{"as_of":"2026-08-12T21:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5f0a6cccd761a3e6fb57b9b11fcb5620cb6c4a44cec07c4cd752d82d3f6ba430","coverage":[{"denominator":51,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":51,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T00:47:48.648554Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+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/2608.07905/citation-record","integrity":"/paper/2608.07905/integrity","json":"/paper/2608.07905/citation-record.json","paper":"/paper/2608.07905"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.18194","last_updated":"2024-12-24T06:03:42Z","snapshot_observed_at":"2026-08-11T04:54:18.910403Z","submitted_at":"2024-12-24T06:03:42Z","title":"VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.18194","snapshot_observed_at":"2026-08-12T00:47:48.475113Z","title":"Vlabench: A large-scale benchmark for language- conditioned robotics manipulation with long-horizon reasoning tasks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.475113Z"},"links":{"cited_paper":"/paper/2412.18194","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:1f58863b06e97f88300236023282b4fe009d6c2aee617286a80f8b4283406321","observation_id":"d0d2ef7b-364e-4d66-b04f-60f0462db2ae","resolution":{"observed_at":"2026-08-12T00:47:48.475113Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07548","last_updated":"2024-03-13T02:31:47Z","snapshot_observed_at":"2026-08-12T14:17:30.146697Z","submitted_at":"2024-03-12T11:33:48Z","title":"Online Continual Learning For Interactive Instruction Following Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.07548","snapshot_observed_at":"2026-08-12T00:47:48.479233Z","title":"Online continual learning for interactive instruction following agents,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.479233Z"},"links":{"cited_paper":"/paper/2403.07548","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:6372e270a4da85574b30159cad31dae67705fcfe8da4d78c4d63ffa0fbf406d5","observation_id":"097511db-190b-4f7e-8bd2-a90f9e37e9d7","resolution":{"observed_at":"2026-08-12T00:47:48.479233Z","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":"2026-08-12T00:47:49.294304Z","title":"Realfred: An embodied instruction following benchmark in photo-realistic environ- ments,","venue":null,"work_id":"a8e204bd-0303-4c3a-81cc-ff5f0bea2878","year":2024},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.483300Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:56c75128cae9810976f384b27dae5cfcbcd792f58eb03f4f378eb64968be6c07","observation_id":"f08937cc-b295-4d44-b2b2-66d90af0f2d7","resolution":{"observed_at":"2026-08-12T00:47:49.299953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.03232","last_updated":"2025-08-05T09:01:47Z","snapshot_observed_at":"2026-08-11T15:49:16.913082Z","submitted_at":"2025-08-05T09:01:47Z","title":"CookBench: A Long-Horizon Embodied Planning Benchmark for Complex Cooking Scenarios","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.03232","snapshot_observed_at":"2026-08-12T00:47:48.486961Z","title":"Cookbench: A long-horizon embodied planning benchmark for complex cooking scenarios,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.486961Z"},"links":{"cited_paper":"/paper/2508.03232","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:89cf7a74dd97052c8e2d552c22b0c2f3c88ff98c498f48a001015e8b6bbc2a6b","observation_id":"4aceb509-dd17-4f70-8f1c-9035a34f0944","resolution":{"observed_at":"2026-08-12T00:47:48.486961Z","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":"2026-08-12T00:47:49.284002Z","title":"Episodic transformer for vision- and-language navigation,","venue":null,"work_id":"6fb7cd7c-1eed-4c8e-beca-2d919cf82449","year":2021},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.490925Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:6df817082baecd9a3f3cefebf2f742bc845c91009623ae160308f9b37c54b2fa","observation_id":"ff889581-33ff-4bc6-b911-d5d92e7f1e10","resolution":{"observed_at":"2026-08-12T00:47:49.287451Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:47:49.273233Z","title":"Look wide and interpret twice: Improving performance on interactive instruction-following tasks,","venue":null,"work_id":"3b6ee7ea-cd5c-4a66-8348-b0660bedcdef","year":null},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.494194Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:b29643f730cfa20b55443a8f5b60670c64b8865c482d168405fbf6ccb20e42cc","observation_id":"9b2fd8d0-111a-40bf-bf0b-052e3e872603","resolution":{"observed_at":"2026-08-12T00:47:49.276738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:47:49.250953Z","title":"Spoc: Imitating shortest paths in simulation enables effective navigation and manipulation in the real world,","venue":null,"work_id":"3d6f0472-d5ae-48ba-b609-ec38914251b9","year":2024},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.501457Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:7f5cbb1a38dd4060058001c59b1a818869daa371489ddc96afaa16d847986f78","observation_id":"261e35c5-8818-4eb4-ba0e-c06c54249edc","resolution":{"observed_at":"2026-08-12T00:47:49.255065Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.07342","last_updated":"2022-03-16T22:46:34Z","snapshot_observed_at":"2026-08-12T14:17:39.575928Z","submitted_at":"2021-10-12T16:40:01Z","title":"FILM: Following Instructions in Language with Modular Methods","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.07342","snapshot_observed_at":"2026-08-12T00:47:48.505126Z","title":"Film: Following instructions in language with modular methods,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.505126Z"},"links":{"cited_paper":"/paper/2110.07342","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:2fe0c3ac708a6437c741356bfe68cd870ba6c88128724a39f52cd788b1e8f591","observation_id":"19897148-1787-4388-9560-2298d77a535c","resolution":{"observed_at":"2026-08-12T00:47:48.505126Z","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":"2026-08-12T00:47:49.239316Z","title":"Multi-level compositional reason- ing for interactive instruction following,","venue":null,"work_id":"f9222720-415c-48f9-9c1d-ae922bfe002d","year":2023},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.508888Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:eb87304418d12c323fc026c812d0f710991e9993cbd151cb22f21994c34132c1","observation_id":"3ed32068-53fd-4fe5-b5fc-aefbfdfd90f9","resolution":{"observed_at":"2026-08-12T00:47:49.243112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:47:49.227934Z","title":"Disco: Embodied navigation and interaction via differentiable scene semantics and dual-level control,","venue":null,"work_id":"47542a33-ca62-46bf-80fb-ffc1b035a815","year":2024},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.512206Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:23e305a5e9fc7f78b2d002754ca73422d37e7eca04ef5b33a169004da261be7d","observation_id":"96d588f2-abab-42cb-8691-b49ed2a0e5b1","resolution":{"observed_at":"2026-08-12T00:47:49.232017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:47:49.216566Z","title":"Multi-modal grounded planning and efficient replanning for learning embodied agents with a few examples,","venue":null,"work_id":"18e7424c-a074-470c-ba05-84b1e88d7ae9","year":2025},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.516021Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:57440cb68d474dd90452dce782004bc55235aee29db75b27cf8fa96d276f6b51","observation_id":"ce783213-92ad-4999-a78b-b8dc0fdcf13c","resolution":{"observed_at":"2026-08-12T00:47:49.220293Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.01691","last_updated":"2022-08-16T16:06:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-04T17:57:11Z","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.01691","snapshot_observed_at":"2026-08-12T00:47:48.519648Z","title":"Do as i can, not as i say: Grounding language in robotic affordances,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.519648Z"},"links":{"cited_paper":"/paper/2204.01691","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:403efe2f1ca7a41fad6b7f4072a514ce1c4ae50ab9a7ed9be54834484e63cd7a","observation_id":"9211e4e5-769e-4daf-8915-e15f3c6ea373","resolution":{"observed_at":"2026-08-12T00:47:48.519648Z","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":"2026-08-12T00:47:49.205449Z","title":"Progprompt: Generating situated robot task plans using large language models,","venue":null,"work_id":"1cfc0327-fbac-446e-9122-669d0cd08229","year":2023},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.523776Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:4cce4a384b1c929a2cf0771c1a89ad6e7d3eda5edca1542eb2e505380a04f907","observation_id":"c8d4faaa-b1d5-44dc-b4e2-70b1d7e05ae6","resolution":{"observed_at":"2026-08-12T00:47:49.209319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.06135","last_updated":"2023-09-27T23:17:28Z","snapshot_observed_at":"2026-07-06T15:53:11.310262Z","submitted_at":"2023-07-12T12:37:55Z","title":"SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.06135","snapshot_observed_at":"2026-08-12T00:47:48.527188Z","title":"Sayplan: Grounding large language models using 3d scene graphs for scalable robot task planning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.527188Z"},"links":{"cited_paper":"/paper/2307.06135","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:321390a7fd3c8c36de32b0f14a43c623c626dd8411e173a7ec585a1f6a53f4ba","observation_id":"41ea833f-6e46-4057-a296-2890e5da0bd5","resolution":{"observed_at":"2026-08-12T00:47:48.527188Z","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":"2026-08-12T00:47:49.194515Z","title":"Retrieval- augmented hierarchical in-context reinforcement learning and hindsight modular reflections for task planning with llms,","venue":null,"work_id":"ed761252-75e9-4156-a611-98b3daa6cbc6","year":2025},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.531206Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:1543e9b264e463d64e7368de5d4987d4e78f2b60b5f27c1e236fc05b1dcba6c2","observation_id":"01061845-751c-4e3a-967b-be16511eb7d8","resolution":{"observed_at":"2026-08-12T00:47:49.198102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T00:47:48.534462Z","title":"Llm-planner: Few-shot grounded planning for embodied agents with large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.534462Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:224dbd7351625249165ee6fe2875d855fe2490e40dc371be59c0a3e25e74f8c0","observation_id":"cc713381-aa14-43c9-ba4e-d6625d3b38c3","resolution":{"observed_at":"2026-08-12T00:47:48.534462Z","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":"2026-08-12T00:47:49.176463Z","title":"Robogpt: an llm-based long-term decision-making embodied agent for instruction following tasks,","venue":null,"work_id":"356f33d1-7862-4fab-b5c0-045981ed7054","year":2025},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.538052Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:981a26c5abd99a38cd01e120cbbaa813c0ed6f69aa1d6222e87f9d7fa522927a","observation_id":"3d9d7972-b518-4dc1-a6ca-5bf97eab3cd7","resolution":{"observed_at":"2026-08-12T00:47:49.180059Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03300","last_updated":"2024-04-27T15:25:53Z","snapshot_observed_at":"2026-08-06T14:58:42.911363Z","submitted_at":"2024-02-05T18:55:32Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-08-12T00:47:48.541443Z","title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.541443Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:cd0deef59e134bcbf449926161e05f025f5c125373629b588719581dd67a1306","observation_id":"25526fee-3c77-4d3f-8a6f-3f50501e6b85","resolution":{"observed_at":"2026-08-12T00:47:48.541443Z","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":"2026-08-12T00:47:48.545251Z","title":"Concept- graphs: Open-vocabulary 3d scene graphs for perception and planning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.545251Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:9485fb6f9549d888698c58915a86a283dadd7bf541ac9a87a6b5096a2ca2d33e","observation_id":"e67615b0-134b-46f4-976b-52d56417ca08","resolution":{"observed_at":"2026-08-12T00:47:48.545251Z","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":"2026-08-12T00:47:49.159213Z","title":"Search3d: Hierarchical open-vocabulary 3d segmentation,","venue":null,"work_id":"0bc72cdc-b3f2-4834-b614-f1840466db1c","year":2025},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.548120Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:9a430152232556fcae2e08432f624751797a983fa05c1bdd7d092b0cdde81b18","observation_id":"c2263949-9ed6-40f3-bd58-f43fd505acb7","resolution":{"observed_at":"2026-08-12T00:47:49.162651Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T00:47:48.550907Z","title":"Alfred: A benchmark for interpret- ing grounded instructions for everyday tasks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.550907Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:39df1dbf0121ed0369d35d4e0b99eb9dc03f80cdf86378fd449629ad4035f29c","observation_id":"0203bbce-bcb4-4177-b53b-62e071c6a532","resolution":{"observed_at":"2026-08-12T00:47:48.550907Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1712.05474","last_updated":"2022-08-26T17:12:17Z","snapshot_observed_at":"2026-07-06T06:14:28.435222Z","submitted_at":"2017-12-14T23:17:24Z","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.05474","snapshot_observed_at":"2026-08-12T00:47:48.553706Z","title":"Ai2-thor: An interactive 3d environment for visual ai,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.553706Z"},"links":{"cited_paper":"/paper/1712.05474","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:d480905aa2d9b91b20eba6a3a964c9c825fb9bd2a9b8515994a42d96a2d48ee6","observation_id":"987d1740-c82e-4f82-81cf-ad978394988e","resolution":{"observed_at":"2026-08-12T00:47:48.553706Z","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":"2026-08-12T00:47:49.141283Z","title":"Virtualhome: Simulating household activities via programs,","venue":null,"work_id":"cf8b2e7d-f543-475a-9782-b57b0c1d6df7","year":2018},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.556689Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:4aabfcd9c745d4d5b0a8276af5ee2788aebfd8b6b6df821f855fdf5f07a579fc","observation_id":"4c18270b-a053-4719-ae04-441b272dc779","resolution":{"observed_at":"2026-08-12T00:47:49.145310Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:47:49.130427Z","title":"Factorizing perception and policy for interactive instruction following,","venue":null,"work_id":"6be047f2-4fd2-4e11-9c84-89616421e48d","year":2021},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.559625Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:fd94d25b51787cfcb890beaf9011003f52e07ffd252e886f44d35ff816f19cb9","observation_id":"cc968a3d-ea2b-4290-a501-c35834493128","resolution":{"observed_at":"2026-08-12T00:47:49.134008Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.03267","last_updated":"2024-03-12T09:01:54Z","snapshot_observed_at":"2026-07-06T14:15:05.596076Z","submitted_at":"2022-11-07T02:24:39Z","title":"Prompter: Utilizing Large Language Model Prompting for a Data Efficient Embodied Instruction Following","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.03267","snapshot_observed_at":"2026-08-12T00:47:48.562595Z","title":"Prompter: Utilizing large language model prompting for a data efficient embodied instruction following,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.562595Z"},"links":{"cited_paper":"/paper/2211.03267","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:795c3d6137cd332f3be3335fdc48c5d832837f04d4a05f1f6bee33601d92d30a","observation_id":"4cfc3c25-8ebc-4d17-80c5-34f46da38fe3","resolution":{"observed_at":"2026-08-12T00:47:48.562595Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.03017","last_updated":"2024-03-05T14:53:53Z","snapshot_observed_at":"2026-07-06T17:39:53.791209Z","submitted_at":"2024-03-05T14:53:53Z","title":"OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Following","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.03017","snapshot_observed_at":"2026-08-12T00:47:48.566019Z","title":"Opex: A component- wise analysis of llm-centric agents in embodied instruction following,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.566019Z"},"links":{"cited_paper":"/paper/2403.03017","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:de59ee830a210901177bc29bbdb0eaa336b1561216bcd9b24b70612be45a7818","observation_id":"fc223705-0346-4bb0-919b-594f2709df37","resolution":{"observed_at":"2026-08-12T00:47:48.566019Z","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":"2026-08-12T00:47:49.119005Z","title":"Epo: Hierarchical llm agents with environment preference optimization,","venue":null,"work_id":"a4fb403f-eb68-46c0-a9e4-8e4221884d1a","year":2024},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.569823Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:15d7717c2e01f841b4d7620ad4325b9cc23cd36ce83ce1b18fb30cae695be864","observation_id":"83617d46-7322-4115-a466-e7d9c738fe5a","resolution":{"observed_at":"2026-08-12T00:47:49.122913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.05608","last_updated":"2022-07-12T15:20:48Z","snapshot_observed_at":"2026-08-08T09:48:52.583612Z","submitted_at":"2022-07-12T15:20:48Z","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.05608","snapshot_observed_at":"2026-08-12T00:47:48.573045Z","title":"Inner monologue: Embod- ied reasoning through planning with language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.573045Z"},"links":{"cited_paper":"/paper/2207.05608","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:6ffa2cdc7a10cde03dfc7fe8c94c452589fc5b61f565c3af3d8d773e8b1b086f","observation_id":"d5c3009e-8120-4e83-9282-01c1000b1e71","resolution":{"observed_at":"2026-08-12T00:47:48.573045Z","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":"2026-08-12T00:47:49.108229Z","title":"Pre-emptive action revision by environmental feedback for embodied instruction following agents,","venue":null,"work_id":"5155837e-6d1e-46bc-ac5c-bfede3087bcf","year":2024},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.576332Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:2cfeb18754104f3ebbfd0f17df8d61d2c2b3015d2bdd63a70955b0122e4d71da","observation_id":"0e01dfef-7f99-4582-ac15-a8c76216413c","resolution":{"observed_at":"2026-08-12T00:47:49.111624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T00:47:48.579665Z","title":"Chain-of-thought prompting elicits reasoning in large language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.579665Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:5055271bd73661ef651f1f16a37dd34194dc2e362aec45992f566cc32751a6f5","observation_id":"f51d8f40-374e-4ad3-b038-f7d26678e9ff","resolution":{"observed_at":"2026-08-12T00:47:48.579665Z","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":"2026-08-12T00:47:49.089883Z","title":"Unsupervised explanation generation via correct instantiations,","venue":null,"work_id":"ea99ec2e-12c2-4a97-9ddb-473fc13a0e5f","year":2023},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.582846Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:da4e11e85d45d1c80428d15a4ba0a8985809725584d270a98a0bb0ca3a264770","observation_id":"8463d740-1e12-4a8b-8e78-c3853a453d0b","resolution":{"observed_at":"2026-08-12T00:47:49.094036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.06892","last_updated":"2025-03-10T03:37:36Z","snapshot_observed_at":"2026-08-07T17:18:06.193061Z","submitted_at":"2025-03-10T03:37:36Z","title":"SafePlan: Leveraging Formal Logic and Chain-of-Thought Reasoning for Enhanced Safety in LLM-based Robotic Task Planning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.06892","snapshot_observed_at":"2026-08-12T00:47:48.585899Z","title":"Safeplan: Leveraging formal logic and chain-of-thought reasoning for enhanced safety in llm-based robotic task planning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.585899Z"},"links":{"cited_paper":"/paper/2503.06892","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:4c31de73d763b0445013859cce58ee916202f539e0a9fe321108a92998a7d5fc","observation_id":"4092e538-ef9d-45c2-affc-38bbcb983d81","resolution":{"observed_at":"2026-08-12T00:47:48.585899Z","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":"2026-08-12T00:47:48.589207Z","title":"Self-refine: Iter- ative refinement with self-feedback,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.589207Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:d6bc9765dc01b30fc6667828d4bbc2f723e2a3fc81778f61abcfa3040cb30ab0","observation_id":"3da8dd71-e0a2-453e-9b50-dd5736c365ec","resolution":{"observed_at":"2026-08-12T00:47:48.589207Z","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":"2026-08-12T00:47:49.070588Z","title":"Amor: A recipe for building adaptable modular knowledge agents through process feedback,","venue":null,"work_id":"f1f6d1e0-925e-46ca-887c-352dc2966de7","year":2024},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.592591Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:36bccd4999b9a450f0ffaa9f93e98ac2b9fc5f9e62d42486401cd156124e42a8","observation_id":"5a03c1ac-902d-432b-b325-8d25285e75b3","resolution":{"observed_at":"2026-08-12T00:47:49.074584Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:47:49.057696Z","title":"P-rag: Progressive retrieval augmented generation for planning on embodied everyday task,","venue":null,"work_id":"b15059b4-eef2-46ca-aca0-6d9c3998df41","year":2024},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.596209Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:f03f0a8f9c47829020d7ef74e1ae51e783a36a1b156d79f7092957da720544b0","observation_id":"901eea8f-723f-46ce-b3e3-685bfab70ad6","resolution":{"observed_at":"2026-08-12T00:47:49.062429Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:47:49.045478Z","title":"Instructrag: Leveraging retrieval-augmented generation on instruction graphs for llm-based task planning,","venue":null,"work_id":"7815d495-b75f-45ed-bb25-a34f7b161ddb","year":2025},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.599511Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:293b00b87508aa02b0f6c131996e30a180142440c94263d5ffe4cc4cead450d1","observation_id":"d201aab4-5bd2-4101-97cf-ee2dab6f87f3","resolution":{"observed_at":"2026-08-12T00:47:49.049396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:47:49.033966Z","title":"Double-feedback: Enhancing large language models reasoning in robotic tasks by knowl- edge graphs,","venue":null,"work_id":"06af2674-61db-4ce8-bddc-eab15838a517","year":2025},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.602700Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:78808ec29149eb21e64ff47f9006d2945c47c1daddaeb5ffb62c5b2523a2d89c","observation_id":"8f647854-c1e0-42d2-8e5f-05bde973edd9","resolution":{"observed_at":"2026-08-12T00:47:49.037770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.19410","last_updated":"2025-05-26T01:59:00Z","snapshot_observed_at":"2026-08-10T09:08:03.452058Z","submitted_at":"2025-05-26T01:59:00Z","title":"Self-Reflective Planning with Knowledge Graphs: Enhancing LLM Reasoning Reliability for Question Answering","version":1},"cited_work":{"arxiv_id":"2505.19410","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.19410","snapshot_observed_at":"2026-08-12T00:47:48.839018Z","title":"Self-Reflective Planning with Knowledge Graphs: Enhancing LLM Reasoning Reliability for Question Answering","venue":"cs.CL","work_id":"7ce83291-5bfa-4eb2-b944-c27b85640f59","year":2025},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.605911Z"},"links":{"cited_paper":"/paper/2505.19410","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:aae93e734f42085d82ce14c5a88d302433f9f2d5e533adb04c8a989ffab31d5f","observation_id":"b307ba83-8b47-42f2-8761-40c328dcc2d7","resolution":{"observed_at":"2026-08-12T00:47:48.843230Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.11436","last_updated":"2024-06-07T04:52:29Z","snapshot_observed_at":"2026-08-12T14:14:46.427877Z","submitted_at":"2023-09-20T16:12:32Z","title":"You Only Look at Screens: Multimodal Chain-of-Action Agents","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.11436","snapshot_observed_at":"2026-08-12T00:47:48.609892Z","title":"You only look at screens: Multimodal chain- of-action agents,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.609892Z"},"links":{"cited_paper":"/paper/2309.11436","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:5e6d709a1f004481e9de607b00d887732e3b6a7634d7215f770dfe1b034aa417","observation_id":"90af5c98-51e6-4d22-9217-44fbebef610b","resolution":{"observed_at":"2026-08-12T00:47:48.609892Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.13958","last_updated":"2025-04-16T21:45:32Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-04-16T21:45:32Z","title":"ToolRL: Reward is All Tool Learning Needs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.13958","snapshot_observed_at":"2026-08-12T00:47:48.613693Z","title":"Toolrl: Reward is all tool learning needs,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.613693Z"},"links":{"cited_paper":"/paper/2504.13958","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:7705f2ed50157cd5eaf2484869d25a1b7bbeff9af12861f4810ba60a4c39fadd","observation_id":"f1b0ec0f-27ce-48df-b549-8261ed1d4d20","resolution":{"observed_at":"2026-08-12T00:47:48.613693Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.18548","last_updated":"2025-03-13T16:48:34Z","snapshot_observed_at":"2026-08-07T17:49:46.596474Z","submitted_at":"2025-02-25T15:56:56Z","title":"What is the Alignment Objective of GRPO?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.18548","snapshot_observed_at":"2026-08-12T00:47:48.617633Z","title":"What is the alignment objective of grpo?","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.617633Z"},"links":{"cited_paper":"/paper/2502.18548","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:e95133a27473cadc8677e819d76ad9df59c15055b26e7708c9ba937dccb67cd8","observation_id":"7f819eed-dbc1-40c0-8d3d-1f4203d7de1a","resolution":{"observed_at":"2026-08-12T00:47:48.617633Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-12T00:47:48.621352Z","title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.621352Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:4bfd2e88c423322483c7aa6fffc8cf993a7b1c2983b4d2f5119af7d9719b55c7","observation_id":"7833ba14-7d2e-44b4-aa7b-f411030cef2d","resolution":{"observed_at":"2026-08-12T00:47:48.621352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.14768","last_updated":"2025-02-20T17:49:26Z","snapshot_observed_at":"2026-08-04T12:32:53.090165Z","submitted_at":"2025-02-20T17:49:26Z","title":"Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.14768","snapshot_observed_at":"2026-08-12T00:47:48.625599Z","title":"Logic-rl: Unleashing llm reasoning with rule-based reinforcement learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.625599Z"},"links":{"cited_paper":"/paper/2502.14768","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:008951b73fef4e7de1d488c54031541352020cd0e52156cb3ac3a77270b3e6d1","observation_id":"b20bfa9a-b1e3-402a-af2e-40ce9f073a59","resolution":{"observed_at":"2026-08-12T00:47:48.625599Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.11738","last_updated":"2024-02-21T12:59:21Z","snapshot_observed_at":"2026-07-31T18:12:14.483728Z","submitted_at":"2023-05-19T15:19:44Z","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.11738","snapshot_observed_at":"2026-08-12T00:47:48.629467Z","title":"Critic: Large language models can self-correct with tool-interactive critiquing,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.629467Z"},"links":{"cited_paper":"/paper/2305.11738","citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:235490d0a042da6b0ad3b4ec1e26b08ad7dcdd15627a20bf46bf2bfadec108de","observation_id":"ebe04acd-e761-477a-a583-c27d6e287ea0","resolution":{"observed_at":"2026-08-12T00:47:48.629467Z","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":"2026-08-12T00:47:48.633427Z","title":"Context-aware planning and environment-aware memory for instruction following embodied agents,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.633427Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:08ad60d42386c35a60e0e561ce3b1ae5f99038c06e0903e4df64cfc0f864b2ec","observation_id":"37b5f39e-e1f5-4f56-a772-f53cbbf9c871","resolution":{"observed_at":"2026-08-12T00:47:48.633427Z","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":"2505.18382","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:47:48.756123Z","title":"One demo is all it takes: Planning domain derivation with llms from a single demonstration,","venue":null,"work_id":"e03e3d1b-80c7-4dfa-b2ce-15dff564b3b7","year":2025},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.636526Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:b9fd48b528d933525adc9cb122c0f62a9a0f6e7d6765c18ac9da75fda8cf9248","observation_id":"26012b19-aedd-4e8f-bf63-afb9a269e349","resolution":{"observed_at":"2026-08-12T00:47:48.763199Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:47:49.015448Z","title":"A persistent spatial semantic representation for high-level natural language instruction exe- cution,","venue":null,"work_id":"9e20ec00-28fd-4237-8713-c9dcdf8beb3f","year":2022},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.639579Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:5a6be62c80bb33f11954ce63031f45c27efb04a56377e7a984f0d7f144b9ab9a","observation_id":"f779d019-8ba7-4b89-aed3-a182c595eace","resolution":{"observed_at":"2026-08-12T00:47:49.018980Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:47:49.003889Z","title":"Lota-bench: Benchmarking language-oriented task planners for embodied agents,","venue":null,"work_id":"74ddd289-56d0-4f99-84dc-187ef69dc19f","year":2024},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.642672Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:b1d5a6ca1c5367dd51f87033789e57051642c4182e921bc1c29758c0a11a51a0","observation_id":"7d67d89b-f2a4-4d0a-b62a-a5cc07b581ee","resolution":{"observed_at":"2026-08-12T00:47:49.007464Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:47:48.992211Z","title":"Lifelong experience abstraction and planning,","venue":null,"work_id":"45b68836-ef93-455e-97e9-d02a5c209051","year":2025},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.645654Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:b6d9220ff73114177e28756d8dbbd936da00bd9976d06e60395ab86e659aff39","observation_id":"fd4d0c53-7b4a-4c2d-bb6b-218ef9dd1a32","resolution":{"observed_at":"2026-08-12T00:47:48.995842Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:47:48.981440Z","title":"Embodied agent interface: Benchmarking llms for embodied decision making,","venue":null,"work_id":"48f3583f-32fb-46fc-804b-d8d7614a9d54","year":2024},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.648554Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:927834868bf0770a91c3ef34a090f220d493a540a6bc1fc904d527fb1aed6ec1","observation_id":"da251454-6a79-4932-a832-66ecafdcb0b6","resolution":{"observed_at":"2026-08-12T00:47:48.984896Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:47:49.263081Z","title":null,"venue":null,"work_id":"13ef227b-0dcb-45fe-abdf-fd94b94f2c81","year":2021},"citing_paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-12T00:47:48.497777Z"},"links":{"citing_paper":"/paper/2608.07905"},"observation_digest":"sha256:44f4c9e55f8dfb878fe6bdca493a3f31fecbd23c67d436f9f2baa5e1671c5c60","observation_id":"2707230e-bcb0-4d21-b77e-2094ef24476b","resolution":{"observed_at":"2026-08-12T00:47:49.266645Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.07905","last_updated":"2026-08-08T04:05:05Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-12T20:14:44.900356Z","submitted_at":"2026-08-08T04:05:05Z","title":"GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":25,"verified_exact":2,"verified_fuzzy":24},"total_outbound_references":51},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 0 inbound Pith citation observations for arXiv:2608.07905."}