{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:G6ZSX6LUIO3Y3HQIJMAE2QKTNM","short_pith_number":"pith:G6ZSX6LU","schema_version":"1.0","canonical_sha256":"37b32bf97443b78d9e084b004d41536b13f30bbebfcfba182238e4546a2f242f","source":{"kind":"arxiv","id":"2306.05696","version":1},"attestation_state":"computed","paper":{"title":"Embodied Executable Policy Learning with Language-based Scene Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ding Zhao, Jielin Qiu, Mengdi Xu, Seungwhan Moon, William Han","submitted_at":"2023-06-09T06:34:09Z","abstract_excerpt":"Large Language models (LLMs) have shown remarkable success in assisting robot learning tasks, i.e., complex household planning. However, the performance of pretrained LLMs heavily relies on domain-specific templated text data, which may be infeasible in real-world robot learning tasks with image-based observations. Moreover, existing LLMs with text inputs lack the capability to evolve with non-expert interactions with environments. In this work, we introduce a novel learning paradigm that generates robots' executable actions in the form of text, derived solely from visual observations, using l"},"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":"2306.05696","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-06-09T06:34:09Z","cross_cats_sorted":[],"title_canon_sha256":"3d6c5b926bf004238e1555496ab6c667f470ebe283993beb9db7e9943b461971","abstract_canon_sha256":"1bff79673d17d23aaf83b8618521d5031bb33ab6173c979b8da1aca0cd3a6181"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:09.125308Z","signature_b64":"oaj/rlCt+6ftv4glybH0p6aWhnj5i3+VGhLLbSGz706eNyKQU7nB845embstPurKQ/n8PeUNPgiDd7f+NtG+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37b32bf97443b78d9e084b004d41536b13f30bbebfcfba182238e4546a2f242f","last_reissued_at":"2026-07-05T06:19:09.124881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:09.124881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embodied Executable Policy Learning with Language-based Scene Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ding Zhao, Jielin Qiu, Mengdi Xu, Seungwhan Moon, William Han","submitted_at":"2023-06-09T06:34:09Z","abstract_excerpt":"Large Language models (LLMs) have shown remarkable success in assisting robot learning tasks, i.e., complex household planning. However, the performance of pretrained LLMs heavily relies on domain-specific templated text data, which may be infeasible in real-world robot learning tasks with image-based observations. Moreover, existing LLMs with text inputs lack the capability to evolve with non-expert interactions with environments. In this work, we introduce a novel learning paradigm that generates robots' executable actions in the form of text, derived solely from visual observations, using l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05696","kind":"arxiv","version":1},"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/2306.05696/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":"2306.05696","created_at":"2026-07-05T06:19:09.124936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05696v1","created_at":"2026-07-05T06:19:09.124936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05696","created_at":"2026-07-05T06:19:09.124936+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6ZSX6LUIO3Y","created_at":"2026-07-05T06:19:09.124936+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6ZSX6LUIO3Y3HQI","created_at":"2026-07-05T06:19:09.124936+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6ZSX6LU","created_at":"2026-07-05T06:19:09.124936+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/G6ZSX6LUIO3Y3HQIJMAE2QKTNM","json":"https://pith.science/pith/G6ZSX6LUIO3Y3HQIJMAE2QKTNM.json","graph_json":"https://pith.science/api/pith-number/G6ZSX6LUIO3Y3HQIJMAE2QKTNM/graph.json","events_json":"https://pith.science/api/pith-number/G6ZSX6LUIO3Y3HQIJMAE2QKTNM/events.json","paper":"https://pith.science/paper/G6ZSX6LU"},"agent_actions":{"view_html":"https://pith.science/pith/G6ZSX6LUIO3Y3HQIJMAE2QKTNM","download_json":"https://pith.science/pith/G6ZSX6LUIO3Y3HQIJMAE2QKTNM.json","view_paper":"https://pith.science/paper/G6ZSX6LU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05696&json=true","fetch_graph":"https://pith.science/api/pith-number/G6ZSX6LUIO3Y3HQIJMAE2QKTNM/graph.json","fetch_events":"https://pith.science/api/pith-number/G6ZSX6LUIO3Y3HQIJMAE2QKTNM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6ZSX6LUIO3Y3HQIJMAE2QKTNM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6ZSX6LUIO3Y3HQIJMAE2QKTNM/action/storage_attestation","attest_author":"https://pith.science/pith/G6ZSX6LUIO3Y3HQIJMAE2QKTNM/action/author_attestation","sign_citation":"https://pith.science/pith/G6ZSX6LUIO3Y3HQIJMAE2QKTNM/action/citation_signature","submit_replication":"https://pith.science/pith/G6ZSX6LUIO3Y3HQIJMAE2QKTNM/action/replication_record"}},"created_at":"2026-07-05T06:19:09.124936+00:00","updated_at":"2026-07-05T06:19:09.124936+00:00"}