{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PEQSFWR4D2PDWVEO24ZOTI6QON","short_pith_number":"pith:PEQSFWR4","canonical_record":{"source":{"id":"2605.29119","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T21:28:26Z","cross_cats_sorted":[],"title_canon_sha256":"cb2a065b21808b4aa6faccb944a1388d8346eec97c98b7389a464bf7a85ec733","abstract_canon_sha256":"a035d74e69025c736500f3a1814d0084b09283924fd94897f099fe6a1ef1205a"},"schema_version":"1.0"},"canonical_sha256":"792122da3c1e9e3b548ed732e9a3d0734b1dc4c397bd352fc46786d5954549a2","source":{"kind":"arxiv","id":"2605.29119","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29119","created_at":"2026-05-29T01:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29119v1","created_at":"2026-05-29T01:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29119","created_at":"2026-05-29T01:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"PEQSFWR4D2PD","created_at":"2026-05-29T01:05:19Z"},{"alias_kind":"pith_short_16","alias_value":"PEQSFWR4D2PDWVEO","created_at":"2026-05-29T01:05:19Z"},{"alias_kind":"pith_short_8","alias_value":"PEQSFWR4","created_at":"2026-05-29T01:05:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PEQSFWR4D2PDWVEO24ZOTI6QON","target":"record","payload":{"canonical_record":{"source":{"id":"2605.29119","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T21:28:26Z","cross_cats_sorted":[],"title_canon_sha256":"cb2a065b21808b4aa6faccb944a1388d8346eec97c98b7389a464bf7a85ec733","abstract_canon_sha256":"a035d74e69025c736500f3a1814d0084b09283924fd94897f099fe6a1ef1205a"},"schema_version":"1.0"},"canonical_sha256":"792122da3c1e9e3b548ed732e9a3d0734b1dc4c397bd352fc46786d5954549a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:19.241795Z","signature_b64":"EUQeai/eUvYqwWmhUgeV+MFbZF7iIwxlMpdkt1yUrbBEwj3E54pQwEEYwLunvDV0nhAlQkWH168D9s48hZfbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"792122da3c1e9e3b548ed732e9a3d0734b1dc4c397bd352fc46786d5954549a2","last_reissued_at":"2026-05-29T01:05:19.240854Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:19.240854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.29119","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":"2026-05-29T01:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xjjQfsrwVwlUr5F0GwpaXSHTvSKXr7CiqCf7bckmtcz1QtJ9ZTkEv7h2B13rfmmPtHCojbFZJQ8D7chXcVRxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T02:19:52.333977Z"},"content_sha256":"774c6d9e9fb66552555581c92ce250207a26340c560cabed4376bdd40547db64","schema_version":"1.0","event_id":"sha256:774c6d9e9fb66552555581c92ce250207a26340c560cabed4376bdd40547db64"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PEQSFWR4D2PDWVEO24ZOTI6QON","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PRO-CUA: Process-Reward Optimization for Computer Use Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Han Zhao, Hao Bai, Rui Yang, Tong Zhang, Yifei He","submitted_at":"2026-05-27T21:28:26Z","abstract_excerpt":"Computer use agents (CUAs) have shown strong potential for automating complex digital workflows, yet their training remains constrained by costly live environment interaction and limited high-quality supervision. Existing filtered behavior cloning pipelines suffer from imitation bottlenecks, including distribution shift from the expert demonstration and the absence of negative learning signals. Meanwhile, standard trajectory-level reinforcement learning struggles with sparse rewards, ambiguous credit assignment, and high infrastructure costs for long-horizon GUI interaction. In this work, we p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29119","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/2605.29119/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":"2026-05-29T01:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SDaS9at81n7vw5qhgN9U12JyU41blnPllaL0jgpgx+ZTQXYa4wlxSNFRBLhK9vDr3qbcDWuCdPKiOHuIqx2ODA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T02:19:52.334770Z"},"content_sha256":"1bf37a7b81d9bfbbbce0720a5ab8712fdad3a84da1d11ae6d8a79788afbb44f5","schema_version":"1.0","event_id":"sha256:1bf37a7b81d9bfbbbce0720a5ab8712fdad3a84da1d11ae6d8a79788afbb44f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PEQSFWR4D2PDWVEO24ZOTI6QON/bundle.json","state_url":"https://pith.science/pith/PEQSFWR4D2PDWVEO24ZOTI6QON/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PEQSFWR4D2PDWVEO24ZOTI6QON/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":"2026-06-12T02:19:52Z","links":{"resolver":"https://pith.science/pith/PEQSFWR4D2PDWVEO24ZOTI6QON","bundle":"https://pith.science/pith/PEQSFWR4D2PDWVEO24ZOTI6QON/bundle.json","state":"https://pith.science/pith/PEQSFWR4D2PDWVEO24ZOTI6QON/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PEQSFWR4D2PDWVEO24ZOTI6QON/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PEQSFWR4D2PDWVEO24ZOTI6QON","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":"a035d74e69025c736500f3a1814d0084b09283924fd94897f099fe6a1ef1205a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T21:28:26Z","title_canon_sha256":"cb2a065b21808b4aa6faccb944a1388d8346eec97c98b7389a464bf7a85ec733"},"schema_version":"1.0","source":{"id":"2605.29119","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29119","created_at":"2026-05-29T01:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29119v1","created_at":"2026-05-29T01:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29119","created_at":"2026-05-29T01:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"PEQSFWR4D2PD","created_at":"2026-05-29T01:05:19Z"},{"alias_kind":"pith_short_16","alias_value":"PEQSFWR4D2PDWVEO","created_at":"2026-05-29T01:05:19Z"},{"alias_kind":"pith_short_8","alias_value":"PEQSFWR4","created_at":"2026-05-29T01:05:19Z"}],"graph_snapshots":[{"event_id":"sha256:1bf37a7b81d9bfbbbce0720a5ab8712fdad3a84da1d11ae6d8a79788afbb44f5","target":"graph","created_at":"2026-05-29T01:05:19Z","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/2605.29119/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Computer use agents (CUAs) have shown strong potential for automating complex digital workflows, yet their training remains constrained by costly live environment interaction and limited high-quality supervision. Existing filtered behavior cloning pipelines suffer from imitation bottlenecks, including distribution shift from the expert demonstration and the absence of negative learning signals. Meanwhile, standard trajectory-level reinforcement learning struggles with sparse rewards, ambiguous credit assignment, and high infrastructure costs for long-horizon GUI interaction. In this work, we p","authors_text":"Han Zhao, Hao Bai, Rui Yang, Tong Zhang, Yifei He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T21:28:26Z","title":"PRO-CUA: Process-Reward Optimization for Computer Use Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29119","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":"sha256:774c6d9e9fb66552555581c92ce250207a26340c560cabed4376bdd40547db64","target":"record","created_at":"2026-05-29T01:05:19Z","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":"a035d74e69025c736500f3a1814d0084b09283924fd94897f099fe6a1ef1205a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T21:28:26Z","title_canon_sha256":"cb2a065b21808b4aa6faccb944a1388d8346eec97c98b7389a464bf7a85ec733"},"schema_version":"1.0","source":{"id":"2605.29119","kind":"arxiv","version":1}},"canonical_sha256":"792122da3c1e9e3b548ed732e9a3d0734b1dc4c397bd352fc46786d5954549a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"792122da3c1e9e3b548ed732e9a3d0734b1dc4c397bd352fc46786d5954549a2","first_computed_at":"2026-05-29T01:05:19.240854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:19.240854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EUQeai/eUvYqwWmhUgeV+MFbZF7iIwxlMpdkt1yUrbBEwj3E54pQwEEYwLunvDV0nhAlQkWH168D9s48hZfbBg==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:19.241795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29119","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:774c6d9e9fb66552555581c92ce250207a26340c560cabed4376bdd40547db64","sha256:1bf37a7b81d9bfbbbce0720a5ab8712fdad3a84da1d11ae6d8a79788afbb44f5"],"state_sha256":"6d601c68a520db8aa0d394a306107b211c59b3bc2fdf2d8d9760a8ddb0c9c020"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7uVI4xmtiMWXHA9Hy6FFfFcfX6IwZCK6Qt/aubDTB3ZBo6M8iwNpt63jmQWT5FvcCeKCbdzhLfJSTanrlGnqBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T02:19:52.339371Z","bundle_sha256":"6836f1418e21829c0eeca8233bc87f28072c6415093966c7ad98be995c240522"}}