{"as_of":"2026-08-09T14:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dcf4714268f0fc456befc99e264a7d66f1f5d36cba41cabee8ede4a882bfee36","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T10:50:59.522064Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-16T18:48:17.204802Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.10385","last_updated":"2024-09-29T06:53:40Z","snapshot_observed_at":"2026-08-04T07:08:08.900324Z","submitted_at":"2024-07-15T01:33:54Z","title":"By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.10385","snapshot_observed_at":"2026-08-09T10:50:59.522064Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.02883","last_updated":"2025-07-18T23:00:52Z","snapshot_observed_at":"2026-08-09T10:44:34.499829Z","submitted_at":"2025-02-05T04:41:59Z","title":"SensorChat: Answering Qualitative and Quantitative Questions during Long-Term Multimodal Sensor Interactions","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-09T10:50:59.522064Z"},"links":{"cited_paper":"/paper/2407.10385","citing_paper":"/paper/2502.02883"},"observation_digest":"sha256:2e4e3aa272d92544d4aa2ddfbf6ad8a91644b54c805b8d6a076170c98b2dc788","observation_id":"67cbc23c-daaf-43be-8252-b0652ba7a3b4","resolution":{"observed_at":"2026-08-09T10:50:59.522064Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10385","last_updated":"2024-09-29T06:53:40Z","snapshot_observed_at":"2026-08-04T07:08:08.900324Z","submitted_at":"2024-07-15T01:33:54Z","title":"By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.10385","snapshot_observed_at":"2026-08-08T12:14:20.410753Z","title":"By my eyes: Grounding multimodal large language models with sensor data via visual prompting","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.07608","last_updated":"2025-04-28T18:35:59Z","snapshot_observed_at":"2026-08-08T12:07:20.049894Z","submitted_at":"2025-02-11T14:58:54Z","title":"Time2Lang: Bridging Time-Series Foundation Models and Large Language Models for Health Sensing Beyond Prompting","version":3},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-08T12:14:20.410753Z"},"links":{"cited_paper":"/paper/2407.10385","citing_paper":"/paper/2502.07608"},"observation_digest":"sha256:0fd3eee9fbe4ca22050e66853cc61f4d1d4450e1d17e3e16b5bb97dc368747f1","observation_id":"86ec7702-2def-4a6e-85f1-eb67fbd5026d","resolution":{"observed_at":"2026-08-08T12:14:20.410753Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10385","last_updated":"2024-09-29T06:53:40Z","snapshot_observed_at":"2026-08-04T07:08:08.900324Z","submitted_at":"2024-07-15T01:33:54Z","title":"By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting","version":2},"cited_work":{"arxiv_id":"2407.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.10385","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Kailai Yang, Tianlin Zhang, Ziyan Kuang, Qianqian Xie, Jimin Huang, and Sophia Ananiadou","venue":null,"work_id":"f3139d84-b096-4ab6-914d-fcd8203b9599","year":2024},"citing_paper":{"arxiv_id":"2512.23025","last_updated":"2026-05-08T21:30:15Z","snapshot_observed_at":"2026-07-06T22:40:12.666349Z","submitted_at":"2025-12-28T18:00:57Z","title":"LENS: LLM-Enabled Narrative Synthesis for Mental Health by Aligning Multimodal Sensing with Language Models","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-16T18:46:45.455333Z"},"links":{"cited_paper":"/paper/2407.10385","citing_paper":"/paper/2512.23025"},"observation_digest":"sha256:501e26cb2b38b16b14bf42e36d03c270fd321af71dae30f2ff41ad46620cc439","observation_id":"e50ae3c4-1777-4649-9969-ebeb8cdbb092","resolution":{"observed_at":"2026-05-16T18:48:17.207135Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2407.10385/citation-record","integrity":"/paper/2407.10385/integrity","json":"/paper/2407.10385/citation-record.json","paper":"/paper/2407.10385"},"outbound":[],"paper":{"arxiv_id":"2407.10385","last_updated":"2024-09-29T06:53:40Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-04T07:08:08.900324Z","submitted_at":"2024-07-15T01:33:54Z","title":"By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2407.10385."}