{"as_of":"2026-08-14T13:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:06052f546ae023e34c3fea1742f2431e53a3d3d524450410949b26ef18ed877f","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":"2026-08-14T06:32:32.682623+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":"2026-08-11T17:55:13.575770Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-10T22:57:23.723001Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.07904","last_updated":"2024-12-09T05:45:00Z","snapshot_observed_at":"2026-08-14T06:48:24.510311Z","submitted_at":"2024-06-12T06:12:04Z","title":"Grounding Multimodal Large Language Models in Actions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07904","snapshot_observed_at":"2026-08-11T17:55:13.575770Z","title":"Grounding mul- timodal large language models in actions","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08442","last_updated":"2024-12-11T15:06:25Z","snapshot_observed_at":"2026-08-11T17:46:57.888519Z","submitted_at":"2024-12-11T15:06:25Z","title":"From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-11T17:55:13.575770Z"},"links":{"cited_paper":"/paper/2406.07904","citing_paper":"/paper/2412.08442"},"observation_digest":"sha256:1ca7ff87580d6d1b78ede4a4c51fe5238c1fb1d3c49189298f30de22fa65a171","observation_id":"993975e1-c0fb-4c98-9b8c-74b390afadb6","resolution":{"observed_at":"2026-08-11T17:55:13.575770Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07904","last_updated":"2024-12-09T05:45:00Z","snapshot_observed_at":"2026-08-14T06:48:24.510311Z","submitted_at":"2024-06-12T06:12:04Z","title":"Grounding Multimodal Large Language Models in Actions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07904","snapshot_observed_at":"2026-08-11T11:22:41.405361Z","title":"Grounding multimodal large language models in actions,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.15576","last_updated":"2025-05-27T07:05:44Z","snapshot_observed_at":"2026-08-12T05:19:00.568745Z","submitted_at":"2024-12-20T05:17:06Z","title":"QUART-Online: Latency-Free Large Multimodal Language Model for Quadruped Robot Learning","version":5},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T11:22:41.405361Z"},"links":{"cited_paper":"/paper/2406.07904","citing_paper":"/paper/2412.15576"},"observation_digest":"sha256:50b30015da7eeec4b81dd7a6d0d9e3e4118ef1741cf7d6f21e6c88b37c494a52","observation_id":"2608c188-55e2-4c61-b7e3-fa4c413ad1dd","resolution":{"observed_at":"2026-08-11T11:22:41.405361Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07904","last_updated":"2024-12-09T05:45:00Z","snapshot_observed_at":"2026-08-14T06:48:24.510311Z","submitted_at":"2024-06-12T06:12:04Z","title":"Grounding Multimodal Large Language Models in Actions","version":2},"cited_work":{"arxiv_id":"2406.07904","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.07904","snapshot_observed_at":"2026-08-10T22:57:23.723001Z","title":"Grounding Multimodal Large Language Models in Actions","venue":"cs.LG","work_id":"4fb49e51-65af-48b8-962d-1983c6041f8d","year":2024},"citing_paper":{"arxiv_id":"2501.00398","last_updated":"2025-04-03T01:09:23Z","snapshot_observed_at":"2026-08-14T03:25:53.634177Z","submitted_at":"2024-12-31T11:27:17Z","title":"TSPE: Task-Specific Prompt Ensemble for Improved Zero-Shot Audio Classification","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T22:57:23.676860Z"},"links":{"cited_paper":"/paper/2406.07904","citing_paper":"/paper/2501.00398"},"observation_digest":"sha256:c8665561a1bd1d17759c021aa744d9f734801b65a74c307ab1639abd67f1cdf0","observation_id":"806f129c-24c2-4a50-bb8f-8c3a2313824c","resolution":{"observed_at":"2026-08-10T22:57:23.729374Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2406.07904/citation-record","integrity":"/paper/2406.07904/integrity","json":"/paper/2406.07904/citation-record.json","paper":"/paper/2406.07904"},"outbound":[],"paper":{"arxiv_id":"2406.07904","last_updated":"2024-12-09T05:45:00Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T06:48:24.510311Z","submitted_at":"2024-06-12T06:12:04Z","title":"Grounding Multimodal Large Language Models in Actions"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2406.07904."}