{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SS3JRCD332SLBYB6NGMXQQZVU4","short_pith_number":"pith:SS3JRCD3","canonical_record":{"source":{"id":"2412.04454","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T18:58:26Z","cross_cats_sorted":[],"title_canon_sha256":"a5deb504993ca2dabbfe454d87f27a0c5412959e16ffd63d95fdcb42d9d3c974","abstract_canon_sha256":"a49b0464fcb57a8d5ff4ed96178df17e73a14922a224929076a8fa6753c05eeb"},"schema_version":"1.0"},"canonical_sha256":"94b698887bdea4b0e03e6999784335a711978c8009ca086c1c494069066dad7b","source":{"kind":"arxiv","id":"2412.04454","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04454","created_at":"2026-05-18T04:03:03Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04454v2","created_at":"2026-05-18T04:03:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04454","created_at":"2026-05-18T04:03:03Z"},{"alias_kind":"pith_short_12","alias_value":"SS3JRCD332SL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"SS3JRCD332SLBYB6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"SS3JRCD3","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SS3JRCD332SLBYB6NGMXQQZVU4","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04454","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T18:58:26Z","cross_cats_sorted":[],"title_canon_sha256":"a5deb504993ca2dabbfe454d87f27a0c5412959e16ffd63d95fdcb42d9d3c974","abstract_canon_sha256":"a49b0464fcb57a8d5ff4ed96178df17e73a14922a224929076a8fa6753c05eeb"},"schema_version":"1.0"},"canonical_sha256":"94b698887bdea4b0e03e6999784335a711978c8009ca086c1c494069066dad7b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:03:03.836585Z","signature_b64":"4fkDDXmSw4KxaLF8IBTpAzLFMPLLhuxCT8uPcBQY464/XSfjpx+A5yxIEQ52N3ma05SLjEZFhEMZTf92Ket3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94b698887bdea4b0e03e6999784335a711978c8009ca086c1c494069066dad7b","last_reissued_at":"2026-05-18T04:03:03.835929Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:03:03.835929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04454","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":"2026-05-18T04:03:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PKSue5vaREyX/Q1ZKdVaILss9POBTqdveoAHABXE75xsEQUhOwDvSm70x9NPRfIhDU/O/LYcGuxpwK1tsruGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T23:34:14.421181Z"},"content_sha256":"e8d73dce47ff732233fe4aaf547e416a4df2ea01bd5194613e166ec7a6c64381","schema_version":"1.0","event_id":"sha256:e8d73dce47ff732233fe4aaf547e416a4df2ea01bd5194613e166ec7a6c64381"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SS3JRCD332SLBYB6NGMXQQZVU4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amrita Saha, Caiming Xiong, Doyen Sahoo, Dunjie Lu, Junli Wang, Tao Yu, Tianbao Xie, Yiheng Xu, Zekun Wang","submitted_at":"2024-12-05T18:58:26Z","abstract_excerpt":"Automating GUI tasks remains challenging due to reliance on textual representations, platform-specific action spaces, and limited reasoning capabilities. We introduce Aguvis, a unified vision-based framework for autonomous GUI agents that directly operates on screen images, standardizes cross-platform interactions and incorporates structured reasoning via inner monologue. To enable this, we construct Aguvis Data Collection, a large-scale dataset with multimodal grounding and reasoning annotations, and develop a two-stage training pipeline that separates GUI grounding from planning and reasonin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04454","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":""},"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":"2026-05-18T04:03:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s30EBBxBYdemJsdCsCArQtYhKfkpAEpO1TEW9aZDTIrkCiZ9CpTAsDeYzoko5yTvmLkQzkFG6vkQT4jYkYG+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T23:34:14.421801Z"},"content_sha256":"07ef2f4155581a10f92631dd3579494b89f8929188373a9f722a3d9ccd4773f8","schema_version":"1.0","event_id":"sha256:07ef2f4155581a10f92631dd3579494b89f8929188373a9f722a3d9ccd4773f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SS3JRCD332SLBYB6NGMXQQZVU4/bundle.json","state_url":"https://pith.science/pith/SS3JRCD332SLBYB6NGMXQQZVU4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SS3JRCD332SLBYB6NGMXQQZVU4/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":"2026-05-18T23:34:14Z","links":{"resolver":"https://pith.science/pith/SS3JRCD332SLBYB6NGMXQQZVU4","bundle":"https://pith.science/pith/SS3JRCD332SLBYB6NGMXQQZVU4/bundle.json","state":"https://pith.science/pith/SS3JRCD332SLBYB6NGMXQQZVU4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SS3JRCD332SLBYB6NGMXQQZVU4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SS3JRCD332SLBYB6NGMXQQZVU4","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":"a49b0464fcb57a8d5ff4ed96178df17e73a14922a224929076a8fa6753c05eeb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T18:58:26Z","title_canon_sha256":"a5deb504993ca2dabbfe454d87f27a0c5412959e16ffd63d95fdcb42d9d3c974"},"schema_version":"1.0","source":{"id":"2412.04454","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04454","created_at":"2026-05-18T04:03:03Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04454v2","created_at":"2026-05-18T04:03:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04454","created_at":"2026-05-18T04:03:03Z"},{"alias_kind":"pith_short_12","alias_value":"SS3JRCD332SL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"SS3JRCD332SLBYB6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"SS3JRCD3","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:07ef2f4155581a10f92631dd3579494b89f8929188373a9f722a3d9ccd4773f8","target":"graph","created_at":"2026-05-18T04:03:03Z","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"},"paper":{"abstract_excerpt":"Automating GUI tasks remains challenging due to reliance on textual representations, platform-specific action spaces, and limited reasoning capabilities. We introduce Aguvis, a unified vision-based framework for autonomous GUI agents that directly operates on screen images, standardizes cross-platform interactions and incorporates structured reasoning via inner monologue. To enable this, we construct Aguvis Data Collection, a large-scale dataset with multimodal grounding and reasoning annotations, and develop a two-stage training pipeline that separates GUI grounding from planning and reasonin","authors_text":"Amrita Saha, Caiming Xiong, Doyen Sahoo, Dunjie Lu, Junli Wang, Tao Yu, Tianbao Xie, Yiheng Xu, Zekun Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T18:58:26Z","title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04454","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:e8d73dce47ff732233fe4aaf547e416a4df2ea01bd5194613e166ec7a6c64381","target":"record","created_at":"2026-05-18T04:03:03Z","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":"a49b0464fcb57a8d5ff4ed96178df17e73a14922a224929076a8fa6753c05eeb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T18:58:26Z","title_canon_sha256":"a5deb504993ca2dabbfe454d87f27a0c5412959e16ffd63d95fdcb42d9d3c974"},"schema_version":"1.0","source":{"id":"2412.04454","kind":"arxiv","version":2}},"canonical_sha256":"94b698887bdea4b0e03e6999784335a711978c8009ca086c1c494069066dad7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94b698887bdea4b0e03e6999784335a711978c8009ca086c1c494069066dad7b","first_computed_at":"2026-05-18T04:03:03.835929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:03:03.835929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4fkDDXmSw4KxaLF8IBTpAzLFMPLLhuxCT8uPcBQY464/XSfjpx+A5yxIEQ52N3ma05SLjEZFhEMZTf92Ket3DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T04:03:03.836585Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04454","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8d73dce47ff732233fe4aaf547e416a4df2ea01bd5194613e166ec7a6c64381","sha256:07ef2f4155581a10f92631dd3579494b89f8929188373a9f722a3d9ccd4773f8"],"state_sha256":"15a263dc52e201f718e4b1ec62c08b70e078b89ebaa1a1304118c2438a2cda72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pEla03sQ4Ej12KpzZrZtPZ+mOL7oyoqyhM+YWENNSo3rseXqmPprsUjeBMDW1t6PdLaA9aeUb708Z3toRATpDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-18T23:34:14.423676Z","bundle_sha256":"3cd255036015b2bfba2b4dc20d9bdb7fcf48f7ddfb1e29c50da64ebeb179d0e5"}}