{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4QWADUUYJ6NI4EOIXM455C62OV","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":"f42f044894a5468f055ee847349035f4011f6edabc8c179634d5a67ff7b1220c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T23:00:25Z","title_canon_sha256":"9f0e6112b81a92ce10c647589e230bb1fa0a02a4875b81690ee3c70e0fc051c5"},"schema_version":"1.0","source":{"id":"2606.20724","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20724","created_at":"2026-06-23T00:11:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20724v1","created_at":"2026-06-23T00:11:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20724","created_at":"2026-06-23T00:11:54Z"},{"alias_kind":"pith_short_12","alias_value":"4QWADUUYJ6NI","created_at":"2026-06-23T00:11:54Z"},{"alias_kind":"pith_short_16","alias_value":"4QWADUUYJ6NI4EOI","created_at":"2026-06-23T00:11:54Z"},{"alias_kind":"pith_short_8","alias_value":"4QWADUUY","created_at":"2026-06-23T00:11:54Z"}],"graph_snapshots":[{"event_id":"sha256:54b3f9480ea66832f28b3cf9f7a6ac7784635542f65846edec0c569f1c4922ce","target":"graph","created_at":"2026-06-23T00:11:54Z","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/2606.20724/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-horizon web agents often fail in ways hidden by final-answer evaluation: they may visit useful pages, produce a well-formed answer, and terminate confidently while still missing fields, over-including unsupported items, or relying on stale evidence. We study these failures with Parallel WebBench, a parallel web-exploration benchmark containing 1,679 verified records: 350 manually curated parallel tasks and 1,329 reconstructed records with verified URL-based trajectories. We train WebExplorer-style agents with GRPO under human-only, balanced human-synthetic, and synthetic-heavy data mixtur","authors_text":"Aagam Sogani, Botao Rui, Minghao Yan, Rishi Agarwal, Shivaram Venkataraman, Swetha Vaidyanathan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T23:00:25Z","title":"When Web Agents Finish but Still Fail: Reproducible Triggers and Trace Diagnostics for Parallel Web Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20724","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":"sha256:4fb411f35536d4416d730833e5842342228ec7706f72cd2472a681709bbd32b8","target":"record","created_at":"2026-06-23T00:11:54Z","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":"f42f044894a5468f055ee847349035f4011f6edabc8c179634d5a67ff7b1220c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T23:00:25Z","title_canon_sha256":"9f0e6112b81a92ce10c647589e230bb1fa0a02a4875b81690ee3c70e0fc051c5"},"schema_version":"1.0","source":{"id":"2606.20724","kind":"arxiv","version":1}},"canonical_sha256":"e42c01d2984f9a8e11c8bb39de8bda75423270f1155a1d84c618f67717262a2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e42c01d2984f9a8e11c8bb39de8bda75423270f1155a1d84c618f67717262a2d","first_computed_at":"2026-06-23T00:11:54.763708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T00:11:54.763708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JZESq2u4msqEmYXADmJGF8wD+/EEozmtio4qGlyNYRjKWeZ2/NB/6jUELa1bHE5MQicPRwAq3D8DPrh8ol1BAA==","signature_status":"signed_v1","signed_at":"2026-06-23T00:11:54.764153Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.20724","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fb411f35536d4416d730833e5842342228ec7706f72cd2472a681709bbd32b8","sha256:54b3f9480ea66832f28b3cf9f7a6ac7784635542f65846edec0c569f1c4922ce"],"state_sha256":"5c5d5ba0a5bce1d73795d6c8f5a5cf7f5ab8149267c6d770610748489196b92f"}