{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:X5JRE3LZCOVOMMI65Z6CXJME7W","short_pith_number":"pith:X5JRE3LZ","canonical_record":{"source":{"id":"2310.04716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-07T07:22:41Z","cross_cats_sorted":[],"title_canon_sha256":"16aad16cd27bb14cbd50bf30f2b099fedec4d824e054f3a3b0b211e74a428fd1","abstract_canon_sha256":"5fdd2f1bca99efc0eb0215f74edd16fa88c75a3207bbd1336b88bccb1a4c7a60"},"schema_version":"1.0"},"canonical_sha256":"bf53126d7913aae6311eee7c2ba584fd8435bd88a6749566e4b193d13da94933","source":{"kind":"arxiv","id":"2310.04716","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04716","created_at":"2026-07-05T06:58:22Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04716v1","created_at":"2026-07-05T06:58:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04716","created_at":"2026-07-05T06:58:22Z"},{"alias_kind":"pith_short_12","alias_value":"X5JRE3LZCOVO","created_at":"2026-07-05T06:58:22Z"},{"alias_kind":"pith_short_16","alias_value":"X5JRE3LZCOVOMMI6","created_at":"2026-07-05T06:58:22Z"},{"alias_kind":"pith_short_8","alias_value":"X5JRE3LZ","created_at":"2026-07-05T06:58:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:X5JRE3LZCOVOMMI65Z6CXJME7W","target":"record","payload":{"canonical_record":{"source":{"id":"2310.04716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-07T07:22:41Z","cross_cats_sorted":[],"title_canon_sha256":"16aad16cd27bb14cbd50bf30f2b099fedec4d824e054f3a3b0b211e74a428fd1","abstract_canon_sha256":"5fdd2f1bca99efc0eb0215f74edd16fa88c75a3207bbd1336b88bccb1a4c7a60"},"schema_version":"1.0"},"canonical_sha256":"bf53126d7913aae6311eee7c2ba584fd8435bd88a6749566e4b193d13da94933","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:22.030119Z","signature_b64":"aM9k91D9yl5T9rchGSZU5Nt2uh1zWkaZP0jW+ymi92s/JPzy6EC2J564cwR771x+5zyvW0D/5aivPd4lbFxaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf53126d7913aae6311eee7c2ba584fd8435bd88a6749566e4b193d13da94933","last_reissued_at":"2026-07-05T06:58:22.029707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:22.029707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.04716","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":"2026-07-05T06:58:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M3hc/Edih3Kp4kWBxhBg2hC8EQsGnqwIMgLt0duDXySMz6WBpvqeEGlWH4+z1mzaQVIOoty0HOe9ni5mjx/aDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:38:22.858144Z"},"content_sha256":"4379a452bd87098b5ab35c3c44637954268ca250f9f397fcc22cb20c602147d2","schema_version":"1.0","event_id":"sha256:4379a452bd87098b5ab35c3c44637954268ca250f9f397fcc22cb20c602147d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:X5JRE3LZCOVOMMI65Z6CXJME7W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wenxuan Xie, Xiaoyi Zhang, Yan Lu, Zhizheng Zhang","submitted_at":"2023-10-07T07:22:41Z","abstract_excerpt":"Recent popularity of Large Language Models (LLMs) has opened countless possibilities in automating numerous AI tasks by connecting LLMs to various domain-specific models or APIs, where LLMs serve as dispatchers while domain-specific models or APIs are action executors. Despite the vast numbers of domain-specific models/APIs, they still struggle to comprehensively cover super diverse automation demands in the interaction between human and User Interfaces (UIs). In this work, we build a multimodal model to ground natural language instructions in given UI screenshots as a generic UI task automati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04716","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/2310.04716/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":"2026-07-05T06:58:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TrMKlhQb9DDtxJK2slNiwk/kD/qEgtr/hAWPf3sAiQ4MQ2E40VKZj6j5vUjdqO+C2ixV1Q2D2vS7w2XU3Q3aBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:38:22.859097Z"},"content_sha256":"d285ddf3df88cadbab0bcc8365554455abfd3d70f6eccf6f2034f0fe2e188b33","schema_version":"1.0","event_id":"sha256:d285ddf3df88cadbab0bcc8365554455abfd3d70f6eccf6f2034f0fe2e188b33"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X5JRE3LZCOVOMMI65Z6CXJME7W/bundle.json","state_url":"https://pith.science/pith/X5JRE3LZCOVOMMI65Z6CXJME7W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X5JRE3LZCOVOMMI65Z6CXJME7W/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":"2026-08-14T08:38:22Z","links":{"resolver":"https://pith.science/pith/X5JRE3LZCOVOMMI65Z6CXJME7W","bundle":"https://pith.science/pith/X5JRE3LZCOVOMMI65Z6CXJME7W/bundle.json","state":"https://pith.science/pith/X5JRE3LZCOVOMMI65Z6CXJME7W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X5JRE3LZCOVOMMI65Z6CXJME7W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:X5JRE3LZCOVOMMI65Z6CXJME7W","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":"5fdd2f1bca99efc0eb0215f74edd16fa88c75a3207bbd1336b88bccb1a4c7a60","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-07T07:22:41Z","title_canon_sha256":"16aad16cd27bb14cbd50bf30f2b099fedec4d824e054f3a3b0b211e74a428fd1"},"schema_version":"1.0","source":{"id":"2310.04716","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04716","created_at":"2026-07-05T06:58:22Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04716v1","created_at":"2026-07-05T06:58:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04716","created_at":"2026-07-05T06:58:22Z"},{"alias_kind":"pith_short_12","alias_value":"X5JRE3LZCOVO","created_at":"2026-07-05T06:58:22Z"},{"alias_kind":"pith_short_16","alias_value":"X5JRE3LZCOVOMMI6","created_at":"2026-07-05T06:58:22Z"},{"alias_kind":"pith_short_8","alias_value":"X5JRE3LZ","created_at":"2026-07-05T06:58:22Z"}],"graph_snapshots":[{"event_id":"sha256:d285ddf3df88cadbab0bcc8365554455abfd3d70f6eccf6f2034f0fe2e188b33","target":"graph","created_at":"2026-07-05T06:58:22Z","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/2310.04716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent popularity of Large Language Models (LLMs) has opened countless possibilities in automating numerous AI tasks by connecting LLMs to various domain-specific models or APIs, where LLMs serve as dispatchers while domain-specific models or APIs are action executors. Despite the vast numbers of domain-specific models/APIs, they still struggle to comprehensively cover super diverse automation demands in the interaction between human and User Interfaces (UIs). In this work, we build a multimodal model to ground natural language instructions in given UI screenshots as a generic UI task automati","authors_text":"Wenxuan Xie, Xiaoyi Zhang, Yan Lu, Zhizheng Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-07T07:22:41Z","title":"Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04716","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":"sha256:4379a452bd87098b5ab35c3c44637954268ca250f9f397fcc22cb20c602147d2","target":"record","created_at":"2026-07-05T06:58:22Z","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":"5fdd2f1bca99efc0eb0215f74edd16fa88c75a3207bbd1336b88bccb1a4c7a60","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-07T07:22:41Z","title_canon_sha256":"16aad16cd27bb14cbd50bf30f2b099fedec4d824e054f3a3b0b211e74a428fd1"},"schema_version":"1.0","source":{"id":"2310.04716","kind":"arxiv","version":1}},"canonical_sha256":"bf53126d7913aae6311eee7c2ba584fd8435bd88a6749566e4b193d13da94933","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf53126d7913aae6311eee7c2ba584fd8435bd88a6749566e4b193d13da94933","first_computed_at":"2026-07-05T06:58:22.029707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:22.029707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aM9k91D9yl5T9rchGSZU5Nt2uh1zWkaZP0jW+ymi92s/JPzy6EC2J564cwR771x+5zyvW0D/5aivPd4lbFxaBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:22.030119Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.04716","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4379a452bd87098b5ab35c3c44637954268ca250f9f397fcc22cb20c602147d2","sha256:d285ddf3df88cadbab0bcc8365554455abfd3d70f6eccf6f2034f0fe2e188b33"],"state_sha256":"7da8d32b0699471e6f2fd72effadd2a82185a0e7378bc1b513f425a7bcbd3a61"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dSOaPeS7FlEApNx7/etPp+wDPubIaGpyXpLo0Y+gn/llvOfyiRMZhEcSfJ8NTaVazJcEl7NCAoKBZzgISfNJAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:38:22.865300Z","bundle_sha256":"dd44c579bf33faaf74d7fdf7a853dbab649cdc14fadf49399a1c34d6bce175fc"}}