{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KQU55627G4I6DHVPXBHBGZN373","short_pith_number":"pith:KQU55627","canonical_record":{"source":{"id":"2508.03396","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-05T12:45:21Z","cross_cats_sorted":[],"title_canon_sha256":"b220ee67c509f42cffd030977b486daee53672a73ba59a9cf8046db8b1ddef34","abstract_canon_sha256":"9d17713b0963a54f809789a184fb93ef633d2eabe02c20c2e2c2d1a4818edd87"},"schema_version":"1.0"},"canonical_sha256":"5429defb5f3711e19eafb84e1365bbfeedea9b8516371d2519656772b211ab06","source":{"kind":"arxiv","id":"2508.03396","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.03396","created_at":"2026-07-05T11:48:55Z"},{"alias_kind":"arxiv_version","alias_value":"2508.03396v1","created_at":"2026-07-05T11:48:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03396","created_at":"2026-07-05T11:48:55Z"},{"alias_kind":"pith_short_12","alias_value":"KQU55627G4I6","created_at":"2026-07-05T11:48:55Z"},{"alias_kind":"pith_short_16","alias_value":"KQU55627G4I6DHVP","created_at":"2026-07-05T11:48:55Z"},{"alias_kind":"pith_short_8","alias_value":"KQU55627","created_at":"2026-07-05T11:48:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KQU55627G4I6DHVPXBHBGZN373","target":"record","payload":{"canonical_record":{"source":{"id":"2508.03396","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-05T12:45:21Z","cross_cats_sorted":[],"title_canon_sha256":"b220ee67c509f42cffd030977b486daee53672a73ba59a9cf8046db8b1ddef34","abstract_canon_sha256":"9d17713b0963a54f809789a184fb93ef633d2eabe02c20c2e2c2d1a4818edd87"},"schema_version":"1.0"},"canonical_sha256":"5429defb5f3711e19eafb84e1365bbfeedea9b8516371d2519656772b211ab06","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:55.744450Z","signature_b64":"VjTlom2ZquHptmD0CVdG94psw8BoYAMbKb84ky88Dkg8RmkST/1wgJwPY7AX2U2isS0Uzco8DgdWlxit2CCWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5429defb5f3711e19eafb84e1365bbfeedea9b8516371d2519656772b211ab06","last_reissued_at":"2026-07-05T11:48:55.743982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:55.743982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.03396","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":"2026-07-05T11:48:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mg7dWVZI/ST1LZowSVoqpxpXPRj8yL5F0lBC1UympcIRc6/NzkV1WVv+V+cvHE9TBokwS1I2Brg6PwUKQCRQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:38:35.542279Z"},"content_sha256":"8948d4c660768b61573fdfe9956eaa75820793c3efc61a8e44086aeba768117c","schema_version":"1.0","event_id":"sha256:8948d4c660768b61573fdfe9956eaa75820793c3efc61a8e44086aeba768117c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KQU55627G4I6DHVPXBHBGZN373","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hide and Seek with LLMs: An Adversarial Game for Sneaky Error Generation and Self-Improving Diagnosis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jing Chen, Jirong Wen, Mengqi Wei, Rui Zou, Xin Zhao, Yutao Zhu","submitted_at":"2025-08-05T12:45:21Z","abstract_excerpt":"Large Language Models (LLMs) excel in reasoning and generation across domains, but still struggle with identifying and diagnosing complex errors. This stems mainly from training objectives that prioritize correct answers, limiting exposure to and learning from errors. While recent studies have begun to address this by introducing error signals, most rely on shallow, static errors, restricting improvement in deep diagnostic ability. To overcome this, we propose Hide and Seek Game (HSG), a dynamic adversarial framework for error generation and diagnosis, and evaluate it on mathematical problem-s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03396","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/2508.03396/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":"2026-07-05T11:48:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MZsNNVA1/c3Jtvb2Sl5E20mmFgfVl8HLFyMqeZcPx6cvHQFbBze2gwkgj/P6aMJUKIjAeYKs+XuizDQ31wFgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:38:35.542792Z"},"content_sha256":"98f386c99e25b34dcbfd70c280a37f8e2cb5f9e0905184c9fe010779ad15f57d","schema_version":"1.0","event_id":"sha256:98f386c99e25b34dcbfd70c280a37f8e2cb5f9e0905184c9fe010779ad15f57d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KQU55627G4I6DHVPXBHBGZN373/bundle.json","state_url":"https://pith.science/pith/KQU55627G4I6DHVPXBHBGZN373/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KQU55627G4I6DHVPXBHBGZN373/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":"2026-08-14T14:38:35Z","links":{"resolver":"https://pith.science/pith/KQU55627G4I6DHVPXBHBGZN373","bundle":"https://pith.science/pith/KQU55627G4I6DHVPXBHBGZN373/bundle.json","state":"https://pith.science/pith/KQU55627G4I6DHVPXBHBGZN373/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KQU55627G4I6DHVPXBHBGZN373/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KQU55627G4I6DHVPXBHBGZN373","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":"9d17713b0963a54f809789a184fb93ef633d2eabe02c20c2e2c2d1a4818edd87","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-05T12:45:21Z","title_canon_sha256":"b220ee67c509f42cffd030977b486daee53672a73ba59a9cf8046db8b1ddef34"},"schema_version":"1.0","source":{"id":"2508.03396","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.03396","created_at":"2026-07-05T11:48:55Z"},{"alias_kind":"arxiv_version","alias_value":"2508.03396v1","created_at":"2026-07-05T11:48:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03396","created_at":"2026-07-05T11:48:55Z"},{"alias_kind":"pith_short_12","alias_value":"KQU55627G4I6","created_at":"2026-07-05T11:48:55Z"},{"alias_kind":"pith_short_16","alias_value":"KQU55627G4I6DHVP","created_at":"2026-07-05T11:48:55Z"},{"alias_kind":"pith_short_8","alias_value":"KQU55627","created_at":"2026-07-05T11:48:55Z"}],"graph_snapshots":[{"event_id":"sha256:98f386c99e25b34dcbfd70c280a37f8e2cb5f9e0905184c9fe010779ad15f57d","target":"graph","created_at":"2026-07-05T11:48:55Z","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/2508.03396/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) excel in reasoning and generation across domains, but still struggle with identifying and diagnosing complex errors. This stems mainly from training objectives that prioritize correct answers, limiting exposure to and learning from errors. While recent studies have begun to address this by introducing error signals, most rely on shallow, static errors, restricting improvement in deep diagnostic ability. To overcome this, we propose Hide and Seek Game (HSG), a dynamic adversarial framework for error generation and diagnosis, and evaluate it on mathematical problem-s","authors_text":"Jing Chen, Jirong Wen, Mengqi Wei, Rui Zou, Xin Zhao, Yutao Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-05T12:45:21Z","title":"Hide and Seek with LLMs: An Adversarial Game for Sneaky Error Generation and Self-Improving Diagnosis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03396","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":"sha256:8948d4c660768b61573fdfe9956eaa75820793c3efc61a8e44086aeba768117c","target":"record","created_at":"2026-07-05T11:48:55Z","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":"9d17713b0963a54f809789a184fb93ef633d2eabe02c20c2e2c2d1a4818edd87","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-05T12:45:21Z","title_canon_sha256":"b220ee67c509f42cffd030977b486daee53672a73ba59a9cf8046db8b1ddef34"},"schema_version":"1.0","source":{"id":"2508.03396","kind":"arxiv","version":1}},"canonical_sha256":"5429defb5f3711e19eafb84e1365bbfeedea9b8516371d2519656772b211ab06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5429defb5f3711e19eafb84e1365bbfeedea9b8516371d2519656772b211ab06","first_computed_at":"2026-07-05T11:48:55.743982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:55.743982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VjTlom2ZquHptmD0CVdG94psw8BoYAMbKb84ky88Dkg8RmkST/1wgJwPY7AX2U2isS0Uzco8DgdWlxit2CCWBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:55.744450Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.03396","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8948d4c660768b61573fdfe9956eaa75820793c3efc61a8e44086aeba768117c","sha256:98f386c99e25b34dcbfd70c280a37f8e2cb5f9e0905184c9fe010779ad15f57d"],"state_sha256":"14d9982393de510a8509a9651ff3ad4ee3270971f91aa4b4ed6c8aac2726c2b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CNLZ2R9+kZ3cLKBniQaLEu404h2QLW7tyVrtALsWQGq8lwrMYPo8BsxHglibZ2S/v88cWKwiFXhaAKdJzyUNDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T14:38:35.548468Z","bundle_sha256":"51a984b6857d7e27ff486381801cf85f6c16755cccdfdbf33e990e29e0cb373f"}}