2021},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.041411Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:ffd69210652435db8a49979d6550de49070ba6b62d1660c86fe06aa073e6559f","observation_id":"4f8a6515-c435-4a8b-8ae4-803157881b40","resolution":{"observed_at":"2026-08-15T16:30:01.628654Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:30:01.600376Z","title":"Stable-Baselines3: Reliable reinforcement learning implementations,","venue":null,"work_id":"b5bdf424-7389-470a-8eed-8fab08bece1e","year":2021},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.048114Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:bb5437f60af7e561300d2dc06d608870d3dba9eae83fa46deb29530a99e08e9a","observation_id":"55370e6c-bd8a-46ee-9a2b-992c74c6813c","resolution":{"observed_at":"2026-08-15T16:30:01.606586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.17032","last_updated":"2025-11-02T13:42:19Z","snapshot_observed_at":"2026-08-13T22:24:37.672685Z","submitted_at":"2024-07-24T06:35:05Z","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.17032","snapshot_observed_at":"2026-08-15T16:30:01.053190Z","title":"Gymnasium: A standard interface for reinforcement learning environments,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.053190Z"},"links":{"cited_paper":"/paper/2407.17032","citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:b80a639df7ae69e1079ee884edf062bc3d9d23885b8641bb438cb8743944deda","observation_id":"36b1d9b1-cb93-4452-9a14-558ba644d07a","resolution":{"observed_at":"2026-08-15T16:30:01.053190Z","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":"2026-08-15T16:30:01.059569Z","title":"TensorFlow: Large-scale machine learning on heterogeneous systems,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.059569Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:f56236d2d6d4e9712b7f7db4be377d0a37852a69ad8b91accba42bfdf68dace7","observation_id":"1938f371-8da7-4d9c-b246-c8b43c5b97e3","resolution":{"observed_at":"2026-08-15T16:30:01.059569Z","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":"10.1145/1401132","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:30:01.159616Z","title":"Scalable parallel programming with cuda,","venue":null,"work_id":"8076e939-97cc-4d66-8cbe-f009da06adb4","year":2008},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.064780Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:bef2792e118c44d6493e50d825c73c9b3099deb85e62db0b1bde3e83152f9e07","observation_id":"ab9a3c30-435a-409a-93bc-d1e377c99de3","resolution":{"observed_at":"2026-08-15T16:30:01.167180Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:30:01.069299Z","title":"mlco2/codecarbon: v2.4.1,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.069299Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:bb48e7793225b0020b576273ef54e56bc3e805dd75a2c0238b634504bc32e537","observation_id":"2604ef47-5794-4f12-94c1-f174d30f9e28","resolution":{"observed_at":"2026-08-15T16:30:01.069299Z","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":"2026-08-15T16:30:01.553951Z","title":"United states of america 2024 carbon intensity data,","venue":null,"work_id":"e578df2f-6898-4ae1-a381-54e9d43382ad","year":2024},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.074470Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:19aec65cebdd2d4a49b90173a3c70c258893dbebf45f1825a1862239454f5dba","observation_id":"bb25df81-234e-4af4-a5ac-4a3227e41318","resolution":{"observed_at":"2026-08-15T16:30:01.560025Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:30:01.535932Z","title":"The arcade learning environment: An evaluation platform for general agents,","venue":null,"work_id":"2e9a3c4b-2681-4a78-96d7-97a7647a7ac6","year":null},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.079007Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:cb483b7c5dbe545122dec44c8cd1dc86345debedfba757be40bc7963f8f102c4","observation_id":"12ffead1-573a-4774-9230-d01d1315b83d","resolution":{"observed_at":"2026-08-15T16:30:01.541392Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:30:01.515527Z","title":"Rl algorithms — stable baselines 2.10.3a0 documentation","venue":null,"work_id":"08738a6e-b53d-4362-9b5a-25799917c38d","year":null},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.088506Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:c8ce9728ce0f9519b93b1c2e041acebd7678a5c118eb5d8993e7a2108ddc5c8a","observation_id":"14037c70-2128-4f5e-972d-c21a661e70a4","resolution":{"observed_at":"2026-08-15T16:30:01.520895Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:30:01.496963Z","title":"Average energy prices for the united states, regions, census divisions, and selected metropolitan areas : Midwest information office : U.s. bureau of labor statistics","venue":null,"work_id":"09a2ceb7-2295-4011-8f8d-bfe018f859a2","year":null},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.093636Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:e8fb68b4d9eabf8ade7abfc86ed2edfe4c956e69bb5157caa4a13bd71d134660","observation_id":"12c1c2ad-65ee-41ff-bd52-0962ceddd894","resolution":{"observed_at":"2026-08-15T16:30:01.503250Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:30:01.475269Z","title":"Rates — my account — local","venue":null,"work_id":"f172c4b9-705c-4ccc-aa25-17c46d3709c0","year":null},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.098178Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:a4ca154f4184f08da2d2bb65c8a167fbc3deeb518cf6658e4eccfd200e46cbc6","observation_id":"c6dfafc5-3905-4f00-8ea4-53a3c8465cb1","resolution":{"observed_at":"2026-08-15T16:30:01.484145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:30:01.083775Z","title":"Available: https://doi.org/10.1613/jair.3912","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:01.083775Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:85e3e3426c64f82b251e95845f3c144a02de95f4d8b99a38b5d3ebfb9823d977","observation_id":"e19676d9-c6b0-406f-bc25-1351da0e7668","resolution":{"observed_at":"2026-08-15T16:30:01.083775Z","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":"2026-08-15T16:30:00.908129Z","title":"Available: https://doi.org/10.1016/j.patter.2021.100340","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.908129Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:c6541f2b08a1bf6a1f8490237444b6dfd6077e840ca85c6bc8b26ef5aa71c565","observation_id":"63ef888d-98d6-46b3-a70d-81091ccb2da6","resolution":{"observed_at":"2026-08-15T16:30:00.908129Z","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":"2026-08-15T16:30:01.882205Z","title":"Available: https://sustainability.google/reports/","venue":null,"work_id":"4a7488c1-64f6-4096-acd9-44c60e3759ee","year":null},"citing_paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:00.938274Z"},"links":{"citing_paper":"/paper/2509.05273"},"observation_digest":"sha256:e54e8b214c8238124715c307c145d303041e99f5f96554ea7fb6dbdb27520102","observation_id":"207ad6ac-fd2c-4db6-a58d-05e76d46216a","resolution":{"observed_at":"2026-08-15T16:30:01.888458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.05273","last_updated":"2025-09-05T17:29:51Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T00:41:07.250289Z","submitted_at":"2025-09-05T17:29:51Z","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks"},"reference_resolution":{"displayed":41,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":20,"verified_exact":1,"verified_fuzzy":19},"total_outbound_references":41},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 1 inbound Pith citation observation for arXiv:2509.05273."}