{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4NBYRBFRYRBB5EJV4GV454VQKW","short_pith_number":"pith:4NBYRBFR","canonical_record":{"source":{"id":"2503.15500","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-01-21T02:27:07Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"caf5732b5916b2ed2dab6a9f6eed072090adf1d40a770eecf24fe93918617a83","abstract_canon_sha256":"23a8774c59e74a3c5472203c096abf2cd190dbfd43b5795a7677798e2ededed5"},"schema_version":"1.0"},"canonical_sha256":"e3438884b1c4421e9135e1abcef2b055b12e132a478af70b4ac5ec0c0e9673aa","source":{"kind":"arxiv","id":"2503.15500","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15500","created_at":"2026-07-05T10:35:51Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15500v1","created_at":"2026-07-05T10:35:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15500","created_at":"2026-07-05T10:35:51Z"},{"alias_kind":"pith_short_12","alias_value":"4NBYRBFRYRBB","created_at":"2026-07-05T10:35:51Z"},{"alias_kind":"pith_short_16","alias_value":"4NBYRBFRYRBB5EJV","created_at":"2026-07-05T10:35:51Z"},{"alias_kind":"pith_short_8","alias_value":"4NBYRBFR","created_at":"2026-07-05T10:35:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4NBYRBFRYRBB5EJV4GV454VQKW","target":"record","payload":{"canonical_record":{"source":{"id":"2503.15500","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-01-21T02:27:07Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"caf5732b5916b2ed2dab6a9f6eed072090adf1d40a770eecf24fe93918617a83","abstract_canon_sha256":"23a8774c59e74a3c5472203c096abf2cd190dbfd43b5795a7677798e2ededed5"},"schema_version":"1.0"},"canonical_sha256":"e3438884b1c4421e9135e1abcef2b055b12e132a478af70b4ac5ec0c0e9673aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:51.370663Z","signature_b64":"7QjhVNP6z/G6qqIa9LHfpKmIGCiq07curXu0RqUzzgDQX10U+NwQaBr+/Ei2HkgONy/+n/zMlMg/YbndAj6NCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3438884b1c4421e9135e1abcef2b055b12e132a478af70b4ac5ec0c0e9673aa","last_reissued_at":"2026-07-05T10:35:51.370056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:51.370056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.15500","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":"2026-07-05T10:35:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aH6zMntISOXDBop4Jab6+BuQcsE92gz3QGnbVbN7FaGTcima9BeyI++oBfmteoXh8JSOt5UvZ3jwYixRP43SCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:27:45.707868Z"},"content_sha256":"aa5d2cc217bde851dae56e55b3c03c1edf97da55d96ebea8d9186a39eb616247","schema_version":"1.0","event_id":"sha256:aa5d2cc217bde851dae56e55b3c03c1edf97da55d96ebea8d9186a39eb616247"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4NBYRBFRYRBB5EJV4GV454VQKW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ImageInThat: Manipulating Images to Convey User Instructions to Robots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.HC","authors_text":"Anthony Tang, Bilge Mutlu, Blaine Lewis, Jiannan Li, Karthik Mahadevan, Tovi Grossman","submitted_at":"2025-01-21T02:27:07Z","abstract_excerpt":"Foundation models are rapidly improving the capability of robots in performing everyday tasks autonomously such as meal preparation, yet robots will still need to be instructed by humans due to model performance, the difficulty of capturing user preferences, and the need for user agency. Robots can be instructed using various methods-natural language conveys immediate instructions but can be abstract or ambiguous, whereas end-user programming supports longer horizon tasks but interfaces face difficulties in capturing user intent. In this work, we propose using direct manipulation of images as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15500","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/2503.15500/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":"2026-07-05T10:35:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7hAH/lOKaJw6NgKKfElp6D+GDTwrdadOCPlJRyKHBZ27rzAA49UEnReAI3Gg7wbc5tarBV0A/vzxdHc/wIL0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:27:45.708389Z"},"content_sha256":"bb7b33906efa62b8612fbf0a1e520b5fe1352e133ec8bce1e4390c5800a8d825","schema_version":"1.0","event_id":"sha256:bb7b33906efa62b8612fbf0a1e520b5fe1352e133ec8bce1e4390c5800a8d825"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4NBYRBFRYRBB5EJV4GV454VQKW/bundle.json","state_url":"https://pith.science/pith/4NBYRBFRYRBB5EJV4GV454VQKW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4NBYRBFRYRBB5EJV4GV454VQKW/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":"2026-08-11T08:27:45Z","links":{"resolver":"https://pith.science/pith/4NBYRBFRYRBB5EJV4GV454VQKW","bundle":"https://pith.science/pith/4NBYRBFRYRBB5EJV4GV454VQKW/bundle.json","state":"https://pith.science/pith/4NBYRBFRYRBB5EJV4GV454VQKW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4NBYRBFRYRBB5EJV4GV454VQKW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4NBYRBFRYRBB5EJV4GV454VQKW","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":"23a8774c59e74a3c5472203c096abf2cd190dbfd43b5795a7677798e2ededed5","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-01-21T02:27:07Z","title_canon_sha256":"caf5732b5916b2ed2dab6a9f6eed072090adf1d40a770eecf24fe93918617a83"},"schema_version":"1.0","source":{"id":"2503.15500","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15500","created_at":"2026-07-05T10:35:51Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15500v1","created_at":"2026-07-05T10:35:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15500","created_at":"2026-07-05T10:35:51Z"},{"alias_kind":"pith_short_12","alias_value":"4NBYRBFRYRBB","created_at":"2026-07-05T10:35:51Z"},{"alias_kind":"pith_short_16","alias_value":"4NBYRBFRYRBB5EJV","created_at":"2026-07-05T10:35:51Z"},{"alias_kind":"pith_short_8","alias_value":"4NBYRBFR","created_at":"2026-07-05T10:35:51Z"}],"graph_snapshots":[{"event_id":"sha256:bb7b33906efa62b8612fbf0a1e520b5fe1352e133ec8bce1e4390c5800a8d825","target":"graph","created_at":"2026-07-05T10:35:51Z","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/2503.15500/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Foundation models are rapidly improving the capability of robots in performing everyday tasks autonomously such as meal preparation, yet robots will still need to be instructed by humans due to model performance, the difficulty of capturing user preferences, and the need for user agency. Robots can be instructed using various methods-natural language conveys immediate instructions but can be abstract or ambiguous, whereas end-user programming supports longer horizon tasks but interfaces face difficulties in capturing user intent. In this work, we propose using direct manipulation of images as ","authors_text":"Anthony Tang, Bilge Mutlu, Blaine Lewis, Jiannan Li, Karthik Mahadevan, Tovi Grossman","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-01-21T02:27:07Z","title":"ImageInThat: Manipulating Images to Convey User Instructions to Robots"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15500","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:aa5d2cc217bde851dae56e55b3c03c1edf97da55d96ebea8d9186a39eb616247","target":"record","created_at":"2026-07-05T10:35:51Z","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":"23a8774c59e74a3c5472203c096abf2cd190dbfd43b5795a7677798e2ededed5","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-01-21T02:27:07Z","title_canon_sha256":"caf5732b5916b2ed2dab6a9f6eed072090adf1d40a770eecf24fe93918617a83"},"schema_version":"1.0","source":{"id":"2503.15500","kind":"arxiv","version":1}},"canonical_sha256":"e3438884b1c4421e9135e1abcef2b055b12e132a478af70b4ac5ec0c0e9673aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3438884b1c4421e9135e1abcef2b055b12e132a478af70b4ac5ec0c0e9673aa","first_computed_at":"2026-07-05T10:35:51.370056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:51.370056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7QjhVNP6z/G6qqIa9LHfpKmIGCiq07curXu0RqUzzgDQX10U+NwQaBr+/Ei2HkgONy/+n/zMlMg/YbndAj6NCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:51.370663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.15500","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa5d2cc217bde851dae56e55b3c03c1edf97da55d96ebea8d9186a39eb616247","sha256:bb7b33906efa62b8612fbf0a1e520b5fe1352e133ec8bce1e4390c5800a8d825"],"state_sha256":"6a0fd3ade78763fc17349e0adf014f5faad245aa432c07e7fdcaa9ce2b32ca04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PKQWhGUfzJx+7sZIvpHydCnnT/lPPM+lqgLW0SDIX/WCAjpq1Er2j3RPtcUVPEFe3bY0aknZiuxekckO0oJNCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T08:27:45.712939Z","bundle_sha256":"5193e1986e5d15291f987a0f9ad6907199b5348c9d2e64f5310ac88f733ded88"}}