{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WIX2ZSXPDBN6Q2WX7NFMHBG7EW","short_pith_number":"pith:WIX2ZSXP","schema_version":"1.0","canonical_sha256":"b22faccaef185be86ad7fb4ac384df25a5bc9c4cd9630eff6e6db091e13ea29c","source":{"kind":"arxiv","id":"2410.17856","version":3},"attestation_state":"computed","paper":{"title":"ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anji Liu, Kewei Lian, Shaofei Cai, Xiaojian Ma, Yitao Liang, Zhancun Mu, Zihao Wang","submitted_at":"2024-10-23T13:26:59Z","abstract_excerpt":"Vision-language models (VLMs) have excelled in multimodal tasks, but adapting them to embodied decision-making in open-world environments presents challenges. One critical issue is bridging the gap between discrete entities in low-level observations and the abstract concepts required for effective planning. A common solution is building hierarchical agents, where VLMs serve as high-level reasoners that break down tasks into executable sub-tasks, typically specified using language. However, language suffers from the inability to communicate detailed spatial information. We propose visual-tempor"},"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":"2410.17856","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-23T13:26:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f0f1d7e41bb66fd98c372e5c12befaee6decf6af153fac062cb49301c5106f1b","abstract_canon_sha256":"42d285055c5dea0f4c85f86c5a8c37dcfcae086ccc4751ee6cf7b2e31934038b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:39.374692Z","signature_b64":"ELth/xT94WTUut/PZLviphCX3e53U0tjAb0SNJaNFg9RuK/8X/9DUcJxC/UMxvNiGDR6/PZaHlNHX/cPeOA3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b22faccaef185be86ad7fb4ac384df25a5bc9c4cd9630eff6e6db091e13ea29c","last_reissued_at":"2026-07-05T10:35:39.374165Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:39.374165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anji Liu, Kewei Lian, Shaofei Cai, Xiaojian Ma, Yitao Liang, Zhancun Mu, Zihao Wang","submitted_at":"2024-10-23T13:26:59Z","abstract_excerpt":"Vision-language models (VLMs) have excelled in multimodal tasks, but adapting them to embodied decision-making in open-world environments presents challenges. One critical issue is bridging the gap between discrete entities in low-level observations and the abstract concepts required for effective planning. A common solution is building hierarchical agents, where VLMs serve as high-level reasoners that break down tasks into executable sub-tasks, typically specified using language. However, language suffers from the inability to communicate detailed spatial information. We propose visual-tempor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17856","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/2410.17856/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":"2410.17856","created_at":"2026-07-05T10:35:39.374227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17856v3","created_at":"2026-07-05T10:35:39.374227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17856","created_at":"2026-07-05T10:35:39.374227+00:00"},{"alias_kind":"pith_short_12","alias_value":"WIX2ZSXPDBN6","created_at":"2026-07-05T10:35:39.374227+00:00"},{"alias_kind":"pith_short_16","alias_value":"WIX2ZSXPDBN6Q2WX","created_at":"2026-07-05T10:35:39.374227+00:00"},{"alias_kind":"pith_short_8","alias_value":"WIX2ZSXP","created_at":"2026-07-05T10:35:39.374227+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.01925","citing_title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","ref_index":132,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WIX2ZSXPDBN6Q2WX7NFMHBG7EW","json":"https://pith.science/pith/WIX2ZSXPDBN6Q2WX7NFMHBG7EW.json","graph_json":"https://pith.science/api/pith-number/WIX2ZSXPDBN6Q2WX7NFMHBG7EW/graph.json","events_json":"https://pith.science/api/pith-number/WIX2ZSXPDBN6Q2WX7NFMHBG7EW/events.json","paper":"https://pith.science/paper/WIX2ZSXP"},"agent_actions":{"view_html":"https://pith.science/pith/WIX2ZSXPDBN6Q2WX7NFMHBG7EW","download_json":"https://pith.science/pith/WIX2ZSXPDBN6Q2WX7NFMHBG7EW.json","view_paper":"https://pith.science/paper/WIX2ZSXP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17856&json=true","fetch_graph":"https://pith.science/api/pith-number/WIX2ZSXPDBN6Q2WX7NFMHBG7EW/graph.json","fetch_events":"https://pith.science/api/pith-number/WIX2ZSXPDBN6Q2WX7NFMHBG7EW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WIX2ZSXPDBN6Q2WX7NFMHBG7EW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WIX2ZSXPDBN6Q2WX7NFMHBG7EW/action/storage_attestation","attest_author":"https://pith.science/pith/WIX2ZSXPDBN6Q2WX7NFMHBG7EW/action/author_attestation","sign_citation":"https://pith.science/pith/WIX2ZSXPDBN6Q2WX7NFMHBG7EW/action/citation_signature","submit_replication":"https://pith.science/pith/WIX2ZSXPDBN6Q2WX7NFMHBG7EW/action/replication_record"}},"created_at":"2026-07-05T10:35:39.374227+00:00","updated_at":"2026-07-05T10:35:39.374227+00:00"}