{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:33N5IHA3VKDU3FL6EUNCFYNOAY","short_pith_number":"pith:33N5IHA3","canonical_record":{"source":{"id":"2402.07872","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-02-12T18:33:47Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"f5ebb3fb981af6e263d5978ca6632afbe6b134b2768d18d64eab8895c8d55eb0","abstract_canon_sha256":"d7196323cbb364cef9a5b7ede7989f44330d78bbe737f85b32a73df165396ffc"},"schema_version":"1.0"},"canonical_sha256":"dedbd41c1baa874d957e251a22e1ae06328bba26af5b0b277f33bd5e8c2d23b0","source":{"kind":"arxiv","id":"2402.07872","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07872","created_at":"2026-07-05T07:44:13Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07872v1","created_at":"2026-07-05T07:44:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07872","created_at":"2026-07-05T07:44:13Z"},{"alias_kind":"pith_short_12","alias_value":"33N5IHA3VKDU","created_at":"2026-07-05T07:44:13Z"},{"alias_kind":"pith_short_16","alias_value":"33N5IHA3VKDU3FL6","created_at":"2026-07-05T07:44:13Z"},{"alias_kind":"pith_short_8","alias_value":"33N5IHA3","created_at":"2026-07-05T07:44:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:33N5IHA3VKDU3FL6EUNCFYNOAY","target":"record","payload":{"canonical_record":{"source":{"id":"2402.07872","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-02-12T18:33:47Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"f5ebb3fb981af6e263d5978ca6632afbe6b134b2768d18d64eab8895c8d55eb0","abstract_canon_sha256":"d7196323cbb364cef9a5b7ede7989f44330d78bbe737f85b32a73df165396ffc"},"schema_version":"1.0"},"canonical_sha256":"dedbd41c1baa874d957e251a22e1ae06328bba26af5b0b277f33bd5e8c2d23b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:13.655537Z","signature_b64":"TA1LooZL9bKNp/ZMCz2GSx5AAQsRioiC+n1ngSJ+MZnP8vg6qQeAbcrqxofZL/HBON3tM348nwMEWFqjw5eVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dedbd41c1baa874d957e251a22e1ae06328bba26af5b0b277f33bd5e8c2d23b0","last_reissued_at":"2026-07-05T07:44:13.655029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:13.655029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.07872","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:44:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"71SAJ7d7cHKr0yyUx5gzcWwRsYyc0bkF/Tauzcmq8oo5csWfi/Az4EjD0k/jPyhU1mKPYxh1UwmqgN9xB0YgDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:06:28.004913Z"},"content_sha256":"714e836db7cba296d196ff0082ad59d04645f48802927482c7c3f2d546a4b240","schema_version":"1.0","event_id":"sha256:714e836db7cba296d196ff0082ad59d04645f48802927482c7c3f2d546a4b240"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:33N5IHA3VKDU3FL6EUNCFYNOAY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Andy Zeng, Annie Xie, Ayzaan Wahid, Brian Ichter, Chelsea Finn, Danny Driess, Fei Xia, Ishita Dasgupta, Jacky Liang, Karol Hausman, Kuang-Huei Lee, Nicolas Heess, Peng Xu, Quan Vuong, Sean Kirmani, Sergey Levine, Soroush Nasiriany, Ted Xiao, Tingnan Zhang, Tsang-Wei Edward Lee, Wenhao Yu, Yuke Zhu, Zhuo Xu","submitted_at":"2024-02-12T18:33:47Z","abstract_excerpt":"Vision language models (VLMs) have shown impressive capabilities across a variety of tasks, from logical reasoning to visual understanding. This opens the door to richer interaction with the world, for example robotic control. However, VLMs produce only textual outputs, while robotic control and other spatial tasks require outputting continuous coordinates, actions, or trajectories. How can we enable VLMs to handle such settings without fine-tuning on task-specific data?\n  In this paper, we propose a novel visual prompting approach for VLMs that we call Prompting with Iterative Visual Optimiza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07872","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/2402.07872/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":"2026-07-05T07:44:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lJmNsvYPmBJ9AeCql7CfzCuPhMMlNhabdWfm4qg4Pa21QX4Qxi0fiXgpBzZ1fPK2SVHlGQpHSzvQt4hONxp0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:06:28.005435Z"},"content_sha256":"b3e60238699e3de17474afb815d44c091d0383b3488906b7a7711ab5c5729dc4","schema_version":"1.0","event_id":"sha256:b3e60238699e3de17474afb815d44c091d0383b3488906b7a7711ab5c5729dc4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/33N5IHA3VKDU3FL6EUNCFYNOAY/bundle.json","state_url":"https://pith.science/pith/33N5IHA3VKDU3FL6EUNCFYNOAY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/33N5IHA3VKDU3FL6EUNCFYNOAY/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":"2026-08-06T04:06:28Z","links":{"resolver":"https://pith.science/pith/33N5IHA3VKDU3FL6EUNCFYNOAY","bundle":"https://pith.science/pith/33N5IHA3VKDU3FL6EUNCFYNOAY/bundle.json","state":"https://pith.science/pith/33N5IHA3VKDU3FL6EUNCFYNOAY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/33N5IHA3VKDU3FL6EUNCFYNOAY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:33N5IHA3VKDU3FL6EUNCFYNOAY","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":"d7196323cbb364cef9a5b7ede7989f44330d78bbe737f85b32a73df165396ffc","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-02-12T18:33:47Z","title_canon_sha256":"f5ebb3fb981af6e263d5978ca6632afbe6b134b2768d18d64eab8895c8d55eb0"},"schema_version":"1.0","source":{"id":"2402.07872","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07872","created_at":"2026-07-05T07:44:13Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07872v1","created_at":"2026-07-05T07:44:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07872","created_at":"2026-07-05T07:44:13Z"},{"alias_kind":"pith_short_12","alias_value":"33N5IHA3VKDU","created_at":"2026-07-05T07:44:13Z"},{"alias_kind":"pith_short_16","alias_value":"33N5IHA3VKDU3FL6","created_at":"2026-07-05T07:44:13Z"},{"alias_kind":"pith_short_8","alias_value":"33N5IHA3","created_at":"2026-07-05T07:44:13Z"}],"graph_snapshots":[{"event_id":"sha256:b3e60238699e3de17474afb815d44c091d0383b3488906b7a7711ab5c5729dc4","target":"graph","created_at":"2026-07-05T07:44:13Z","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/2402.07872/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision language models (VLMs) have shown impressive capabilities across a variety of tasks, from logical reasoning to visual understanding. This opens the door to richer interaction with the world, for example robotic control. However, VLMs produce only textual outputs, while robotic control and other spatial tasks require outputting continuous coordinates, actions, or trajectories. How can we enable VLMs to handle such settings without fine-tuning on task-specific data?\n  In this paper, we propose a novel visual prompting approach for VLMs that we call Prompting with Iterative Visual Optimiza","authors_text":"Andy Zeng, Annie Xie, Ayzaan Wahid, Brian Ichter, Chelsea Finn, Danny Driess, Fei Xia, Ishita Dasgupta, Jacky Liang, Karol Hausman, Kuang-Huei Lee, Nicolas Heess, Peng Xu, Quan Vuong, Sean Kirmani, Sergey Levine, Soroush Nasiriany, Ted Xiao, Tingnan Zhang, Tsang-Wei Edward Lee, Wenhao Yu, Yuke Zhu, Zhuo Xu","cross_cats":["cs.CL","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-02-12T18:33:47Z","title":"PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07872","kind":"arxiv","version":1},"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":"sha256:714e836db7cba296d196ff0082ad59d04645f48802927482c7c3f2d546a4b240","target":"record","created_at":"2026-07-05T07:44:13Z","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":"d7196323cbb364cef9a5b7ede7989f44330d78bbe737f85b32a73df165396ffc","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-02-12T18:33:47Z","title_canon_sha256":"f5ebb3fb981af6e263d5978ca6632afbe6b134b2768d18d64eab8895c8d55eb0"},"schema_version":"1.0","source":{"id":"2402.07872","kind":"arxiv","version":1}},"canonical_sha256":"dedbd41c1baa874d957e251a22e1ae06328bba26af5b0b277f33bd5e8c2d23b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dedbd41c1baa874d957e251a22e1ae06328bba26af5b0b277f33bd5e8c2d23b0","first_computed_at":"2026-07-05T07:44:13.655029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:44:13.655029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TA1LooZL9bKNp/ZMCz2GSx5AAQsRioiC+n1ngSJ+MZnP8vg6qQeAbcrqxofZL/HBON3tM348nwMEWFqjw5eVAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:44:13.655537Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07872","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:714e836db7cba296d196ff0082ad59d04645f48802927482c7c3f2d546a4b240","sha256:b3e60238699e3de17474afb815d44c091d0383b3488906b7a7711ab5c5729dc4"],"state_sha256":"5cf5e07126d96597b6b56810311ec408f497f9984e44d9ae2bc1979d1cdbc2f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XDotluWRDDmA0fX6XfQ+g29TW228tcngj0apehDnslR3QvaEbrZPRLrP7XFdIEs18Qomz1W3W5IkEFzB7LWbBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:06:28.011636Z","bundle_sha256":"52ffa22a3f9f76e5079eab342377ad0d32578d43d748ef4681d59ccd9bf7bc57"}}