{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KUWAZ7XPKWHSY4KFKSHLPSHDS4","short_pith_number":"pith:KUWAZ7XP","canonical_record":{"source":{"id":"2607.24054","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T06:51:29Z","cross_cats_sorted":[],"title_canon_sha256":"6263387e1d724a5e6ed036e881b0e2fe0dcfae4ae9f93a26032c0eb123d17d6f","abstract_canon_sha256":"47863609a7fc0fe128dbb30b4b21579e9ac9776fcbe38633abc5e85509710883"},"schema_version":"1.0"},"canonical_sha256":"552c0cfeef558f2c7145548eb7c8e397350ae62ff7a8f163b8cf3a4b10f3d5fc","source":{"kind":"arxiv","id":"2607.24054","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24054","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24054v1","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24054","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"pith_short_12","alias_value":"KUWAZ7XPKWHS","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"pith_short_16","alias_value":"KUWAZ7XPKWHSY4KF","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"pith_short_8","alias_value":"KUWAZ7XP","created_at":"2026-07-28T01:23:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KUWAZ7XPKWHSY4KFKSHLPSHDS4","target":"record","payload":{"canonical_record":{"source":{"id":"2607.24054","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T06:51:29Z","cross_cats_sorted":[],"title_canon_sha256":"6263387e1d724a5e6ed036e881b0e2fe0dcfae4ae9f93a26032c0eb123d17d6f","abstract_canon_sha256":"47863609a7fc0fe128dbb30b4b21579e9ac9776fcbe38633abc5e85509710883"},"schema_version":"1.0"},"canonical_sha256":"552c0cfeef558f2c7145548eb7c8e397350ae62ff7a8f163b8cf3a4b10f3d5fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:43.136119Z","signature_b64":"MfG1XbNzOQdvr6zqYMrMNfrjA5GtOq0TfoDEigEcu48OSXpCjP40Imr7wp6BugghR4w1jJmmgtDpJPBI5ym+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"552c0cfeef558f2c7145548eb7c8e397350ae62ff7a8f163b8cf3a4b10f3d5fc","last_reissued_at":"2026-07-28T01:23:43.135279Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:43.135279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.24054","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":"2026-07-28T01:23:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mumLkJIIUmVRo1UECSOqIImAiP35mwDWBeTYtl0V6ELYUWU6uEn7FE7+RzgcVukJDNfEzIqzqqoycHFkz4hFAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:09:31.024252Z"},"content_sha256":"262c68366742e205d880fdafb4d3a29419b59cd49af442aacd0f311e542d603d","schema_version":"1.0","event_id":"sha256:262c68366742e205d880fdafb4d3a29419b59cd49af442aacd0f311e542d603d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KUWAZ7XPKWHSY4KFKSHLPSHDS4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Success Is Not Self-Explanatory: Auditing Success Provenance in Agent Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Da-Tian Peng, Jingkun Luo","submitted_at":"2026-07-27T06:51:29Z","abstract_excerpt":"A correct answer can conceal why an agent succeeded. Once agents change their information state during evaluation, correctness no longer distinguishes intended reasoning from answer acquisition. Outcome evidence and exposure detection do not establish whether success depended on an acquired target; we call this missing evaluation object success provenance. AcquaBench audits it through matched CLEAN, GOLD, and SHAM value substitution on four standardized surfaces with joint qid-clustered analysis. CLEAN retains benchmark-authorized information. GOLD makes the correct target available. SHAM pres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24054","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/2607.24054/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":"2026-07-28T01:23:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pttSO2utGWeiRysANy6JF6LED5HM3woGegffI1gucthI65qrXOxFMJiKtONiulKTNg7221SNMjwinwibUZ6RBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:09:31.025174Z"},"content_sha256":"666f7aa69cebc5f7c48f68212a64ff4105b54809e2d7c6adb2748b19ec0c4cc0","schema_version":"1.0","event_id":"sha256:666f7aa69cebc5f7c48f68212a64ff4105b54809e2d7c6adb2748b19ec0c4cc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KUWAZ7XPKWHSY4KFKSHLPSHDS4/bundle.json","state_url":"https://pith.science/pith/KUWAZ7XPKWHSY4KFKSHLPSHDS4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KUWAZ7XPKWHSY4KFKSHLPSHDS4/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":"2026-08-11T17:09:31Z","links":{"resolver":"https://pith.science/pith/KUWAZ7XPKWHSY4KFKSHLPSHDS4","bundle":"https://pith.science/pith/KUWAZ7XPKWHSY4KFKSHLPSHDS4/bundle.json","state":"https://pith.science/pith/KUWAZ7XPKWHSY4KFKSHLPSHDS4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KUWAZ7XPKWHSY4KFKSHLPSHDS4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KUWAZ7XPKWHSY4KFKSHLPSHDS4","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":"47863609a7fc0fe128dbb30b4b21579e9ac9776fcbe38633abc5e85509710883","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T06:51:29Z","title_canon_sha256":"6263387e1d724a5e6ed036e881b0e2fe0dcfae4ae9f93a26032c0eb123d17d6f"},"schema_version":"1.0","source":{"id":"2607.24054","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24054","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24054v1","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24054","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"pith_short_12","alias_value":"KUWAZ7XPKWHS","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"pith_short_16","alias_value":"KUWAZ7XPKWHSY4KF","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"pith_short_8","alias_value":"KUWAZ7XP","created_at":"2026-07-28T01:23:43Z"}],"graph_snapshots":[{"event_id":"sha256:666f7aa69cebc5f7c48f68212a64ff4105b54809e2d7c6adb2748b19ec0c4cc0","target":"graph","created_at":"2026-07-28T01:23:43Z","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/2607.24054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A correct answer can conceal why an agent succeeded. Once agents change their information state during evaluation, correctness no longer distinguishes intended reasoning from answer acquisition. Outcome evidence and exposure detection do not establish whether success depended on an acquired target; we call this missing evaluation object success provenance. AcquaBench audits it through matched CLEAN, GOLD, and SHAM value substitution on four standardized surfaces with joint qid-clustered analysis. CLEAN retains benchmark-authorized information. GOLD makes the correct target available. SHAM pres","authors_text":"Da-Tian Peng, Jingkun Luo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T06:51:29Z","title":"Success Is Not Self-Explanatory: Auditing Success Provenance in Agent Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24054","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":"sha256:262c68366742e205d880fdafb4d3a29419b59cd49af442aacd0f311e542d603d","target":"record","created_at":"2026-07-28T01:23:43Z","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":"47863609a7fc0fe128dbb30b4b21579e9ac9776fcbe38633abc5e85509710883","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T06:51:29Z","title_canon_sha256":"6263387e1d724a5e6ed036e881b0e2fe0dcfae4ae9f93a26032c0eb123d17d6f"},"schema_version":"1.0","source":{"id":"2607.24054","kind":"arxiv","version":1}},"canonical_sha256":"552c0cfeef558f2c7145548eb7c8e397350ae62ff7a8f163b8cf3a4b10f3d5fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"552c0cfeef558f2c7145548eb7c8e397350ae62ff7a8f163b8cf3a4b10f3d5fc","first_computed_at":"2026-07-28T01:23:43.135279Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:43.135279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MfG1XbNzOQdvr6zqYMrMNfrjA5GtOq0TfoDEigEcu48OSXpCjP40Imr7wp6BugghR4w1jJmmgtDpJPBI5ym+BA==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:43.136119Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24054","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:262c68366742e205d880fdafb4d3a29419b59cd49af442aacd0f311e542d603d","sha256:666f7aa69cebc5f7c48f68212a64ff4105b54809e2d7c6adb2748b19ec0c4cc0"],"state_sha256":"ddf5181440c8c0e311decca3e2bdc57e9468b0fd855e61b06049bab3c5120823"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jwuQdnEjlqbruhx+JW5Gv8DQLDxil3l4Zu4yLnNAk0kAF09olpgfVRUVlrYP0twBG5NcJVyBvjsO+i0/7aI4Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T17:09:31.033006Z","bundle_sha256":"cb350bb97486774551a4dfefa438bab4e25e8eccd964347d4ab5173bca0eb1d3"}}