{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GVHQH3PDJ3QOVOASCXQ4BXHBKA","short_pith_number":"pith:GVHQH3PD","canonical_record":{"source":{"id":"2310.08588","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-12T17:59:58Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"3eb8db99dfe836f20075122d5455d9e324894b5210f6f0a52821f9c029e35512","abstract_canon_sha256":"4026e4cd7986b11c3301d7840b277bceaac7cba98f7dcd22171e0250eeda8762"},"schema_version":"1.0"},"canonical_sha256":"354f03ede34ee0eab81215e1c0dce15012919e749afc9dd7ce0a0339028bd3ce","source":{"kind":"arxiv","id":"2310.08588","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08588","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08588v2","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08588","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"pith_short_12","alias_value":"GVHQH3PDJ3QO","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"pith_short_16","alias_value":"GVHQH3PDJ3QOVOAS","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"pith_short_8","alias_value":"GVHQH3PD","created_at":"2026-07-05T09:23:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GVHQH3PDJ3QOVOASCXQ4BXHBKA","target":"record","payload":{"canonical_record":{"source":{"id":"2310.08588","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-12T17:59:58Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"3eb8db99dfe836f20075122d5455d9e324894b5210f6f0a52821f9c029e35512","abstract_canon_sha256":"4026e4cd7986b11c3301d7840b277bceaac7cba98f7dcd22171e0250eeda8762"},"schema_version":"1.0"},"canonical_sha256":"354f03ede34ee0eab81215e1c0dce15012919e749afc9dd7ce0a0339028bd3ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:00.767470Z","signature_b64":"c2RPf2sJEixf5hkondfW0fbkZwf7PWL7Eb9uL0wdf+EFDB0kGhZvUj7urL3oxK/pT4PsJGPGQWMdxpW8eVguAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"354f03ede34ee0eab81215e1c0dce15012919e749afc9dd7ce0a0339028bd3ce","last_reissued_at":"2026-07-05T09:23:00.766966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:00.766966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.08588","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:23:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rgfrg3zUqZMH+XLkjt9z20f3OW6v+HACeLTfXJNjJavHBkN9+MFMgw0mNZEmseJi7SMtYCZg2MHF+D3rkNmaDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:15:35.521917Z"},"content_sha256":"eddbdece4733e87e57f49aee2c671fc216482f0361468deb403ecaa047e06152","schema_version":"1.0","event_id":"sha256:eddbdece4733e87e57f49aee2c671fc216482f0361468deb403ecaa047e06152"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GVHQH3PDJ3QOVOASCXQ4BXHBKA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Octopus: Embodied Vision-Language Programmer from Environmental Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bo Li, Chencheng Jiang, Haoran Tan, Jiamu Kang, Jingkang Yang, Kaiyang Zhou, Shuai Liu, Yuanhan Zhang, Yuhao Dong, Ziwei Liu, Ziyue Wang","submitted_at":"2023-10-12T17:59:58Z","abstract_excerpt":"Large vision-language models (VLMs) have achieved substantial progress in multimodal perception and reasoning. When integrated into an embodied agent, existing embodied VLM works either output detailed action sequences at the manipulation level or only provide plans at an abstract level, leaving a gap between high-level planning and real-world manipulation. To bridge this gap, we introduce Octopus, an embodied vision-language programmer that uses executable code generation as a medium to connect planning and manipulation. Octopus is designed to 1) proficiently comprehend an agent's visual and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08588","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/2310.08588/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:23:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZgGoP+5TGxxibHGz00lPfAWG3tzTwhvHVEyQiVIjoR3/I3d38986SPr5WaIOC8i7vAL1sY6y9Sd5J6lkjVfnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:15:35.522913Z"},"content_sha256":"8421414bcdb69936c46121af4a70d59103f5378dc5814f551d057d885296c316","schema_version":"1.0","event_id":"sha256:8421414bcdb69936c46121af4a70d59103f5378dc5814f551d057d885296c316"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GVHQH3PDJ3QOVOASCXQ4BXHBKA/bundle.json","state_url":"https://pith.science/pith/GVHQH3PDJ3QOVOASCXQ4BXHBKA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GVHQH3PDJ3QOVOASCXQ4BXHBKA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T17:15:35Z","links":{"resolver":"https://pith.science/pith/GVHQH3PDJ3QOVOASCXQ4BXHBKA","bundle":"https://pith.science/pith/GVHQH3PDJ3QOVOASCXQ4BXHBKA/bundle.json","state":"https://pith.science/pith/GVHQH3PDJ3QOVOASCXQ4BXHBKA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GVHQH3PDJ3QOVOASCXQ4BXHBKA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GVHQH3PDJ3QOVOASCXQ4BXHBKA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4026e4cd7986b11c3301d7840b277bceaac7cba98f7dcd22171e0250eeda8762","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-12T17:59:58Z","title_canon_sha256":"3eb8db99dfe836f20075122d5455d9e324894b5210f6f0a52821f9c029e35512"},"schema_version":"1.0","source":{"id":"2310.08588","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08588","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08588v2","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08588","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"pith_short_12","alias_value":"GVHQH3PDJ3QO","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"pith_short_16","alias_value":"GVHQH3PDJ3QOVOAS","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"pith_short_8","alias_value":"GVHQH3PD","created_at":"2026-07-05T09:23:00Z"}],"graph_snapshots":[{"event_id":"sha256:8421414bcdb69936c46121af4a70d59103f5378dc5814f551d057d885296c316","target":"graph","created_at":"2026-07-05T09:23:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.08588/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large vision-language models (VLMs) have achieved substantial progress in multimodal perception and reasoning. When integrated into an embodied agent, existing embodied VLM works either output detailed action sequences at the manipulation level or only provide plans at an abstract level, leaving a gap between high-level planning and real-world manipulation. To bridge this gap, we introduce Octopus, an embodied vision-language programmer that uses executable code generation as a medium to connect planning and manipulation. Octopus is designed to 1) proficiently comprehend an agent's visual and ","authors_text":"Bo Li, Chencheng Jiang, Haoran Tan, Jiamu Kang, Jingkang Yang, Kaiyang Zhou, Shuai Liu, Yuanhan Zhang, Yuhao Dong, Ziwei Liu, Ziyue Wang","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-12T17:59:58Z","title":"Octopus: Embodied Vision-Language Programmer from Environmental Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08588","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:eddbdece4733e87e57f49aee2c671fc216482f0361468deb403ecaa047e06152","target":"record","created_at":"2026-07-05T09:23:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4026e4cd7986b11c3301d7840b277bceaac7cba98f7dcd22171e0250eeda8762","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-12T17:59:58Z","title_canon_sha256":"3eb8db99dfe836f20075122d5455d9e324894b5210f6f0a52821f9c029e35512"},"schema_version":"1.0","source":{"id":"2310.08588","kind":"arxiv","version":2}},"canonical_sha256":"354f03ede34ee0eab81215e1c0dce15012919e749afc9dd7ce0a0339028bd3ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"354f03ede34ee0eab81215e1c0dce15012919e749afc9dd7ce0a0339028bd3ce","first_computed_at":"2026-07-05T09:23:00.766966Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:00.766966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c2RPf2sJEixf5hkondfW0fbkZwf7PWL7Eb9uL0wdf+EFDB0kGhZvUj7urL3oxK/pT4PsJGPGQWMdxpW8eVguAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:00.767470Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.08588","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eddbdece4733e87e57f49aee2c671fc216482f0361468deb403ecaa047e06152","sha256:8421414bcdb69936c46121af4a70d59103f5378dc5814f551d057d885296c316"],"state_sha256":"9c478b76fa87bba44f750ced1838672792d84a9cfc72f91b15c420383965992e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NC5FpdAm8n3OwYTUSlpKl2DnKeksHCGXQQhEASyjrMaYkIojBRWmAt0zhwsLof7c/BplwUztBYqcDjZYrcfuCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:15:35.530923Z","bundle_sha256":"ce866abcfffee9dcfac63a4512f21a955924dba16ed7b4d15c61f5c3d981928a"}}