{"as_of":"2026-08-15T10:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e09cdd909c00c966f74bd7f3565be8de0b68ccca7320f307ec57b132c76b10cd","coverage":[{"denominator":30,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":30,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T13:41:18.342896Z","state":"measured"},{"denominator":30,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":30,"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/2608.10949/citation-record","integrity":"/paper/2608.10949/integrity","json":"/paper/2608.10949/citation-record.json","paper":"/paper/2608.10949"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2511.21631","last_updated":"2025-11-27T12:16:54Z","snapshot_observed_at":"2026-08-11T14:42:37.584016Z","submitted_at":"2025-11-26T17:59:08Z","title":"Qwen3-VL Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.21631","snapshot_observed_at":"2026-08-12T13:41:18.260265Z","title":"Qwen3-vl technical report.arXiv preprint arXiv:2511.21631,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.260265Z"},"links":{"cited_paper":"/paper/2511.21631","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:4043609edc91b74aaeb68e84354d21749b7abfb05cbbe0a7b7f656090e42a7d2","observation_id":"926d380d-e889-4441-94a6-6223bc70b7cf","resolution":{"observed_at":"2026-08-12T13:41:18.260265Z","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":"2026-08-12T13:41:19.064881Z","title":"Streamkv: Streaming video question-answering with segment-based kv cache retrieval and compression","venue":null,"work_id":"7d7e1bdd-4fa8-4ddb-bbe8-83422c264ce4","year":2025},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.269603Z"},"links":{"citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:52c036cba2ff1a050242f3da3d173299fd0ab5b7431c0b7f20c38137515c5324","observation_id":"a1cebe94-514f-4c8d-91c3-26190ffea55c","resolution":{"observed_at":"2026-08-12T13:41:19.067845Z","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":"2603.12262","last_updated":"2026-07-17T07:23:56Z","snapshot_observed_at":"2026-08-09T09:42:44.258435Z","submitted_at":"2026-03-12T17:59:51Z","title":"Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2603.12262","snapshot_observed_at":"2026-08-12T13:41:18.272347Z","title":"Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.272347Z"},"links":{"cited_paper":"/paper/2603.12262","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:81c72faa551fe94fd6b9b4db4455a28bd6d9f17f2444b6c9f95a3b05a2a4f2d7","observation_id":"0a28ddb3-19d6-4c3b-b438-6432bc1232cc","resolution":{"observed_at":"2026-08-12T13:41:18.272347Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.00814","last_updated":"2026-05-08T16:52:48Z","snapshot_observed_at":"2026-08-13T11:26:37.424755Z","submitted_at":"2026-05-01T17:54:37Z","title":"Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs","version":2},"cited_work":{"arxiv_id":"2605.00814","doi":null,"metadata_source":"pith","pith_arxiv_id":"2605.00814","snapshot_observed_at":"2026-08-12T13:41:18.959057Z","title":"Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs","venue":"cs.CV","work_id":"ddf7cee0-4d54-4c64-9dc1-46fbf59b67e4","year":2026},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.276127Z"},"links":{"cited_paper":"/paper/2605.00814","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:322a19187bf998355453bfee03ff61f13743f99b64d9a0a3727b11ebfd03c60e","observation_id":"ab342a4c-a017-47cc-8330-806b0a4e7fa8","resolution":{"observed_at":"2026-08-12T13:41:18.961944Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21523","last_updated":"2025-06-20T08:41:41Z","snapshot_observed_at":"2026-08-08T02:35:34.040619Z","submitted_at":"2025-05-23T05:08:40Z","title":"More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.21523","snapshot_observed_at":"2026-08-12T13:41:18.281795Z","title":"More thinking, less seeing? assessing amplified hallucination in multimodal reasoning models.arXiv preprint arXiv:2505.21523,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.281795Z"},"links":{"cited_paper":"/paper/2505.21523","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:42d451cf8de7ebfcf92d030793bd9d4d973e2f06e8e275c4dcbf238e2fb67f02","observation_id":"98dbb522-71ca-425e-8847-629ee301d9dc","resolution":{"observed_at":"2026-08-12T13:41:18.281795Z","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":"2026-08-12T13:41:18.284699Z","title":"Thinking in streaming video.arXiv preprint arXiv:2603.12938,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.284699Z"},"links":{"citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:5e035f6184c6e8fec78da95adef2df1d9d0365ca14e73e78b9a4fde90f7b6608","observation_id":"e7b46061-5870-43c3-9c72-f23524518fe7","resolution":{"observed_at":"2026-08-12T13:41:18.284699Z","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":"2026-08-12T13:41:18.287201Z","title":"From narrow to panoramic vision: Attention-guided cold-start reshapes multimodal reasoning.arXiv preprint arXiv:2603.03825,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.287201Z"},"links":{"citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:b4e86aa77e29f56b61c92a62b9f74c79429c08b34dc2379ddcac3758cc367f9c","observation_id":"5d9fc892-9d7c-46f0-ad06-54a620542ae4","resolution":{"observed_at":"2026-08-12T13:41:18.287201Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.07433","last_updated":"2026-06-05T16:29:13Z","snapshot_observed_at":"2026-08-01T21:05:06.439607Z","submitted_at":"2026-06-05T16:29:13Z","title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.07433","snapshot_observed_at":"2026-08-12T13:41:18.289865Z","title":"Watch, remember, reason: Human-view video understanding with mllms.arXiv preprint arXiv:2606.07433,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.289865Z"},"links":{"cited_paper":"/paper/2606.07433","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:eb825a96f20e7e89c8ffc33e0dc87e7ac45cdb67db953de6598321bc10033fb9","observation_id":"d613dd20-b8ac-47c9-abcb-98a6b7bc44a4","resolution":{"observed_at":"2026-08-12T13:41:18.289865Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.15269","last_updated":"2026-04-23T12:54:38Z","snapshot_observed_at":"2026-08-12T15:58:40.311449Z","submitted_at":"2025-05-21T08:47:15Z","title":"LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.15269","snapshot_observed_at":"2026-08-12T13:41:18.292557Z","title":"Livevlm: Efficient online video understanding via streaming-oriented kv cache and retrieval.arXiv preprint arXiv:2505.15269,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.292557Z"},"links":{"cited_paper":"/paper/2505.15269","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:e9df3c4313996d66c1e1e3d258bb1302ecd9659abec76c732dbb50bbb22e17c5","observation_id":"f39c948b-d36a-4df1-b9af-e742e4f5c2b1","resolution":{"observed_at":"2026-08-12T13:41:18.292557Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.02441","last_updated":"2025-04-24T01:47:25Z","snapshot_observed_at":"2026-08-09T08:18:07.362879Z","submitted_at":"2025-04-03T09:58:19Z","title":"Cognitive Memory in Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.02441","snapshot_observed_at":"2026-08-12T13:41:18.295276Z","title":"Cognitive memory in large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.295276Z"},"links":{"cited_paper":"/paper/2504.02441","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:d21fbeb59103d3c82303457c469a71b57cc3373a85cd3b60c98879686c7bb4ba","observation_id":"467e1f73-893f-4c17-8c33-a2f2ca882ae0","resolution":{"observed_at":"2026-08-12T13:41:18.295276Z","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":"2026-08-12T13:41:18.297989Z","title":"A simple baseline for streaming video understanding","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.297989Z"},"links":{"citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:8e96f6a42a121c7bab018f06a52be54b4cc47d4a8ff43e3b400f9ae228d27d93","observation_id":"e664415a-eecb-4e23-9bc8-97e84d482d64","resolution":{"observed_at":"2026-08-12T13:41:18.297989Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.25658","last_updated":"2026-06-24T10:11:08Z","snapshot_observed_at":"2026-08-13T04:50:24.738378Z","submitted_at":"2026-06-24T10:11:08Z","title":"Towards a Dynamic and Fixed-budget Memory Bank for Efficient Streaming Video Understanding","version":1},"cited_work":{"arxiv_id":"2606.25658","doi":null,"metadata_source":"pith","pith_arxiv_id":"2606.25658","snapshot_observed_at":"2026-08-12T13:41:18.732092Z","title":"Towards a Dynamic and Fixed-budget Memory Bank for Efficient Streaming Video Understanding","venue":"cs.CV","work_id":"c1173179-15f1-423b-951c-f79c05cc9419","year":2026},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.301746Z"},"links":{"cited_paper":"/paper/2606.25658","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:33e9d8e584cda4bf9938a420fc1f45726c53a4cc64237b0ce810d9ae92afcfce","observation_id":"6621e3a6-c0f0-4333-a277-a453b9263635","resolution":{"observed_at":"2026-08-12T13:41:18.737565Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.16449","last_updated":"2024-03-09T06:43:37Z","snapshot_observed_at":"2026-08-13T10:44:25.209833Z","submitted_at":"2023-07-31T07:15:45Z","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.16449","snapshot_observed_at":"2026-08-12T13:41:18.304786Z","title":"Moviechat: From dense token to sparse memory for long video understanding","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.304786Z"},"links":{"cited_paper":"/paper/2307.16449","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:0c58d075a286c9ab261efda28460ca3713e446042e3bdb56a48351291228b873","observation_id":"3c7e52cc-c906-400e-b98e-4059bff20dea","resolution":{"observed_at":"2026-08-12T13:41:18.304786Z","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":"2026-08-12T13:41:18.308685Z","title":"Onevision-encoder: Codec-aligned sparsity as a foundational principle for multimodal intelligence.arXiv preprint arXiv:2602.08683,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.308685Z"},"links":{"citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:7b0dcdfda2cde27f8434be98a1f60f5302ef2a702f9c15aaae4f3a9ef9a7d741","observation_id":"402009d1-7de0-4d48-ae41-802b9f3878f9","resolution":{"observed_at":"2026-08-12T13:41:18.308685Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2604.15804","last_updated":"2026-04-21T03:35:14Z","snapshot_observed_at":"2026-08-14T13:05:43.952056Z","submitted_at":"2026-04-17T08:05:46Z","title":"Qwen3.5-Omni Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.15804","snapshot_observed_at":"2026-08-12T13:41:18.310715Z","title":"Qwen3.5-omni technical report.arXiv preprint arXiv:2604.15804,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.310715Z"},"links":{"cited_paper":"/paper/2604.15804","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:e5e336538932259674ced0fe4a54316b3c4817d768ac04bc53f6746733e70358","observation_id":"4f894802-cbb2-479a-a837-2516dd55ef9b","resolution":{"observed_at":"2026-08-12T13:41:18.310715Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.09711","last_updated":"2024-05-15T21:53:54Z","snapshot_observed_at":"2026-08-13T05:15:32.116612Z","submitted_at":"2024-05-15T21:53:54Z","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.09711","snapshot_observed_at":"2026-08-12T13:41:18.313401Z","title":"Star: A benchmark for situated reasoning in real-world videos.arXiv preprint arXiv:2405.09711, 2024a","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.313401Z"},"links":{"cited_paper":"/paper/2405.09711","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:b3cca8b0996f2220bff5f69e7a7a95ee4b25802cabcdfe1870f2cd7257fa0390","observation_id":"3dbb8b18-2297-4d87-977c-404964afb82b","resolution":{"observed_at":"2026-08-12T13:41:18.313401Z","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":"2026-08-12T13:41:18.316272Z","title":"Fluxmem: Adaptive hierarchical memory for streaming video understanding.arXiv preprint arXiv:2603.02096,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.316272Z"},"links":{"citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:a3f53caa81ab5fe1ffda6756c7ffa8ae646e9f8901e044e4d6d65e0788a13a93","observation_id":"99926d73-898b-4527-aee8-a0b5e567742f","resolution":{"observed_at":"2026-08-12T13:41:18.316272Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.15717","last_updated":"2025-08-21T16:56:29Z","snapshot_observed_at":"2026-08-14T19:57:35.975349Z","submitted_at":"2025-08-21T16:56:29Z","title":"StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.15717","snapshot_observed_at":"2026-08-12T13:41:18.318833Z","title":"Streammem: Query-agnostic kv cache memory for streaming video understanding.arXiv preprint arXiv:2508.15717,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.318833Z"},"links":{"cited_paper":"/paper/2508.15717","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:977cf0f16454acf7db1dec0f34535cda85fd0b2fe4fb22377f314b05be229f0a","observation_id":"5de72ed4-3b1e-43e5-81aa-8e337e78dddf","resolution":{"observed_at":"2026-08-12T13:41:18.318833Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.01442","last_updated":"2020-03-08T00:09:07Z","snapshot_observed_at":"2026-07-06T08:26:38.349660Z","submitted_at":"2019-10-03T13:16:36Z","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.01442","snapshot_observed_at":"2026-08-12T13:41:18.322273Z","title":"Clevrer: Collision events for video representation and reasoning.arXiv preprint arXiv:1910.01442,","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.322273Z"},"links":{"cited_paper":"/paper/1910.01442","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:2237c6d2580fa5f6c78b76ad700387e117fa7f612d018e2708aebf35e9480bee","observation_id":"29b1fa53-0f43-4ecb-a1bf-f13b8aa445a4","resolution":{"observed_at":"2026-08-12T13:41:18.322273Z","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":"2026-08-12T13:41:18.327731Z","title":"Memory in large language models: Mechanisms, evaluation and evolution.arXiv preprint arXiv:2509.18868,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.327731Z"},"links":{"citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:2684069fc924978d889438b3ca5de82af43e90bc3a5c7d1ef941b560fae023bb","observation_id":"9851ac21-f80c-4e78-9fc0-eed4630eb564","resolution":{"observed_at":"2026-08-12T13:41:18.327731Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.14724","last_updated":"2026-05-07T12:10:26Z","snapshot_observed_at":"2026-08-14T13:28:17.763791Z","submitted_at":"2026-01-21T07:26:15Z","title":"HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.14724","snapshot_observed_at":"2026-08-12T13:41:18.330361Z","title":"Hermes: Kv cache as hierarchical memory for efficient streaming video understanding.arXiv preprint arXiv:2601.14724,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.330361Z"},"links":{"cited_paper":"/paper/2601.14724","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:39f2f7c67a0855e5e36f59f8ea94979c125c509b9f7871508d1c7f45d19d0963","observation_id":"41381c09-ebe1-42bd-a515-b018bf081605","resolution":{"observed_at":"2026-08-12T13:41:18.330361Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.02713","last_updated":"2025-08-01T16:40:14Z","snapshot_observed_at":"2026-08-02T12:24:31.329178Z","submitted_at":"2024-10-03T17:36:49Z","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.02713","snapshot_observed_at":"2026-08-12T13:41:18.333627Z","title":"Llava-video: Video instruction tuning with synthetic data.arXiv preprint arXiv:2410.02713,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.333627Z"},"links":{"cited_paper":"/paper/2410.02713","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:0c98d779cffcbb8155af33c3a6439684189c197faf4944c5cd03e7277c6c3c1f","observation_id":"2a5d28e1-bbf3-4168-b075-bbc0ab1929df","resolution":{"observed_at":"2026-08-12T13:41:18.333627Z","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":"2026-08-12T13:41:19.048741Z","title":"An empirical study on parameter-efficient fine-tuning for multimodal large language models","venue":null,"work_id":"c2e9c02b-1d08-4935-b077-2d796eb4d027","year":2024},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.336266Z"},"links":{"citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:98a539cfccd9c9f9e99c96c44498f36b54076d8d2e67b393f01dbe39c3ffccb9","observation_id":"d485687b-edc1-49ea-a8f4-b2df9a0002af","resolution":{"observed_at":"2026-08-12T13:41:19.051828Z","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":"2409.18938","last_updated":"2024-12-03T03:56:52Z","snapshot_observed_at":"2026-08-15T00:49:52.466345Z","submitted_at":"2024-09-27T17:38:36Z","title":"From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.18938","snapshot_observed_at":"2026-08-12T13:41:18.339565Z","title":"From seconds to hours: Reviewing multimodal large language models on comprehensive long video understanding.arXiv preprint arXiv:2409.18938,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.339565Z"},"links":{"cited_paper":"/paper/2409.18938","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:7472150a841c373462a0871dead88fd37435e4ca24bec23d866a18cc8a00c504","observation_id":"5f7ffbed-55c0-485d-86de-2473a4e3220b","resolution":{"observed_at":"2026-08-12T13:41:18.339565Z","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":"2026-08-12T13:41:19.040608Z","title":"Temporal distance, content similarity, and merge frequency determine event consolidation, while a spatiotemporal window stores recent observations","venue":null,"work_id":"e46cc8c9-3980-43dd-9c16-cb8fe0d565bd","year":2025},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.342896Z"},"links":{"citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:cd121d2528d7b5d858698f502408a250e92d2b3f13f58bcd10a4751124ef7337","observation_id":"4498e27e-bc6f-4f69-9315-ba2ee8c90af6","resolution":{"observed_at":"2026-08-12T13:41:19.043778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T13:41:18.325326Z","title":"Vismem: Latent vision memory unlocks potential of vision-language models.arXiv preprint arXiv:2511.11007,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.325326Z"},"links":{"citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:9710c1bdf2eebe7d07d7b675a95fec6bd0656b0908318d0f9cbc3ee792275b54","observation_id":"f28a5f30-cd14-4ed1-acbc-94f3bf4b851b","resolution":{"observed_at":"2026-08-12T13:41:18.325326Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.03186","last_updated":"2024-07-02T17:23:13Z","snapshot_observed_at":"2026-08-13T04:02:49.444355Z","submitted_at":"2024-03-05T18:22:29Z","title":"Cradle: Empowering Foundation Agents Towards General Computer Control","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.03186","snapshot_observed_at":"2026-08-12T13:41:18.306813Z","title":"Cradle: Empowering foundation agents towards general computer control.arXiv preprint arXiv:2403.03186,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.306813Z"},"links":{"cited_paper":"/paper/2403.03186","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:b002cc4a5af9f8b56887c6cdbc13c8801602fcc6173181ff5acc29717468eb7f","observation_id":"a83ce916-a411-424a-91c3-c6d956fcd28e","resolution":{"observed_at":"2026-08-12T13:41:18.306813Z","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":"2026-08-12T13:41:18.265663Z","title":"Scaling the long video understanding of multimodal large language models via visual memory mechanism.arXiv preprint arXiv:2603.29252, 2026a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.265663Z"},"links":{"citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:e071449fc5fbe2d4a09c6994fa48bb370f9f3044e1bad1ba3be581f1c4ad7dec","observation_id":"c8c77833-2295-4d9e-8f25-ec13a0c16f64","resolution":{"observed_at":"2026-08-12T13:41:18.265663Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.24164","last_updated":"2026-01-08T17:01:05Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-10-31T17:22:30Z","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.24164","snapshot_observed_at":"2026-08-12T13:41:18.263135Z","title":"arXiv preprint arXiv:2410.24164,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.263135Z"},"links":{"cited_paper":"/paper/2410.24164","citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:9bc603b3085f2d6f68eb49511bd1978c1b912e41f7fe7082a6a665382823509b","observation_id":"31876af5-e8af-43d7-b583-0fa72d3fcca7","resolution":{"observed_at":"2026-08-12T13:41:18.263135Z","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":"2026-08-12T13:41:19.056709Z","title":"Streamingbench: Assessing the gap for mllms to achieve streaming video understanding","venue":null,"work_id":"37196fed-1a7f-4482-ab03-9f096e3c1e17","year":2026},"citing_paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","version":1},"reference_index":2026,"source":"pdf_text","source_observed_at":"2026-08-12T13:41:18.279236Z"},"links":{"citing_paper":"/paper/2608.10949"},"observation_digest":"sha256:a3f199bac304e3fa251daf7ba6068d4e537b3ebb115f85fcb9fc992ef8d70993","observation_id":"5ec7a7b3-3b96-4d15-bdf7-0acf7f6473da","resolution":{"observed_at":"2026-08-12T13:41:19.059737Z","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"}}],"paper":{"arxiv_id":"2608.10949","last_updated":"2026-08-11T14:19:03Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T05:55:45.139118Z","submitted_at":"2026-08-11T14:19:03Z","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding"},"reference_resolution":{"displayed":30,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":2,"verified_fuzzy":4},"total_outbound_references":30},"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 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2608.10949."}