{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3VP3X4RFTKV7JVVN3UKY7ILLEP","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":"0424ca42d0185da41e0493d4a4cfe43fe6b01731344d2ca48469279e28734877","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T12:44:01Z","title_canon_sha256":"3dc0481e1d6e851bd87fea1cca3120d596ba57893b1f9957ef7ba18888864f6f"},"schema_version":"1.0","source":{"id":"2605.23574","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23574","created_at":"2026-05-25T02:02:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23574v1","created_at":"2026-05-25T02:02:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23574","created_at":"2026-05-25T02:02:20Z"},{"alias_kind":"pith_short_12","alias_value":"3VP3X4RFTKV7","created_at":"2026-05-25T02:02:20Z"},{"alias_kind":"pith_short_16","alias_value":"3VP3X4RFTKV7JVVN","created_at":"2026-05-25T02:02:20Z"},{"alias_kind":"pith_short_8","alias_value":"3VP3X4RF","created_at":"2026-05-25T02:02:20Z"}],"graph_snapshots":[{"event_id":"sha256:d934774fcca64f56b8a3ea8c7ae194fdac7b0f8e453a3b7d8e5000082a79b8ea","target":"graph","created_at":"2026-05-25T02:02:20Z","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/2605.23574/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-horizon language agents can make many plausible local tool calls yet fail to persist until a requested count is actually complete. We study this gap as Quantitative Goal Persistence (QGP): whether an agent keeps working until an external verifier confirms enough distinct valid items. PushBench turns this into a benchmark for repository-artifact collection and verifier-backed work units, so repeated work, duplicate submissions, false completion, and progress drift are measured directly rather than hidden behind a final success flag. In matched controller comparisons, a state-tracking retri","authors_text":"Liyou Gao, Shengchao Qin, Wensheng Tang, Yuandao Cai, Yuzhang Zhu","cross_cats":["cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T12:44:01Z","title":"Push Your Agent: Measuring and Enforcing Quantitative Goal Persistence in Long-Horizon LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23574","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":"sha256:85ff001e48e6eea0fe59b918dfda6d4110f568612c17e6e0303c4744f7ede94a","target":"record","created_at":"2026-05-25T02:02:20Z","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":"0424ca42d0185da41e0493d4a4cfe43fe6b01731344d2ca48469279e28734877","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T12:44:01Z","title_canon_sha256":"3dc0481e1d6e851bd87fea1cca3120d596ba57893b1f9957ef7ba18888864f6f"},"schema_version":"1.0","source":{"id":"2605.23574","kind":"arxiv","version":1}},"canonical_sha256":"dd5fbbf2259aabf4d6addd158fa16b23cf659f9eef6438488b5079891b340e9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd5fbbf2259aabf4d6addd158fa16b23cf659f9eef6438488b5079891b340e9c","first_computed_at":"2026-05-25T02:02:20.283285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:02:20.283285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OzInCFv6YeHbxi0EQcFykh6z5DiWNW7ezVC9hk/KhCI1D6tyht1uJ2SOrJHPAzSfsufPYTJo1qlyDOMHrATSBA==","signature_status":"signed_v1","signed_at":"2026-05-25T02:02:20.284086Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23574","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85ff001e48e6eea0fe59b918dfda6d4110f568612c17e6e0303c4744f7ede94a","sha256:d934774fcca64f56b8a3ea8c7ae194fdac7b0f8e453a3b7d8e5000082a79b8ea"],"state_sha256":"0d02fa9797d5bb5e207acc6a770c323ec193c4f62c767ed929dfea8ea45c63ec"}