{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5OWTG55CQM26K45SG7FN5E74WE","short_pith_number":"pith:5OWTG55C","canonical_record":{"source":{"id":"2312.08914","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T13:20:57Z","cross_cats_sorted":[],"title_canon_sha256":"aa5a0704f04c1339748622f898540f995331262d4d04648abebcfe9290bd7d90","abstract_canon_sha256":"9a10bdcfb541b92d0f0078da7155d4f09dce138f9ae9bbc2fd1eaa14f6329497"},"schema_version":"1.0"},"canonical_sha256":"ebad3377a28335e573b237cade93fcb1389921d080ba13bd563a618f50f83c51","source":{"kind":"arxiv","id":"2312.08914","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08914","created_at":"2026-07-05T09:54:24Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08914v3","created_at":"2026-07-05T09:54:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08914","created_at":"2026-07-05T09:54:24Z"},{"alias_kind":"pith_short_12","alias_value":"5OWTG55CQM26","created_at":"2026-07-05T09:54:24Z"},{"alias_kind":"pith_short_16","alias_value":"5OWTG55CQM26K45S","created_at":"2026-07-05T09:54:24Z"},{"alias_kind":"pith_short_8","alias_value":"5OWTG55C","created_at":"2026-07-05T09:54:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5OWTG55CQM26K45SG7FN5E74WE","target":"record","payload":{"canonical_record":{"source":{"id":"2312.08914","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T13:20:57Z","cross_cats_sorted":[],"title_canon_sha256":"aa5a0704f04c1339748622f898540f995331262d4d04648abebcfe9290bd7d90","abstract_canon_sha256":"9a10bdcfb541b92d0f0078da7155d4f09dce138f9ae9bbc2fd1eaa14f6329497"},"schema_version":"1.0"},"canonical_sha256":"ebad3377a28335e573b237cade93fcb1389921d080ba13bd563a618f50f83c51","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:24.566994Z","signature_b64":"+c2pcZH6seLDTXkA/mObP0qf3x2TDuwJWcg6xXj8I5ZgPDuM9DgRgJk1DQ6vMbF25ihfpnbIekemQp9ov5cnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebad3377a28335e573b237cade93fcb1389921d080ba13bd563a618f50f83c51","last_reissued_at":"2026-07-05T09:54:24.566375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:24.566375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.08914","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:54:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e4HcoFdO+xe1Yfe7YzdLzD+5PPTnt9GQjl0OePGjFud/XhPhu6yaF03KZkruZigjSEbW1peD3AZK05vPo1UVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:34:16.256963Z"},"content_sha256":"862762140c950e9d062f760e3bc9d99310ef393516576553bff16ced1c5eac69","schema_version":"1.0","event_id":"sha256:862762140c950e9d062f760e3bc9d99310ef393516576553bff16ced1c5eac69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5OWTG55CQM26K45SG7FN5E74WE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CogAgent: A Visual Language Model for GUI Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Xu, Jiazheng Xu, Jie Tang, Juanzi Li, Junhui Ji, Ming Ding, Qingsong Lv, Weihan Wang, Wenmeng Yu, Wenyi Hong, Yan Wang, Yuxiao Dong, Yuxuan Zhang, Zihan Wang","submitted_at":"2023-12-14T13:20:57Z","abstract_excerpt":"People are spending an enormous amount of time on digital devices through graphical user interfaces (GUIs), e.g., computer or smartphone screens. Large language models (LLMs) such as ChatGPT can assist people in tasks like writing emails, but struggle to understand and interact with GUIs, thus limiting their potential to increase automation levels. In this paper, we introduce CogAgent, an 18-billion-parameter visual language model (VLM) specializing in GUI understanding and navigation. By utilizing both low-resolution and high-resolution image encoders, CogAgent supports input at a resolution "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08914","kind":"arxiv","version":3},"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/2312.08914/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":"2026-07-05T09:54:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pcXQQ2h6hrTJYGQpXqODZrWt080PLyksXfeNoPtvadfpptsezZz/IU7tIsLwA5h//3pj5U+wLktEBw1XGb6TDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:34:16.258093Z"},"content_sha256":"72c416560ff60afb2b31a40a41831579150a3c1b65845721c45e2f118099f695","schema_version":"1.0","event_id":"sha256:72c416560ff60afb2b31a40a41831579150a3c1b65845721c45e2f118099f695"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5OWTG55CQM26K45SG7FN5E74WE/bundle.json","state_url":"https://pith.science/pith/5OWTG55CQM26K45SG7FN5E74WE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5OWTG55CQM26K45SG7FN5E74WE/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":"2026-08-09T06:34:16Z","links":{"resolver":"https://pith.science/pith/5OWTG55CQM26K45SG7FN5E74WE","bundle":"https://pith.science/pith/5OWTG55CQM26K45SG7FN5E74WE/bundle.json","state":"https://pith.science/pith/5OWTG55CQM26K45SG7FN5E74WE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5OWTG55CQM26K45SG7FN5E74WE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5OWTG55CQM26K45SG7FN5E74WE","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":"9a10bdcfb541b92d0f0078da7155d4f09dce138f9ae9bbc2fd1eaa14f6329497","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T13:20:57Z","title_canon_sha256":"aa5a0704f04c1339748622f898540f995331262d4d04648abebcfe9290bd7d90"},"schema_version":"1.0","source":{"id":"2312.08914","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08914","created_at":"2026-07-05T09:54:24Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08914v3","created_at":"2026-07-05T09:54:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08914","created_at":"2026-07-05T09:54:24Z"},{"alias_kind":"pith_short_12","alias_value":"5OWTG55CQM26","created_at":"2026-07-05T09:54:24Z"},{"alias_kind":"pith_short_16","alias_value":"5OWTG55CQM26K45S","created_at":"2026-07-05T09:54:24Z"},{"alias_kind":"pith_short_8","alias_value":"5OWTG55C","created_at":"2026-07-05T09:54:24Z"}],"graph_snapshots":[{"event_id":"sha256:72c416560ff60afb2b31a40a41831579150a3c1b65845721c45e2f118099f695","target":"graph","created_at":"2026-07-05T09:54:24Z","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/2312.08914/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"People are spending an enormous amount of time on digital devices through graphical user interfaces (GUIs), e.g., computer or smartphone screens. Large language models (LLMs) such as ChatGPT can assist people in tasks like writing emails, but struggle to understand and interact with GUIs, thus limiting their potential to increase automation levels. In this paper, we introduce CogAgent, an 18-billion-parameter visual language model (VLM) specializing in GUI understanding and navigation. By utilizing both low-resolution and high-resolution image encoders, CogAgent supports input at a resolution ","authors_text":"Bin Xu, Jiazheng Xu, Jie Tang, Juanzi Li, Junhui Ji, Ming Ding, Qingsong Lv, Weihan Wang, Wenmeng Yu, Wenyi Hong, Yan Wang, Yuxiao Dong, Yuxuan Zhang, Zihan Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T13:20:57Z","title":"CogAgent: A Visual Language Model for GUI Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08914","kind":"arxiv","version":3},"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":"sha256:862762140c950e9d062f760e3bc9d99310ef393516576553bff16ced1c5eac69","target":"record","created_at":"2026-07-05T09:54:24Z","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":"9a10bdcfb541b92d0f0078da7155d4f09dce138f9ae9bbc2fd1eaa14f6329497","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T13:20:57Z","title_canon_sha256":"aa5a0704f04c1339748622f898540f995331262d4d04648abebcfe9290bd7d90"},"schema_version":"1.0","source":{"id":"2312.08914","kind":"arxiv","version":3}},"canonical_sha256":"ebad3377a28335e573b237cade93fcb1389921d080ba13bd563a618f50f83c51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebad3377a28335e573b237cade93fcb1389921d080ba13bd563a618f50f83c51","first_computed_at":"2026-07-05T09:54:24.566375Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:24.566375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+c2pcZH6seLDTXkA/mObP0qf3x2TDuwJWcg6xXj8I5ZgPDuM9DgRgJk1DQ6vMbF25ihfpnbIekemQp9ov5cnCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:24.566994Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.08914","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:862762140c950e9d062f760e3bc9d99310ef393516576553bff16ced1c5eac69","sha256:72c416560ff60afb2b31a40a41831579150a3c1b65845721c45e2f118099f695"],"state_sha256":"6e4e03d45517cff815433f774091bbb72f26d64def9d5f9536ac574547045db9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B2CSTqMQGhJaVYcpMlHvK5vUd7ciO0Fvky6fnMThr8fAdVsONb3XkahZAPlUi6oBzeVLES0RD5Pl4fMTIAQICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:34:16.262608Z","bundle_sha256":"12ad87d7cb660c48f4c749dae5d1c1adffc0082e90f507457f1f4d9974a87bcd"}}