{"as_of":"2026-08-22T18:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:31b288b92b82300a7f282b997a3d640583c07b3d2ef56f116db2dff33ff05210","coverage":[{"denominator":21,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":21,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T09:35:38.887808Z","state":"measured"},{"denominator":21,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":21,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/2607.20730/citation-record","integrity":"/paper/2607.20730/integrity","json":"/paper/2607.20730/citation-record.json","paper":"/paper/2607.20730"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-17T09:58:46.058102Z","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":"2026-08-01T09:35:37.168236Z","title":"Gpt-4 technical report,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:37.168236Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:80284c6a044faa5e5807acb394f7f7c23d5360521d9d382d6d5c52899101f1db","observation_id":"d14d3ab1-911c-48f4-9cc4-0f242907aee1","resolution":{"observed_at":"2026-08-01T09:35:37.168236Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-18T18:18:37.449517Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-08-01T09:35:37.246933Z","title":"Deepseek-v3 technical report,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:37.246933Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:5b9699795116f8eed659b4bf127f8fdaa56c602b3fb87b4e8a74795c699675a0","observation_id":"24f071c6-cc09-40c4-8b11-00d3df9b382e","resolution":{"observed_at":"2026-08-01T09:35:37.246933Z","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":"2026-08-01T09:35:37.397954Z","title":"Toolformer: Language models can teach themselves to use tools,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:37.397954Z"},"links":{"citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:22ccac0fddfaf77f3faf6ed8034f47c0ea0a5544c5ecc069fc098b171583123f","observation_id":"06ef6de0-4194-491d-adbe-ff739505b675","resolution":{"observed_at":"2026-08-01T09:35:37.397954Z","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":"2026-08-01T09:35:37.484725Z","title":"Geo: Generative engine optimization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:37.484725Z"},"links":{"citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:a854b402c731be911a10f0daf26ba95c219eadc8c300a11c5d47ff6c7f27650f","observation_id":"4cb3e5de-c70e-49c8-b678-df0b3e77556f","resolution":{"observed_at":"2026-08-01T09:35:37.484725Z","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":"2026-08-01T09:35:37.538381Z","title":"Combating knowledge corruption in agent systems: A byzantine- tolerant secure collaborative rag framework,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:37.538381Z"},"links":{"citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:7b831cfc56d86b7e94ed37fb737bf8d60a7e6a1372170f8cf26dcca7a6ed19f9","observation_id":"5b9a358d-1dee-42fb-a87d-410422b6e636","resolution":{"observed_at":"2026-08-01T09:35:37.538381Z","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":"2026-08-01T09:35:37.618151Z","title":"“liar, liar pants on fire","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:37.618151Z"},"links":{"citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:d192c0cb1816f180bf7569a96b5d11a46ed7a70ab5b3b4fef629d36e952535da","observation_id":"a0be6acd-9de5-4dc9-8cb0-04eb3b286360","resolution":{"observed_at":"2026-08-01T09:35:37.618151Z","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":"2026-08-01T09:35:37.704566Z","title":"Fakenewsnet: A data repository with news content, social context, and spatiotemporal information for studying fake news on social media,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:37.704566Z"},"links":{"citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:0a9ca91b0ac9cb734d9f491ffb13fcff2e17eb4e127530556d825368006b3ac9","observation_id":"dbb39c89-818b-4429-92d3-f520cb1367cf","resolution":{"observed_at":"2026-08-01T09:35:37.704566Z","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":"2026-08-01T09:35:37.772167Z","title":"Politifact fact check dataset,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:37.772167Z"},"links":{"citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:8a1fb60f81eff0a8f6dd06dc47bdd61a22619efa5efaeaa6a9b23dfb6b81d075","observation_id":"cf80a740-4bae-4ba4-9601-ce15d0dc704a","resolution":{"observed_at":"2026-08-01T09:35:37.772167Z","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":"2026-08-01T09:35:37.850814Z","title":"Check-covid: Fact-checking covid-19 news claims with scientific evidence,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:37.850814Z"},"links":{"citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:51e2573cf21ba6a7e489d9fb8a9589c6a082c3eaf82236d4c67531f43a53ff0c","observation_id":"c93c34e8-058d-46f3-a6db-8d5366e44312","resolution":{"observed_at":"2026-08-01T09:35:37.850814Z","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":"2026-08-01T09:35:37.922792Z","title":"A survey of fake news: Fundamental the- ories, detection methods, and opportunities,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:37.922792Z"},"links":{"citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:544a8153b129ee17f69a396d0bf409513743ce014f7d38060462dca5f3fc3593","observation_id":"413c3160-18f8-4cea-b2d4-1771bd83636f","resolution":{"observed_at":"2026-08-01T09:35:37.922792Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05046","last_updated":"2024-04-06T08:10:43Z","snapshot_observed_at":"2026-08-17T17:19:01.982619Z","submitted_at":"2023-10-08T07:01:07Z","title":"FakeGPT: Fake News Generation, Explanation and Detection of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05046","snapshot_observed_at":"2026-08-01T09:35:38.024815Z","title":"Fakegpt: fake news generation, explanation and detection of large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:38.024815Z"},"links":{"cited_paper":"/paper/2310.05046","citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:2f02a6c671825982e1c30ea7447c1b671ebb1e49ce8e3616ef7d79406fb50abd","observation_id":"7ee2d63f-fe7c-498a-8dda-ab9e84f60c1b","resolution":{"observed_at":"2026-08-01T09:35:38.024815Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07867","last_updated":"2024-08-13T01:55:06Z","snapshot_observed_at":"2026-08-18T12:32:21.937066Z","submitted_at":"2024-02-12T18:28:36Z","title":"PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.07867","snapshot_observed_at":"2026-08-01T09:35:38.121521Z","title":"Poisonedrag: Knowledge corruption attacks to retrieval-augmented generation of large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:38.121521Z"},"links":{"cited_paper":"/paper/2402.07867","citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:cf40bb9722a103ce51c8bc26abda8af509e08f8170989df5d3d0ef769dc24b76","observation_id":"e6e5ca80-4ad2-4309-9b65-ca2a9cffba0e","resolution":{"observed_at":"2026-08-01T09:35:38.121521Z","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":"2026-08-01T09:35:38.207709Z","title":"Fighting fire with fire: The dual role of llms in crafting and detecting elusive disinformation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:38.207709Z"},"links":{"citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:4d739b447bbb57a78a2c79acd0c0efcfbc4b95a101c4816b991b42fe63b0e178","observation_id":"24f8d0d6-2356-46b7-91ba-b0616f76fdfc","resolution":{"observed_at":"2026-08-01T09:35:38.207709Z","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":"2026-08-01T09:35:38.353515Z","title":"Teller: A trustworthy framework for explainable, generalizable and controllable fake news detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:38.353515Z"},"links":{"citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:81f1ed298f6ca314677ae0ed04ba53a9b8be3fcb1f5e82516b9cdbf88e7d323d","observation_id":"9f61fbbc-475b-46e5-b93f-40ef140b7d36","resolution":{"observed_at":"2026-08-01T09:35:38.353515Z","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":"2026-08-01T09:35:38.488497Z","title":"Robust fake news detection using large language models under adversarial sentiment attacks,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:38.488497Z"},"links":{"citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:3f635269dd5c7cfc8f868c114cacc48524a33a1532f2a929f6a2560a2a3f341f","observation_id":"f30ec907-0a0a-4aea-9ecc-54a81233e07e","resolution":{"observed_at":"2026-08-01T09:35:38.488497Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.09747","last_updated":"2024-03-14T00:35:39Z","snapshot_observed_at":"2026-08-16T14:09:59.681561Z","submitted_at":"2024-03-14T00:35:39Z","title":"Re-Search for The Truth: Multi-round Retrieval-augmented Large Language Models are Strong Fake News Detectors","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.09747","snapshot_observed_at":"2026-08-01T09:35:38.585115Z","title":"Re-search for the truth: Multi-round retrieval-augmented large language models are strong fake news detectors,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:38.585115Z"},"links":{"cited_paper":"/paper/2403.09747","citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:f0aba5d1d186ffb8960c5959722fac5e13ee3b8e2e2c0a8a8cd49f5bd124f3e3","observation_id":"523a5b80-0891-4734-b754-e21a602ed557","resolution":{"observed_at":"2026-08-01T09:35:38.585115Z","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":"2026-08-01T09:35:38.628517Z","title":"Long-form factuality in large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:38.628517Z"},"links":{"citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:fad113b0096563ada873083fee8c03fd471cb64da715bbf4083fbbc8148b825a","observation_id":"cace3962-5db3-403f-8359-00f08ac37f64","resolution":{"observed_at":"2026-08-01T09:35:38.628517Z","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":"2026-08-01T09:35:38.694289Z","title":"Retrieval augmented fact verification by synthesizing contrastive arguments,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:38.694289Z"},"links":{"citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:24ee53e9128de7d1c9cbe4a0cc3957d11c914b30bf5d2b10ea5472d3ce202882","observation_id":"edc09cff-663c-491e-b8fc-f31b63689a7c","resolution":{"observed_at":"2026-08-01T09:35:38.694289Z","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":"2026-08-01T09:35:38.766099Z","title":"FEVER: a large-scale dataset for fact extraction and VERification,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:38.766099Z"},"links":{"citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:c5cc0aafbe973df9ef9b073a77ab59e9eb5e343af15adb9bf92292d98a1be788","observation_id":"a6442b12-f378-41c7-a1d1-405c9c22537a","resolution":{"observed_at":"2026-08-01T09:35:38.766099Z","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":"2026-08-01T09:35:38.824870Z","title":"Deepseek-v4: Towards highly efficient million-token context intelligence,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:38.824870Z"},"links":{"citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:97f17ee4ae0285d3078cdce23719c7dd7e0dec8e9b75f3e98231ec784d2bd8aa","observation_id":"7caee9a1-034c-4772-a777-4fd7f5745e77","resolution":{"observed_at":"2026-08-01T09:35:38.824870Z","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":"2026-08-01T09:35:38.887808Z","title":"Introducing GPT-5.4,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T09:35:38.887808Z"},"links":{"citing_paper":"/paper/2607.20730"},"observation_digest":"sha256:5a4a4df6e4e6d0127015c4e7efa0c87cef46a21dfd2851e4e7e13f7fbfebc263","observation_id":"c84803f2-cfe4-4c34-848c-38b5ef436c9e","resolution":{"observed_at":"2026-08-01T09:35:38.887808Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.20730","last_updated":"2026-07-22T21:04:51Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-18T12:48:29.880235Z","submitted_at":"2026-07-22T21:04:51Z","title":"GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning"},"reference_resolution":{"displayed":21,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":20,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":21},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2607.20730."}