{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L4SFKGG3EASLRLAD33QKXUMXWK","short_pith_number":"pith:L4SFKGG3","schema_version":"1.0","canonical_sha256":"5f245518db2024b8ac03dee0abd197b284560f6af38ae4651d738559d4e68832","source":{"kind":"arxiv","id":"2601.21841","version":3},"attestation_state":"computed","paper":{"title":"Embodied Task Planning via Graph-Informed Action Generation with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Masood Mortazavi, Ning Yan, Xiang Li","submitted_at":"2026-01-29T15:18:58Z","abstract_excerpt":"While Large Language Models (LLMs) have demonstrated strong zero-shot reasoning capabilities, their deployment as embodied agents still faces fundamental challenges in long-horizon planning. Unlike open-ended text generation, embodied agents must decompose high-level intents into actionable sub-goals while adhering to the constraints of a dynamic environment. Standard LLM planners frequently fail to maintain strategy coherence over extended horizons due to context window limitations or hallucinate state transitions that violate environment constraints. We propose GiG, a planning framework that"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2601.21841","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-29T15:18:58Z","cross_cats_sorted":[],"title_canon_sha256":"4fefdc44f109870b15e0798d24759c08ba738f99a3cd75fee13bbfe06dc38de9","abstract_canon_sha256":"0d258ee91353402ba8b6ed53f2c59d5f3b6312b707bc02d07239c14f15d73c4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:23.764614Z","signature_b64":"woxjCl7LQbixj7FKhrmJ54YSM+kkpzCiqq8RmsR0v6j1rUuUWgbqLIxpQDmqF1X5BO2zKU71MmMfbaUGHS5KBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f245518db2024b8ac03dee0abd197b284560f6af38ae4651d738559d4e68832","last_reissued_at":"2026-05-20T00:04:23.763779Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:23.763779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embodied Task Planning via Graph-Informed Action Generation with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Masood Mortazavi, Ning Yan, Xiang Li","submitted_at":"2026-01-29T15:18:58Z","abstract_excerpt":"While Large Language Models (LLMs) have demonstrated strong zero-shot reasoning capabilities, their deployment as embodied agents still faces fundamental challenges in long-horizon planning. Unlike open-ended text generation, embodied agents must decompose high-level intents into actionable sub-goals while adhering to the constraints of a dynamic environment. Standard LLM planners frequently fail to maintain strategy coherence over extended horizons due to context window limitations or hallucinate state transitions that violate environment constraints. We propose GiG, a planning framework that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21841","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.21841/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2601.21841","created_at":"2026-05-20T00:04:23.763923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.21841v3","created_at":"2026-05-20T00:04:23.763923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21841","created_at":"2026-05-20T00:04:23.763923+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4SFKGG3EASL","created_at":"2026-05-20T00:04:23.763923+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4SFKGG3EASLRLAD","created_at":"2026-05-20T00:04:23.763923+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4SFKGG3","created_at":"2026-05-20T00:04:23.763923+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L4SFKGG3EASLRLAD33QKXUMXWK","json":"https://pith.science/pith/L4SFKGG3EASLRLAD33QKXUMXWK.json","graph_json":"https://pith.science/api/pith-number/L4SFKGG3EASLRLAD33QKXUMXWK/graph.json","events_json":"https://pith.science/api/pith-number/L4SFKGG3EASLRLAD33QKXUMXWK/events.json","paper":"https://pith.science/paper/L4SFKGG3"},"agent_actions":{"view_html":"https://pith.science/pith/L4SFKGG3EASLRLAD33QKXUMXWK","download_json":"https://pith.science/pith/L4SFKGG3EASLRLAD33QKXUMXWK.json","view_paper":"https://pith.science/paper/L4SFKGG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.21841&json=true","fetch_graph":"https://pith.science/api/pith-number/L4SFKGG3EASLRLAD33QKXUMXWK/graph.json","fetch_events":"https://pith.science/api/pith-number/L4SFKGG3EASLRLAD33QKXUMXWK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4SFKGG3EASLRLAD33QKXUMXWK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4SFKGG3EASLRLAD33QKXUMXWK/action/storage_attestation","attest_author":"https://pith.science/pith/L4SFKGG3EASLRLAD33QKXUMXWK/action/author_attestation","sign_citation":"https://pith.science/pith/L4SFKGG3EASLRLAD33QKXUMXWK/action/citation_signature","submit_replication":"https://pith.science/pith/L4SFKGG3EASLRLAD33QKXUMXWK/action/replication_record"}},"created_at":"2026-05-20T00:04:23.763923+00:00","updated_at":"2026-05-20T00:04:23.763923+00:00"}