{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HYYNZMIZ5YTFMPUVMZY6NCOSWY","short_pith_number":"pith:HYYNZMIZ","schema_version":"1.0","canonical_sha256":"3e30dcb119ee26563e956671e689d2b6018aa80f5a6f50632ecb72e42e404675","source":{"kind":"arxiv","id":"2305.18898","version":1},"attestation_state":"computed","paper":{"title":"AlphaBlock: Embodied Finetuning for Vision-Language Reasoning in Robot Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Bei Liu, Chuhao Jin, Jiange Yang, Jianlong Fu, Limin Wang, Ruihua Song, Wenhui Tan","submitted_at":"2023-05-30T09:54:20Z","abstract_excerpt":"We propose a novel framework for learning high-level cognitive capabilities in robot manipulation tasks, such as making a smiley face using building blocks. These tasks often involve complex multi-step reasoning, presenting significant challenges due to the limited paired data connecting human instructions (e.g., making a smiley face) and robot actions (e.g., end-effector movement). Existing approaches relieve this challenge by adopting an open-loop paradigm decomposing high-level instructions into simple sub-task plans, and executing them step-by-step using low-level control models. However, "},"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":"2305.18898","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-05-30T09:54:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"42a87a80d05db4b9f0ac603f7dc14a612042c18ace1a40de895f6cf8067a2170","abstract_canon_sha256":"f71a3c98652f9df0ec30c3504be85e614ae059b3351b9fed7f3ebe9ff82720e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:34.667552Z","signature_b64":"Q5PzRz2B8K0LOYbINXHFBUPgvSAd+dCskcYeDjw3niTExDajaXQCWv5DaJbmBB64+4vvs/y7qcKw76fbQ4tICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e30dcb119ee26563e956671e689d2b6018aa80f5a6f50632ecb72e42e404675","last_reissued_at":"2026-07-05T06:15:34.667048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:34.667048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AlphaBlock: Embodied Finetuning for Vision-Language Reasoning in Robot Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Bei Liu, Chuhao Jin, Jiange Yang, Jianlong Fu, Limin Wang, Ruihua Song, Wenhui Tan","submitted_at":"2023-05-30T09:54:20Z","abstract_excerpt":"We propose a novel framework for learning high-level cognitive capabilities in robot manipulation tasks, such as making a smiley face using building blocks. These tasks often involve complex multi-step reasoning, presenting significant challenges due to the limited paired data connecting human instructions (e.g., making a smiley face) and robot actions (e.g., end-effector movement). Existing approaches relieve this challenge by adopting an open-loop paradigm decomposing high-level instructions into simple sub-task plans, and executing them step-by-step using low-level control models. However, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18898","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/2305.18898/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":"2305.18898","created_at":"2026-07-05T06:15:34.667110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18898v1","created_at":"2026-07-05T06:15:34.667110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18898","created_at":"2026-07-05T06:15:34.667110+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYYNZMIZ5YTF","created_at":"2026-07-05T06:15:34.667110+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYYNZMIZ5YTFMPUV","created_at":"2026-07-05T06:15:34.667110+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYYNZMIZ","created_at":"2026-07-05T06:15:34.667110+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":236,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HYYNZMIZ5YTFMPUVMZY6NCOSWY","json":"https://pith.science/pith/HYYNZMIZ5YTFMPUVMZY6NCOSWY.json","graph_json":"https://pith.science/api/pith-number/HYYNZMIZ5YTFMPUVMZY6NCOSWY/graph.json","events_json":"https://pith.science/api/pith-number/HYYNZMIZ5YTFMPUVMZY6NCOSWY/events.json","paper":"https://pith.science/paper/HYYNZMIZ"},"agent_actions":{"view_html":"https://pith.science/pith/HYYNZMIZ5YTFMPUVMZY6NCOSWY","download_json":"https://pith.science/pith/HYYNZMIZ5YTFMPUVMZY6NCOSWY.json","view_paper":"https://pith.science/paper/HYYNZMIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18898&json=true","fetch_graph":"https://pith.science/api/pith-number/HYYNZMIZ5YTFMPUVMZY6NCOSWY/graph.json","fetch_events":"https://pith.science/api/pith-number/HYYNZMIZ5YTFMPUVMZY6NCOSWY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYYNZMIZ5YTFMPUVMZY6NCOSWY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYYNZMIZ5YTFMPUVMZY6NCOSWY/action/storage_attestation","attest_author":"https://pith.science/pith/HYYNZMIZ5YTFMPUVMZY6NCOSWY/action/author_attestation","sign_citation":"https://pith.science/pith/HYYNZMIZ5YTFMPUVMZY6NCOSWY/action/citation_signature","submit_replication":"https://pith.science/pith/HYYNZMIZ5YTFMPUVMZY6NCOSWY/action/replication_record"}},"created_at":"2026-07-05T06:15:34.667110+00:00","updated_at":"2026-07-05T06:15:34.667110+00:00"}