{"as_of":"2026-08-16T17:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3c1659ea1493ff988b658d1ef37082e5239fcdbf440f14cf0e41e647cc1ae626","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":13,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":13,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":13,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":13,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T20:27:20.034849Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":1,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2408.15881","last_updated":"2024-10-23T09:52:23Z","snapshot_observed_at":"2026-08-16T13:23:10.403709Z","submitted_at":"2024-08-28T15:52:23Z","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.15881","snapshot_observed_at":"2026-08-12T20:27:20.034849Z","title":"Llava-mod: Making llava tiny via moe knowledge distillation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.09691","last_updated":"2024-11-14T18:57:07Z","snapshot_observed_at":"2026-08-12T20:20:39.448843Z","submitted_at":"2024-11-14T18:57:07Z","title":"Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T20:27:20.034849Z"},"links":{"cited_paper":"/paper/2408.15881","citing_paper":"/paper/2411.09691"},"observation_digest":"sha256:548ca845868329d932dca9fc0bcf3f4dc1d9d70a49f4952aad07fa37cbbca9f4","observation_id":"acfa3182-69dd-4561-a30b-55dd8f13133e","resolution":{"observed_at":"2026-08-12T20:27:20.034849Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15881","last_updated":"2024-10-23T09:52:23Z","snapshot_observed_at":"2026-08-16T13:23:10.403709Z","submitted_at":"2024-08-28T15:52:23Z","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.15881","snapshot_observed_at":"2026-08-12T04:33:06.994664Z","title":"Llava-mod: Making llava tiny via moe knowledge distillation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01282","last_updated":"2026-06-02T02:45:47Z","snapshot_observed_at":"2026-08-16T05:39:37.807645Z","submitted_at":"2024-12-02T08:55:19Z","title":"Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T04:33:06.994664Z"},"links":{"cited_paper":"/paper/2408.15881","citing_paper":"/paper/2412.01282"},"observation_digest":"sha256:53b734d5ff50a308d617f12ff7b127730cc14ee7d8a078d207d682f9abd87e18","observation_id":"a5b5d26a-1878-4011-ad18-6a00bb4f94fa","resolution":{"observed_at":"2026-08-12T04:33:06.994664Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15881","last_updated":"2024-10-23T09:52:23Z","snapshot_observed_at":"2026-08-16T13:23:10.403709Z","submitted_at":"2024-08-28T15:52:23Z","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.15881","snapshot_observed_at":"2026-08-11T12:44:35.970232Z","title":"Llava-mod: Making llava tiny via moe knowledge distillation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.14219","last_updated":"2025-01-22T03:33:25Z","snapshot_observed_at":"2026-08-13T23:36:29.207493Z","submitted_at":"2024-12-18T14:11:15Z","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","version":2},"reference_index":163,"source":"pdf_text","source_observed_at":"2026-08-11T12:44:35.970232Z"},"links":{"cited_paper":"/paper/2408.15881","citing_paper":"/paper/2412.14219"},"observation_digest":"sha256:5935dd9282faddce60f05b707e394406cba5c5e38149318bd110d8ff89258839","observation_id":"e505e7ca-399f-44ae-a671-5f0d2efe47f9","resolution":{"observed_at":"2026-08-11T12:44:35.970232Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15881","last_updated":"2024-10-23T09:52:23Z","snapshot_observed_at":"2026-08-16T13:23:10.403709Z","submitted_at":"2024-08-28T15:52:23Z","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.15881","snapshot_observed_at":"2026-08-10T22:27:13.611917Z","title":"Llava-mod: Making llava tiny via moe knowledge distillation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01709","last_updated":"2025-03-18T07:34:44Z","snapshot_observed_at":"2026-08-15T13:36:27.630577Z","submitted_at":"2025-01-03T09:10:34Z","title":"MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T22:27:13.611917Z"},"links":{"cited_paper":"/paper/2408.15881","citing_paper":"/paper/2501.01709"},"observation_digest":"sha256:c8dbcd1a05510cac3bed6092a8a9a3de613f5d047f1223f3ed403c5f23139309","observation_id":"1fb87df2-bf6a-4d24-86d2-b06f143106d1","resolution":{"observed_at":"2026-08-10T22:27:13.611917Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15881","last_updated":"2024-10-23T09:52:23Z","snapshot_observed_at":"2026-08-16T13:23:10.403709Z","submitted_at":"2024-08-28T15:52:23Z","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.15881","snapshot_observed_at":"2026-08-10T22:08:35.051307Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.02795","last_updated":"2025-02-17T03:49:14Z","snapshot_observed_at":"2026-08-13T14:51:28.608016Z","submitted_at":"2025-01-06T06:29:55Z","title":"InfiFusion: A Unified Framework for Enhanced Cross-Model Reasoning via LLM Fusion","version":3},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-10T22:08:35.051307Z"},"links":{"cited_paper":"/paper/2408.15881","citing_paper":"/paper/2501.02795"},"observation_digest":"sha256:0fb5ff4aeb53469a4411d298206c1c407e5da1dbe5ad2c1611a0d9f3adf5641a","observation_id":"8dbb2853-d0f2-41ad-a8d6-9881a01f0b1d","resolution":{"observed_at":"2026-08-10T22:08:35.051307Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15881","last_updated":"2024-10-23T09:52:23Z","snapshot_observed_at":"2026-08-16T13:23:10.403709Z","submitted_at":"2024-08-28T15:52:23Z","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.15881","snapshot_observed_at":"2026-08-07T12:09:07.514859Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00479","last_updated":"2025-05-31T09:10:43Z","snapshot_observed_at":"2026-08-09T06:24:07.358275Z","submitted_at":"2025-05-31T09:10:43Z","title":"EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T12:09:07.514859Z"},"links":{"cited_paper":"/paper/2408.15881","citing_paper":"/paper/2506.00479"},"observation_digest":"sha256:46fcd8542759e7f95b390b6933f606ccb2cf85ca56a8366af6d076c519a5bfac","observation_id":"02e740a3-e6a5-40af-9e5b-e2df760632d3","resolution":{"observed_at":"2026-08-07T12:09:07.514859Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15881","last_updated":"2024-10-23T09:52:23Z","snapshot_observed_at":"2026-08-16T13:23:10.403709Z","submitted_at":"2024-08-28T15:52:23Z","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.15881","snapshot_observed_at":"2026-08-07T11:57:29.197574Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.01049","last_updated":"2025-06-01T15:30:37Z","snapshot_observed_at":"2026-08-10T09:29:02.275732Z","submitted_at":"2025-06-01T15:30:37Z","title":"Taming LLMs by Scaling Learning Rates with Gradient Grouping","version":1},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-07T11:57:29.197574Z"},"links":{"cited_paper":"/paper/2408.15881","citing_paper":"/paper/2506.01049"},"observation_digest":"sha256:e460a5f65e3f0547fa520c3de30f54e0bd807549ae75c828d672990bffa1d759","observation_id":"e5acd949-8072-4ba1-91a2-67b0f7a43217","resolution":{"observed_at":"2026-08-07T11:57:29.197574Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15881","last_updated":"2024-10-23T09:52:23Z","snapshot_observed_at":"2026-08-16T13:23:10.403709Z","submitted_at":"2024-08-28T15:52:23Z","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.15881","snapshot_observed_at":"2026-08-06T23:57:25.601970Z","title":"arXiv preprint arXiv:2408.15881 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.15681","last_updated":"2026-06-25T14:33:27Z","snapshot_observed_at":"2026-08-08T08:54:57.204006Z","submitted_at":"2025-06-18T17:59:49Z","title":"GenRecal: Generation after Recalibration from Large to Small Vision-Language Models","version":4},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-06T23:57:25.601970Z"},"links":{"cited_paper":"/paper/2408.15881","citing_paper":"/paper/2506.15681"},"observation_digest":"sha256:2aaa5af5d46a09822590c0d0e42327e70d12fc8b6a4968e2b077731ad035ff47","observation_id":"d467dccd-ba5d-42c6-be9e-3dd45878b382","resolution":{"observed_at":"2026-08-06T23:57:25.601970Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15881","last_updated":"2024-10-23T09:52:23Z","snapshot_observed_at":"2026-08-16T13:23:10.403709Z","submitted_at":"2024-08-28T15:52:23Z","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.15881","snapshot_observed_at":"2026-08-03T21:09:24.726089Z","title":"Llava-mod: Making llava tiny via moe knowledge distillation.arXiv preprint arXiv:2408.15881, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.16672","last_updated":"2026-06-09T22:19:41Z","snapshot_observed_at":"2026-08-15T17:58:47.718751Z","submitted_at":"2025-11-20T18:59:54Z","title":"EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards","version":4},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T21:09:24.726089Z"},"links":{"cited_paper":"/paper/2408.15881","citing_paper":"/paper/2511.16672"},"observation_digest":"sha256:66770396429e04dd68bd1f7c1da34f3708d08287b00ea625ec3fa9496f9e07ac","observation_id":"99b1b392-0dc2-4e2c-9b1c-36795ad393c0","resolution":{"observed_at":"2026-08-03T21:09:24.726089Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15881","last_updated":"2024-10-23T09:52:23Z","snapshot_observed_at":"2026-08-16T13:23:10.403709Z","submitted_at":"2024-08-28T15:52:23Z","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","version":3},"cited_work":{"arxiv_id":"2408.15881","doi":"10.48550/arxiv.2408.15881","metadata_source":"arxiv_reference","pith_arxiv_id":"2408.15881","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Llava-mod: Making llava tiny via moe knowledge distillation.arXiv preprint arXiv:2408.15881","venue":"arXiv (Cornell University)","work_id":"9dbe8839-1c57-413a-84ec-643f71b1c1fb","year":2024},"citing_paper":{"arxiv_id":"2604.14629","last_updated":"2026-04-16T05:13:57Z","snapshot_observed_at":"2026-08-14T10:07:40.756198Z","submitted_at":"2026-04-16T05:13:57Z","title":"Switch-KD: Visual-Switch Knowledge Distillation for Vision-Language Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-10T11:23:46.371799Z"},"links":{"cited_paper":"/paper/2408.15881","citing_paper":"/paper/2604.14629"},"observation_digest":"sha256:1c1c6c620f79ac5c96e2e8f109a9750911ba4e5a03c9ea938910cef90573f134","observation_id":"c331b021-49dd-449b-9275-653f29f25331","resolution":{"observed_at":"2026-05-10T11:25:18.526409Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15881","last_updated":"2024-10-23T09:52:23Z","snapshot_observed_at":"2026-08-16T13:23:10.403709Z","submitted_at":"2024-08-28T15:52:23Z","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","version":3},"cited_work":{"arxiv_id":"2408.15881","doi":"10.48550/arxiv.2408.15881","metadata_source":"arxiv_reference","pith_arxiv_id":"2408.15881","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Llava-mod: Making llava tiny via moe knowledge distillation.arXiv preprint arXiv:2408.15881","venue":"arXiv (Cornell University)","work_id":"9dbe8839-1c57-413a-84ec-643f71b1c1fb","year":2024},"citing_paper":{"arxiv_id":"2604.21027","last_updated":"2026-08-02T16:15:42Z","snapshot_observed_at":"2026-08-10T23:41:30.183421Z","submitted_at":"2026-04-22T19:18:36Z","title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","version":1},"reference_index":214,"source":"arxiv_source","source_observed_at":"2026-05-09T23:51:47.724033Z"},"links":{"cited_paper":"/paper/2408.15881","citing_paper":"/paper/2604.21027"},"observation_digest":"sha256:c0d77e28cf4c4e426af64ab270028ed9b77b90c9112d20e48b1ff782bbdf2173","observation_id":"5b68943e-0271-48d1-8a18-f01ccad88700","resolution":{"observed_at":"2026-05-09T23:54:45.348826Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15881","last_updated":"2024-10-23T09:52:23Z","snapshot_observed_at":"2026-08-16T13:23:10.403709Z","submitted_at":"2024-08-28T15:52:23Z","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","version":3},"cited_work":{"arxiv_id":"2408.15881","doi":"10.48550/arxiv.2408.15881","metadata_source":"arxiv_reference","pith_arxiv_id":"2408.15881","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Llava-mod: Making llava tiny via moe knowledge distillation.arXiv preprint arXiv:2408.15881","venue":"arXiv (Cornell University)","work_id":"9dbe8839-1c57-413a-84ec-643f71b1c1fb","year":2024},"citing_paper":{"arxiv_id":"2606.05718","last_updated":"2026-06-04T05:18:13Z","snapshot_observed_at":"2026-08-13T06:21:31.612832Z","submitted_at":"2026-06-04T05:18:13Z","title":"ViCuR: Visual Cues as Recoverable Privilege for Multimodal On-Policy Distillation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-28T01:59:15.154873Z"},"links":{"cited_paper":"/paper/2408.15881","citing_paper":"/paper/2606.05718"},"observation_digest":"sha256:8e5010e84b6ebe7c214eb4cb8165b3a301568f42487fbad2d0331d1b5072bf6d","observation_id":"52144856-6287-4cda-93d6-004ee972db3e","resolution":{"observed_at":"2026-07-02T12:36:57.017799Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15881","last_updated":"2024-10-23T09:52:23Z","snapshot_observed_at":"2026-08-16T13:23:10.403709Z","submitted_at":"2024-08-28T15:52:23Z","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.15881","snapshot_observed_at":"2026-08-08T00:55:50.120232Z","title":"Llava-mod: Making llava tiny via moe knowledge distillation.arXiv preprint arXiv:2408.15881,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.03112","last_updated":"2026-08-04T04:32:48Z","snapshot_observed_at":"2026-08-14T08:05:42.865502Z","submitted_at":"2026-08-04T04:32:48Z","title":"Adaptive Two-Stage Visual Token Pruning for Efficient Inference in Video-Language Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-08T00:55:50.120232Z"},"links":{"cited_paper":"/paper/2408.15881","citing_paper":"/paper/2608.03112"},"observation_digest":"sha256:e6a83182cb48793c610f17a9cd3da7650d4ee2da64fbb6f5e02e79015ab28d61","observation_id":"afb7bdd5-f0d4-4314-9070-1171eb84c3f4","resolution":{"observed_at":"2026-08-08T00:55:50.120232Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2408.15881/citation-record","integrity":"/paper/2408.15881/integrity","json":"/paper/2408.15881/citation-record.json","paper":"/paper/2408.15881"},"outbound":[],"paper":{"arxiv_id":"2408.15881","last_updated":"2024-10-23T09:52:23Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T13:23:10.403709Z","submitted_at":"2024-08-28T15:52:23Z","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 13 inbound Pith citation observations for arXiv:2408.15881."}