{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HHYYNNP46O3XBBMYKAR4FGC55J","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":"96376777c7fd495cdc9898f6f6dccd27e130354b926fb5a55c2a15f00b2e9d29","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T17:53:18Z","title_canon_sha256":"946cf2f37ea52fc865abf32982c6f3cda4aeb80d61117060a74c70759665e806"},"schema_version":"1.0","source":{"id":"2608.06352","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.06352","created_at":"2026-08-07T01:41:27Z"},{"alias_kind":"arxiv_version","alias_value":"2608.06352v1","created_at":"2026-08-07T01:41:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06352","created_at":"2026-08-07T01:41:27Z"},{"alias_kind":"pith_short_12","alias_value":"HHYYNNP46O3X","created_at":"2026-08-07T01:41:27Z"},{"alias_kind":"pith_short_16","alias_value":"HHYYNNP46O3XBBMY","created_at":"2026-08-07T01:41:27Z"},{"alias_kind":"pith_short_8","alias_value":"HHYYNNP4","created_at":"2026-08-07T01:41:27Z"}],"graph_snapshots":[{"event_id":"sha256:b4fcb5d132e72402f48739e0c8a089762c66b22c26f3166230d7a8247a6e2592","target":"graph","created_at":"2026-08-07T01:41:27Z","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/2608.06352/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning. Executable validation establishes feasibility, yet does not reveal how a task behaves relative to a given solver setting. In this paper, we present CalibForge, an autonomous terminal-task synthesis system that uses verified solver behavior to revise candidate tasks through adversarial solver calibration. Multi-solver calibration targets disagreement within a heterogeneous solver pool, whereas contrastive solver calibration targets a designated strong-pass/","authors_text":"Fanzhe Meng, Guoxin Chen, Jiale Zhao, Ji-Rong Wen, Kai Jia, Ruihua Song, Shuang Sun, Wayne Xin Zhao, Zhiyu Lin","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T17:53:18Z","title":"CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06352","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:da3567385c1019b8c651260c013ae1b995f3e89fc0a7a1ed14475848b75ea8b7","target":"record","created_at":"2026-08-07T01:41:27Z","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":"96376777c7fd495cdc9898f6f6dccd27e130354b926fb5a55c2a15f00b2e9d29","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T17:53:18Z","title_canon_sha256":"946cf2f37ea52fc865abf32982c6f3cda4aeb80d61117060a74c70759665e806"},"schema_version":"1.0","source":{"id":"2608.06352","kind":"arxiv","version":1}},"canonical_sha256":"39f186b5fcf3b77085985023c2985dea640deac03e9827f41615826a2c1f3407","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39f186b5fcf3b77085985023c2985dea640deac03e9827f41615826a2c1f3407","first_computed_at":"2026-08-07T01:41:27.838957Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T01:41:27.838957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qpfgX59FBtzHZb5L/kSpqmwAkazWKZBQ4LoCeC0V2D4XDkPX1PFE8s0auFm8O6h4i2cMmj8ACfkpccmf9oogAA==","signature_status":"signed_v1","signed_at":"2026-08-07T01:41:27.840550Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.06352","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da3567385c1019b8c651260c013ae1b995f3e89fc0a7a1ed14475848b75ea8b7","sha256:b4fcb5d132e72402f48739e0c8a089762c66b22c26f3166230d7a8247a6e2592"],"state_sha256":"e68466b1311cb274e351d8544861117018780aee42095a59b8b43e98d85c20df"}