{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4HVHO2SCHISZZQBIPFU2R56N5D","short_pith_number":"pith:4HVHO2SC","schema_version":"1.0","canonical_sha256":"e1ea776a423a259cc0287969a8f7cde8d5799f2b2812b30de213be1181ea818d","source":{"kind":"arxiv","id":"2306.11335","version":4},"attestation_state":"computed","paper":{"title":"Surfer: Progressive Reasoning with World Models for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Fengda Zhu, Hetao Zheng, Kaidong Zhang, Mas Ma, Pengzhen Ren, Xiaodan Liang, Yuhang Wen, Zixuan Li","submitted_at":"2023-06-20T07:06:04Z","abstract_excerpt":"Considering how to make the model accurately understand and follow natural language instructions and perform actions consistent with world knowledge is a key challenge in robot manipulation. This mainly includes human fuzzy instruction reasoning and the following of physical knowledge. Therefore, the embodied intelligence agent must have the ability to model world knowledge from training data. However, most existing vision and language robot manipulation methods mainly operate in less realistic simulator and language settings and lack explicit modeling of world knowledge. To bridge this gap, w"},"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":"2306.11335","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-06-20T07:06:04Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"430208b768872d781384d26738cb617928581c2c40bfd742de55c52fdefa8a01","abstract_canon_sha256":"b353a0b00b44e6e59e8ba48e251961108d90440eb9a45243541ac42e7ec33c18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:20.654099Z","signature_b64":"+cfrMp8OYp8AbF1+9s0szWSwfee05zQQjuJqdsOkYrQtZyz1346zwaO3By3HOaPhFeqim3nLg4Aaym1jUQ4dBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1ea776a423a259cc0287969a8f7cde8d5799f2b2812b30de213be1181ea818d","last_reissued_at":"2026-07-05T07:58:20.653557Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:20.653557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Surfer: Progressive Reasoning with World Models for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Fengda Zhu, Hetao Zheng, Kaidong Zhang, Mas Ma, Pengzhen Ren, Xiaodan Liang, Yuhang Wen, Zixuan Li","submitted_at":"2023-06-20T07:06:04Z","abstract_excerpt":"Considering how to make the model accurately understand and follow natural language instructions and perform actions consistent with world knowledge is a key challenge in robot manipulation. This mainly includes human fuzzy instruction reasoning and the following of physical knowledge. Therefore, the embodied intelligence agent must have the ability to model world knowledge from training data. However, most existing vision and language robot manipulation methods mainly operate in less realistic simulator and language settings and lack explicit modeling of world knowledge. To bridge this gap, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11335","kind":"arxiv","version":4},"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/2306.11335/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":"2306.11335","created_at":"2026-07-05T07:58:20.653628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11335v4","created_at":"2026-07-05T07:58:20.653628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11335","created_at":"2026-07-05T07:58:20.653628+00:00"},{"alias_kind":"pith_short_12","alias_value":"4HVHO2SCHISZ","created_at":"2026-07-05T07:58:20.653628+00:00"},{"alias_kind":"pith_short_16","alias_value":"4HVHO2SCHISZZQBI","created_at":"2026-07-05T07:58:20.653628+00:00"},{"alias_kind":"pith_short_8","alias_value":"4HVHO2SC","created_at":"2026-07-05T07:58:20.653628+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21741","citing_title":"Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4HVHO2SCHISZZQBIPFU2R56N5D","json":"https://pith.science/pith/4HVHO2SCHISZZQBIPFU2R56N5D.json","graph_json":"https://pith.science/api/pith-number/4HVHO2SCHISZZQBIPFU2R56N5D/graph.json","events_json":"https://pith.science/api/pith-number/4HVHO2SCHISZZQBIPFU2R56N5D/events.json","paper":"https://pith.science/paper/4HVHO2SC"},"agent_actions":{"view_html":"https://pith.science/pith/4HVHO2SCHISZZQBIPFU2R56N5D","download_json":"https://pith.science/pith/4HVHO2SCHISZZQBIPFU2R56N5D.json","view_paper":"https://pith.science/paper/4HVHO2SC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11335&json=true","fetch_graph":"https://pith.science/api/pith-number/4HVHO2SCHISZZQBIPFU2R56N5D/graph.json","fetch_events":"https://pith.science/api/pith-number/4HVHO2SCHISZZQBIPFU2R56N5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4HVHO2SCHISZZQBIPFU2R56N5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4HVHO2SCHISZZQBIPFU2R56N5D/action/storage_attestation","attest_author":"https://pith.science/pith/4HVHO2SCHISZZQBIPFU2R56N5D/action/author_attestation","sign_citation":"https://pith.science/pith/4HVHO2SCHISZZQBIPFU2R56N5D/action/citation_signature","submit_replication":"https://pith.science/pith/4HVHO2SCHISZZQBIPFU2R56N5D/action/replication_record"}},"created_at":"2026-07-05T07:58:20.653628+00:00","updated_at":"2026-07-05T07:58:20.653628+00:00"}