{"as_of":"2026-08-08T18:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:49785a1874c740d6749004d8ac242b41922520b65b4e74925f43d30b73ca5868","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":"2026-08-08T06:32:00.761636+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":"2026-08-06T22:36:45.463037Z","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":"2026-08-06T18:21:51.394587Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.05047","last_updated":"2024-10-07T14:05:05Z","snapshot_observed_at":"2026-07-06T18:42:22.322763Z","submitted_at":"2024-07-06T11:07:18Z","title":"MFE-ETP: A Comprehensive Evaluation Benchmark for Multi-modal Foundation Models on Embodied Task Planning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.05047","snapshot_observed_at":"2026-08-06T22:36:45.463037Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.21252","last_updated":"2025-06-26T13:36:12Z","snapshot_observed_at":"2026-08-07T12:39:14.206067Z","submitted_at":"2025-06-26T13:36:12Z","title":"Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-06T22:36:45.463037Z"},"links":{"cited_paper":"/paper/2407.05047","citing_paper":"/paper/2506.21252"},"observation_digest":"sha256:60b17cda62d4cb0eb5234e297cf93150c579b9b42b36a4bb81ed702662171d0e","observation_id":"b81944de-802d-48d4-8d7c-31505eeed8c7","resolution":{"observed_at":"2026-08-06T22:36:45.463037Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.05047","last_updated":"2024-10-07T14:05:05Z","snapshot_observed_at":"2026-07-06T18:42:22.322763Z","submitted_at":"2024-07-06T11:07:18Z","title":"MFE-ETP: A Comprehensive Evaluation Benchmark for Multi-modal Foundation Models on Embodied Task Planning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.05047","snapshot_observed_at":"2026-08-06T18:30:47.297006Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.08224","last_updated":"2025-07-20T05:22:14Z","snapshot_observed_at":"2026-08-06T18:21:12.044757Z","submitted_at":"2025-07-11T00:17:08Z","title":"Making VLMs More Robot-Friendly: Self-Critical Distillation of Low-Level Procedural Reasoning","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-06T18:30:47.297006Z"},"links":{"cited_paper":"/paper/2407.05047","citing_paper":"/paper/2507.08224"},"observation_digest":"sha256:3867bc91bb6873474f3aaa087ade99164f5571b26b9c27b910bb4ab4030ab856","observation_id":"ffe80c4a-9cbe-46a0-928f-bbf1bbccbf3f","resolution":{"observed_at":"2026-08-06T18:30:47.297006Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.05047","last_updated":"2024-10-07T14:05:05Z","snapshot_observed_at":"2026-07-06T18:42:22.322763Z","submitted_at":"2024-07-06T11:07:18Z","title":"MFE-ETP: A Comprehensive Evaluation Benchmark for Multi-modal Foundation Models on Embodied Task Planning","version":3},"cited_work":{"arxiv_id":"2407.05047","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.05047","snapshot_observed_at":"2026-08-06T18:21:51.394587Z","title":"MFE-ETP: A Comprehensive Evaluation Benchmark for Multi-modal Foundation Models on Embodied Task Planning","venue":"cs.AI","work_id":"360a3059-d653-44f8-b358-9d20b27f9bba","year":2024},"citing_paper":{"arxiv_id":"2507.08496","last_updated":"2025-07-11T11:18:49Z","snapshot_observed_at":"2026-08-06T18:14:37.908727Z","submitted_at":"2025-07-11T11:18:49Z","title":"LLaPa: A Vision-Language Model Framework for Counterfactual-Aware Procedural Planning","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T18:21:50.906222Z"},"links":{"cited_paper":"/paper/2407.05047","citing_paper":"/paper/2507.08496"},"observation_digest":"sha256:d5488bab549a8e385d1bf42bc9cb30462364dfb2c42deff58485989887d5b4fb","observation_id":"abfef92a-a834-42a1-8574-f0094014b7cb","resolution":{"observed_at":"2026-08-06T18:21:51.459545Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2407.05047/citation-record","integrity":"/paper/2407.05047/integrity","json":"/paper/2407.05047/citation-record.json","paper":"/paper/2407.05047"},"outbound":[],"paper":{"arxiv_id":"2407.05047","last_updated":"2024-10-07T14:05:05Z","latest_version":3,"primary_category":"cs.AI","snapshot_observed_at":"2026-07-06T18:42:22.322763Z","submitted_at":"2024-07-06T11:07:18Z","title":"MFE-ETP: A Comprehensive Evaluation Benchmark for Multi-modal Foundation Models on Embodied Task Planning"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2407.05047."}