{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MIMYYXI7PO3EIKCHTHPPKWA3VR","short_pith_number":"pith:MIMYYXI7","schema_version":"1.0","canonical_sha256":"62198c5d1f7bb644284799def5581bac5de069cdad7b14675557cd2391d2fda6","source":{"kind":"arxiv","id":"2506.21230","version":2},"attestation_state":"computed","paper":{"title":"World-aware Planning Narratives Enhance Large Vision-Language Model Planner","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Jingjing Gong, Junhao Shi, Qipeng Guo, Siyin Wang, Xipeng Qiu, Zhaoye Fei","submitted_at":"2025-06-26T13:20:55Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) show promise for embodied planning tasks but struggle with complex scenarios involving unfamiliar environments and multi-step goals. Current approaches rely on environment-agnostic imitation learning that disconnects instructions from environmental contexts, causing models to struggle with context-sensitive instructions and rely on supplementary cues rather than visual reasoning during long-horizon interactions. In this work, we propose World-Aware Planning Narrative Enhancement (WAP), a framework that infuses LVLMs with comprehensive environmental understa"},"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":"2506.21230","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-26T13:20:55Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"de4b00448fbefa4235c8a948524865e782b612d3ba1d72a367ceed892e4c6b06","abstract_canon_sha256":"24e3627f1edc311da5f9552ada59d2335d6ea4bc015616e67e75c648e4d7df08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:45.383633Z","signature_b64":"rA8YHhKaQ3CKciWEw++ks0auED/Iw9U7WheBqKJ3gOXIsvAzseoOv0QtCi0SOpDcDA2Pr6smLUl0YxyTwVGpDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62198c5d1f7bb644284799def5581bac5de069cdad7b14675557cd2391d2fda6","last_reissued_at":"2026-07-05T11:30:45.383138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:45.383138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"World-aware Planning Narratives Enhance Large Vision-Language Model Planner","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Jingjing Gong, Junhao Shi, Qipeng Guo, Siyin Wang, Xipeng Qiu, Zhaoye Fei","submitted_at":"2025-06-26T13:20:55Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) show promise for embodied planning tasks but struggle with complex scenarios involving unfamiliar environments and multi-step goals. Current approaches rely on environment-agnostic imitation learning that disconnects instructions from environmental contexts, causing models to struggle with context-sensitive instructions and rely on supplementary cues rather than visual reasoning during long-horizon interactions. In this work, we propose World-Aware Planning Narrative Enhancement (WAP), a framework that infuses LVLMs with comprehensive environmental understa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21230","kind":"arxiv","version":2},"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/2506.21230/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":"2506.21230","created_at":"2026-07-05T11:30:45.383194+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21230v2","created_at":"2026-07-05T11:30:45.383194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21230","created_at":"2026-07-05T11:30:45.383194+00:00"},{"alias_kind":"pith_short_12","alias_value":"MIMYYXI7PO3E","created_at":"2026-07-05T11:30:45.383194+00:00"},{"alias_kind":"pith_short_16","alias_value":"MIMYYXI7PO3EIKCH","created_at":"2026-07-05T11:30:45.383194+00:00"},{"alias_kind":"pith_short_8","alias_value":"MIMYYXI7","created_at":"2026-07-05T11:30:45.383194+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02466","citing_title":"Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27251","citing_title":"Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09271","citing_title":"Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07774","citing_title":"RoboAgent: Chaining Basic Capabilities for Embodied Task Planning","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MIMYYXI7PO3EIKCHTHPPKWA3VR","json":"https://pith.science/pith/MIMYYXI7PO3EIKCHTHPPKWA3VR.json","graph_json":"https://pith.science/api/pith-number/MIMYYXI7PO3EIKCHTHPPKWA3VR/graph.json","events_json":"https://pith.science/api/pith-number/MIMYYXI7PO3EIKCHTHPPKWA3VR/events.json","paper":"https://pith.science/paper/MIMYYXI7"},"agent_actions":{"view_html":"https://pith.science/pith/MIMYYXI7PO3EIKCHTHPPKWA3VR","download_json":"https://pith.science/pith/MIMYYXI7PO3EIKCHTHPPKWA3VR.json","view_paper":"https://pith.science/paper/MIMYYXI7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21230&json=true","fetch_graph":"https://pith.science/api/pith-number/MIMYYXI7PO3EIKCHTHPPKWA3VR/graph.json","fetch_events":"https://pith.science/api/pith-number/MIMYYXI7PO3EIKCHTHPPKWA3VR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MIMYYXI7PO3EIKCHTHPPKWA3VR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MIMYYXI7PO3EIKCHTHPPKWA3VR/action/storage_attestation","attest_author":"https://pith.science/pith/MIMYYXI7PO3EIKCHTHPPKWA3VR/action/author_attestation","sign_citation":"https://pith.science/pith/MIMYYXI7PO3EIKCHTHPPKWA3VR/action/citation_signature","submit_replication":"https://pith.science/pith/MIMYYXI7PO3EIKCHTHPPKWA3VR/action/replication_record"}},"created_at":"2026-07-05T11:30:45.383194+00:00","updated_at":"2026-07-05T11:30:45.383194+00:00"}