{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KLXVG5R444CQYIRGBG2WA7X73Y","short_pith_number":"pith:KLXVG5R4","canonical_record":{"source":{"id":"2402.11941","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T08:29:03Z","cross_cats_sorted":[],"title_canon_sha256":"fba7e2422e92a197c8550ba8d257596b8329bfbc981ec5e4062c997bb20684fa","abstract_canon_sha256":"0318b160e55d851c78c10ee559d503a59ff8414dba78cbf1e2d376f51d4a2851"},"schema_version":"1.0"},"canonical_sha256":"52ef53763ce7050c222609b5607effde1e0f6bc1c1ec1e0764f47b78b77839ed","source":{"kind":"arxiv","id":"2402.11941","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11941","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11941v3","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11941","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_12","alias_value":"KLXVG5R444CQ","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_16","alias_value":"KLXVG5R444CQYIRG","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_8","alias_value":"KLXVG5R4","created_at":"2026-07-05T08:26:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KLXVG5R444CQYIRGBG2WA7X73Y","target":"record","payload":{"canonical_record":{"source":{"id":"2402.11941","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T08:29:03Z","cross_cats_sorted":[],"title_canon_sha256":"fba7e2422e92a197c8550ba8d257596b8329bfbc981ec5e4062c997bb20684fa","abstract_canon_sha256":"0318b160e55d851c78c10ee559d503a59ff8414dba78cbf1e2d376f51d4a2851"},"schema_version":"1.0"},"canonical_sha256":"52ef53763ce7050c222609b5607effde1e0f6bc1c1ec1e0764f47b78b77839ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:20.022468Z","signature_b64":"Y1sBBZJkeuyjj13PAVdGDw4ga8927vd2y5Wlpt0Yb+Ny5ICqu/LJ19GzysC7o93F9+btTfsK7cXoUzHpmg5KBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52ef53763ce7050c222609b5607effde1e0f6bc1c1ec1e0764f47b78b77839ed","last_reissued_at":"2026-07-05T08:26:20.021900Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:20.021900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.11941","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":"2026-07-05T08:26:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6FZVaTb7ixAlZ7xUBbG8q6uHNc2tlJYH9z6DsndrTneJeMyOXcefTUNaaAcfbbq/o8zLLLWiK/hnbkZP3eYgDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:49:21.929312Z"},"content_sha256":"5c4617ac2e0b984e87de830c34bd9cd945467e2fa5d2dbbdf04d1c21de63a1e6","schema_version":"1.0","event_id":"sha256:5c4617ac2e0b984e87de830c34bd9cd945467e2fa5d2dbbdf04d1c21de63a1e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KLXVG5R444CQYIRGBG2WA7X73Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Xinbei Ma, Zhuosheng Zhang","submitted_at":"2024-02-19T08:29:03Z","abstract_excerpt":"Multimodal large language models (MLLMs) have shown remarkable potential as human-like autonomous language agents to interact with real-world environments, especially for graphical user interface (GUI) automation. However, those GUI agents require comprehensive cognition ability including exhaustive perception and reliable action response. We propose a Comprehensive Cognitive LLM Agent, CoCo-Agent, with two novel approaches, comprehensive environment perception (CEP) and conditional action prediction (CAP), to systematically improve the GUI automation performance. First, CEP facilitates the GU"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11941","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/2402.11941/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":"2026-07-05T08:26:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2EPXIVBGEMDEzR/mIhBC64hIiDfGc5XEtMmWVsSWnw+S+GycWjlzpfsa1Ofxmz/ZMCG2my5aLYPI2rnqQkD2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:49:21.929825Z"},"content_sha256":"79dca3f42da26bb2fe46c1f854dbf8783765f00b568c6084aab8c1f8924cda1e","schema_version":"1.0","event_id":"sha256:79dca3f42da26bb2fe46c1f854dbf8783765f00b568c6084aab8c1f8924cda1e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KLXVG5R444CQYIRGBG2WA7X73Y/bundle.json","state_url":"https://pith.science/pith/KLXVG5R444CQYIRGBG2WA7X73Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KLXVG5R444CQYIRGBG2WA7X73Y/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":"2026-08-10T12:49:21Z","links":{"resolver":"https://pith.science/pith/KLXVG5R444CQYIRGBG2WA7X73Y","bundle":"https://pith.science/pith/KLXVG5R444CQYIRGBG2WA7X73Y/bundle.json","state":"https://pith.science/pith/KLXVG5R444CQYIRGBG2WA7X73Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KLXVG5R444CQYIRGBG2WA7X73Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KLXVG5R444CQYIRGBG2WA7X73Y","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":"0318b160e55d851c78c10ee559d503a59ff8414dba78cbf1e2d376f51d4a2851","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T08:29:03Z","title_canon_sha256":"fba7e2422e92a197c8550ba8d257596b8329bfbc981ec5e4062c997bb20684fa"},"schema_version":"1.0","source":{"id":"2402.11941","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11941","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11941v3","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11941","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_12","alias_value":"KLXVG5R444CQ","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_16","alias_value":"KLXVG5R444CQYIRG","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_8","alias_value":"KLXVG5R4","created_at":"2026-07-05T08:26:20Z"}],"graph_snapshots":[{"event_id":"sha256:79dca3f42da26bb2fe46c1f854dbf8783765f00b568c6084aab8c1f8924cda1e","target":"graph","created_at":"2026-07-05T08:26:20Z","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/2402.11941/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have shown remarkable potential as human-like autonomous language agents to interact with real-world environments, especially for graphical user interface (GUI) automation. However, those GUI agents require comprehensive cognition ability including exhaustive perception and reliable action response. We propose a Comprehensive Cognitive LLM Agent, CoCo-Agent, with two novel approaches, comprehensive environment perception (CEP) and conditional action prediction (CAP), to systematically improve the GUI automation performance. First, CEP facilitates the GU","authors_text":"Hai Zhao, Xinbei Ma, Zhuosheng Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T08:29:03Z","title":"CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11941","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":"sha256:5c4617ac2e0b984e87de830c34bd9cd945467e2fa5d2dbbdf04d1c21de63a1e6","target":"record","created_at":"2026-07-05T08:26:20Z","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":"0318b160e55d851c78c10ee559d503a59ff8414dba78cbf1e2d376f51d4a2851","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T08:29:03Z","title_canon_sha256":"fba7e2422e92a197c8550ba8d257596b8329bfbc981ec5e4062c997bb20684fa"},"schema_version":"1.0","source":{"id":"2402.11941","kind":"arxiv","version":3}},"canonical_sha256":"52ef53763ce7050c222609b5607effde1e0f6bc1c1ec1e0764f47b78b77839ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52ef53763ce7050c222609b5607effde1e0f6bc1c1ec1e0764f47b78b77839ed","first_computed_at":"2026-07-05T08:26:20.021900Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:20.021900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y1sBBZJkeuyjj13PAVdGDw4ga8927vd2y5Wlpt0Yb+Ny5ICqu/LJ19GzysC7o93F9+btTfsK7cXoUzHpmg5KBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:20.022468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11941","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c4617ac2e0b984e87de830c34bd9cd945467e2fa5d2dbbdf04d1c21de63a1e6","sha256:79dca3f42da26bb2fe46c1f854dbf8783765f00b568c6084aab8c1f8924cda1e"],"state_sha256":"3b043408d0d88f0442b02a72275af4e43c31e6f4766ed99d6626ca8bffac2217"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cSfhSsdWpEdxyjJgVxei7ss53FH048GGmY2F4vGsko7Krrnd6gUU35GwGPCjy7lBzHpSiUatV/I1FL0emoDqDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:49:21.934076Z","bundle_sha256":"023ace8666fad73b406f1d5e3f5ac9a74fbf0490fd7ec3cab57fe37b513521df"}}