{"as_of":"2026-08-15T07:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a8ffe6b807288ac6496f55486eb2f7593cbb88d11cbe481044581c054a40955b","coverage":[{"denominator":22,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":22,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T04:14:42.335905Z","state":"measured"},{"denominator":22,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":22,"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/2608.10171/citation-record","integrity":"/paper/2608.10171/integrity","json":"/paper/2608.10171/citation-record.json","paper":"/paper/2608.10171"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:14:43.015248Z","title":"expanded","venue":null,"work_id":"bf1fcdf6-0fce-4fd8-b5f7-e2736fadd323","year":null},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.053750Z"},"links":{"citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:50881e1a1dcf93204fb7137c6680ed426e04b4d3ee71872012a52035457b52a6","observation_id":"c9f008bf-754d-4d69-93e2-901452fc5423","resolution":{"observed_at":"2026-08-14T04:14:43.080275Z","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":"2026-08-14T04:14:42.988791Z","title":"successful","venue":null,"work_id":"6dda284d-9e6b-4686-9ef8-14e4d7721aa3","year":null},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.060251Z"},"links":{"citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:3b17f80acf62a57159fd03b6fb584387dd72ec669d8f7d816a090b556221650b","observation_id":"3cb37e51-b21a-4969-8f2f-d3533f8df5b9","resolution":{"observed_at":"2026-08-14T04:14:42.994488Z","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":"2026-08-14T04:14:42.970292Z","title":"It numerically indicates how closely the attacker model approaches the target model’s vulnerability threshold","venue":null,"work_id":"29425a21-7cea-430b-bfdc-430eb93ae0cc","year":null},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.066969Z"},"links":{"citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:60541617d1f6b4f2552339bcdfda8e965bd44afc54c52daff8d488e7b021e0a9","observation_id":"215acd97-9dcc-43b6-8555-d1983068e8fa","resolution":{"observed_at":"2026-08-14T04:14:42.976257Z","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":"2026-08-14T04:14:42.934326Z","title":"The average of the pairwise cosine similarities between these input vectors was then computed","venue":null,"work_id":"fb18ea68-53a6-49aa-a627-7d4e2e533d01","year":null},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.073514Z"},"links":{"citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:e5824321df36af5f8c97eb681862359df0dd2589b22ebecd623a5f98ad500e4c","observation_id":"bf37eb44-773d-4388-ae27-42674b9a9629","resolution":{"observed_at":"2026-08-14T04:14:42.940888Z","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":"2202.03286","last_updated":"2022-02-07T15:22:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-02-07T15:22:17Z","title":"Red Teaming Language Models with Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.03286","snapshot_observed_at":"2026-08-14T04:14:42.161232Z","title":"Red teaming language models with language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.161232Z"},"links":{"cited_paper":"/paper/2202.03286","citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:559ff4abfaf8ff6a16d73bf7b7a32da70e5ec2c7085053c84dda839334e1479d","observation_id":"16074e01-c34c-46a8-b3a0-eb23df6bd01a","resolution":{"observed_at":"2026-08-14T04:14:42.161232Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.06083","last_updated":"2019-08-17T18:34:11Z","snapshot_observed_at":"2026-08-15T06:41:54.386322Z","submitted_at":"2019-08-17T18:34:11Z","title":"Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.06083","snapshot_observed_at":"2026-08-14T04:14:42.117529Z","title":"Build it break it fix it for dialogue safety: Robustness from adversarial human attack,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.117529Z"},"links":{"cited_paper":"/paper/1908.06083","citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:f76f685fc3b4ee9f19dea602fec42e39e53768dcca984d45a4d850198371d680","observation_id":"978b9e47-b04c-4e88-ab8c-31e093f8c079","resolution":{"observed_at":"2026-08-14T04:14:42.117529Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.11036","last_updated":"2024-06-16T18:18:43Z","snapshot_observed_at":"2026-08-14T10:59:19.207876Z","submitted_at":"2024-06-16T18:18:43Z","title":"garak: A Framework for Security Probing Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.11036","snapshot_observed_at":"2026-08-14T04:14:42.128783Z","title":"garak: A framework for security probing large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.128783Z"},"links":{"cited_paper":"/paper/2406.11036","citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:60875594ea29077ccef5c4fcbc075f35fb7ecb60a04b42b021e782626002062d","observation_id":"46e9e5ed-beeb-443f-a163-6c8dfdf13a45","resolution":{"observed_at":"2026-08-14T04:14:42.128783Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-14T04:14:42.146772Z","title":"GPT-4 technical report,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.146772Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:ac5cd9fe9916d05f620c15c8b690ce7403ef6b9db3e07519b29ba8888ad99095","observation_id":"0b282cf0-8258-47dd-86bc-ef486ea8df2b","resolution":{"observed_at":"2026-08-14T04:14:42.146772Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.08073","last_updated":"2022-12-15T06:19:23Z","snapshot_observed_at":"2026-08-02T04:53:58.766070Z","submitted_at":"2022-12-15T06:19:23Z","title":"Constitutional AI: Harmlessness from AI Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.08073","snapshot_observed_at":"2026-08-14T04:14:42.153344Z","title":"Constitutional AI: Harmlessness from AI feedback,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.153344Z"},"links":{"cited_paper":"/paper/2212.08073","citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:4489535caedbb5d25cbaca10dfee1864700df6cbe28d7e15349e5f6d13581e7b","observation_id":"fb9a8741-b370-47ae-8a9a-58ef71367ba5","resolution":{"observed_at":"2026-08-14T04:14:42.153344Z","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":"2026-08-14T04:14:42.809709Z","title":"Learning diverse attacks on large language models for robust red-teaming and safety tuning,","venue":null,"work_id":"4ed1a619-79fd-405f-889c-3197f44ba04b","year":2025},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.214789Z"},"links":{"citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:68ea6b44d938bd13eb83fe5c82529c9bb9f2c224329f408a173c32c95db1327e","observation_id":"eec82b03-004c-4800-bdb4-f6739d25ccbd","resolution":{"observed_at":"2026-08-14T04:14:42.853114Z","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":"2305.17444","last_updated":"2023-05-27T11:00:15Z","snapshot_observed_at":"2026-08-13T11:31:50.712460Z","submitted_at":"2023-05-27T11:00:15Z","title":"Query-Efficient Black-Box Red Teaming via Bayesian Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.17444","snapshot_observed_at":"2026-08-14T04:14:42.167235Z","title":"Query-efficient black-box red teaming via bayesian optimization,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.167235Z"},"links":{"cited_paper":"/paper/2305.17444","citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:d3d101b17b2bd5ac9b9da4a8a2c2e2e6987a52facf42d46c7200a3df2727256b","observation_id":"876a6e06-1a26-4baa-9489-a474ffcde87e","resolution":{"observed_at":"2026-08-14T04:14:42.167235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16822","last_updated":"2024-12-11T18:07:25Z","snapshot_observed_at":"2026-08-13T04:09:48.076759Z","submitted_at":"2024-02-26T18:47:27Z","title":"Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16822","snapshot_observed_at":"2026-08-14T04:14:42.173329Z","title":"Rainbow teaming: Open-ended generation of diverse adversarial prompts,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.173329Z"},"links":{"cited_paper":"/paper/2402.16822","citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:40c1e289c3dac89f29f5ec1d261f5bf7a371d7430f2c15b4934c0ead0cdb6327","observation_id":"1c269d13-b23f-41e3-bdad-6dc597674b33","resolution":{"observed_at":"2026-08-14T04:14:42.173329Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.11654","last_updated":"2024-06-17T15:36:14Z","snapshot_observed_at":"2026-08-12T23:40:58.330521Z","submitted_at":"2024-06-17T15:36:14Z","title":"Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.11654","snapshot_observed_at":"2026-08-14T04:14:42.185091Z","title":"Ruby teaming: Improving quality diversity search with memory for automated red teaming,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.185091Z"},"links":{"cited_paper":"/paper/2406.11654","citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:c78cdd2270c4049a330d8a2b49827cfdc89615c8cb5ad2d160ed3af43cef5839","observation_id":"f1e3f1c3-bea0-475e-a067-1a4625e255d2","resolution":{"observed_at":"2026-08-14T04:14:42.185091Z","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":"2026-08-14T04:14:42.885330Z","title":"Curiosity-driven red-teaming for large language models,","venue":null,"work_id":"914e10cd-8370-424d-82b4-40a3081ec4ad","year":2024},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.194344Z"},"links":{"citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:14946a0ba32302085f97655ded0c8c7d4e8d318c7e9c988fc0d4e40e9450dd39","observation_id":"59a79e47-269e-4b1d-81cd-ac8729bc1f5e","resolution":{"observed_at":"2026-08-14T04:14:42.892081Z","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":"2503.19786","last_updated":"2025-03-25T15:52:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-03-25T15:52:34Z","title":"Gemma 3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.19786","snapshot_observed_at":"2026-08-14T04:14:42.294745Z","title":"Gemma 3 technical report,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.294745Z"},"links":{"cited_paper":"/paper/2503.19786","citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:ffc4113ee4e4c58d8dd845d9ce733b4f86bd58e7ba64fbfce9471fd477eb2804","observation_id":"983422ee-c685-4272-b407-4a3474f574d2","resolution":{"observed_at":"2026-08-14T04:14:42.294745Z","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":"2026-08-14T04:14:42.912099Z","title":"The results obtained are shown in Figure 2","venue":null,"work_id":"593abd87-fb7e-431f-a625-cd0be8a86f58","year":null},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.097333Z"},"links":{"citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:35e2eb086a40bb7e0116bea8264756f0c1fc60412fe1468aff31b5580b199306","observation_id":"ba40c3b4-5933-4c4b-9d26-acdc89c5db15","resolution":{"observed_at":"2026-08-14T04:14:42.919851Z","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":"2026-08-14T04:14:42.736268Z","title":"Training language models to follow instructions with human feedback,","venue":null,"work_id":"93a3cf2e-9484-4e11-b53b-676b100ac190","year":2022},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.237710Z"},"links":{"citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:4bdf24db749827191a964f685d67908e7a04b06191ac2ea5aff3168e77d39b81","observation_id":"fee17510-a3b5-4a19-91c2-47004f163e43","resolution":{"observed_at":"2026-08-14T04:14:42.759591Z","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":"2026-08-14T04:14:42.695426Z","title":"Flow network based generative models for non-iterative diverse candidate generation,","venue":null,"work_id":"e7d87c55-86f5-4712-820e-f23d4715097f","year":2021},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.262232Z"},"links":{"citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:86a6459cfbf7e7def7d9930e0c54a007a73ac1a0a5f481e2c369b9d9e160aea2","observation_id":"4747bb28-1ba9-418c-bb2c-abbe21ca9b1b","resolution":{"observed_at":"2026-08-14T04:14:42.701740Z","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":"2026-08-14T04:14:42.672937Z","title":"Deep reinforcement learning from human preferences,","venue":null,"work_id":"217d8422-2e9d-444c-b7a6-16a8e6a2973a","year":2017},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.274510Z"},"links":{"citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:f19cc9581d7da0d66b30b6ffe20c17cc48d99fc308b13891f54fe23877cf8ac0","observation_id":"930724b8-bc11-4a46-8648-e519aab6093c","resolution":{"observed_at":"2026-08-14T04:14:42.680276Z","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":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-08-14T04:14:42.280159Z","title":"Qwen3 technical report,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.280159Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:f2bfa9bd861b2ec03853d8f53e71c65f4cd23dedef5708e30944fc7fed4a3dad","observation_id":"203822ad-14c2-4a98-9c3f-f5224c8ccd23","resolution":{"observed_at":"2026-08-14T04:14:42.280159Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2510.14276","last_updated":"2025-10-16T04:00:18Z","snapshot_observed_at":"2026-08-14T07:39:23.817965Z","submitted_at":"2025-10-16T04:00:18Z","title":"Qwen3Guard Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2510.14276","snapshot_observed_at":"2026-08-14T04:14:42.318709Z","title":"Qwen3Guard technical report,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.318709Z"},"links":{"cited_paper":"/paper/2510.14276","citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:188fa3183a20f63ef12eb4e1cacdc3c1b954975bfedf5eb327ac2c74b41bbe32","observation_id":"1e1078c8-7ec9-49a0-8f1c-4dfb88780491","resolution":{"observed_at":"2026-08-14T04:14:42.318709Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-14T04:14:42.335905Z","title":"The Llama 3 herd of models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T04:14:42.335905Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2608.10171"},"observation_digest":"sha256:6220170353503731ccfe5f62c410864fddcc9927d46d0cf643e1d431a9b08f2a","observation_id":"f9989010-205d-4ece-86c2-81f979912a98","resolution":{"observed_at":"2026-08-14T04:14:42.335905Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.10171","last_updated":"2026-08-10T19:39:10Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-14T23:10:15.500433Z","submitted_at":"2026-08-10T19:39:10Z","title":"Generating Attacks for LLMs with GFlowNets"},"reference_resolution":{"displayed":22,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":0,"verified_fuzzy":10},"total_outbound_references":22},"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 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2608.10171."}