{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XJEZ6PAK2B4LNUY74AQ76VWE4D","short_pith_number":"pith:XJEZ6PAK","canonical_record":{"source":{"id":"2607.25152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T23:52:15Z","cross_cats_sorted":[],"title_canon_sha256":"82f3b7cc62e7695b343173e0edf1bcc75328ee62e653c5b3970137e9380bd97b","abstract_canon_sha256":"ba7af8db24b9d2799c146ba3f25224c5922cc71047f6795555f17726ab7b8826"},"schema_version":"1.0"},"canonical_sha256":"ba499f3c0ad078b6d31fe021ff56c4e0d07584aded5253a59c26d0ea04691051","source":{"kind":"arxiv","id":"2607.25152","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.25152","created_at":"2026-07-29T00:25:05Z"},{"alias_kind":"arxiv_version","alias_value":"2607.25152v1","created_at":"2026-07-29T00:25:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25152","created_at":"2026-07-29T00:25:05Z"},{"alias_kind":"pith_short_12","alias_value":"XJEZ6PAK2B4L","created_at":"2026-07-29T00:25:05Z"},{"alias_kind":"pith_short_16","alias_value":"XJEZ6PAK2B4LNUY7","created_at":"2026-07-29T00:25:05Z"},{"alias_kind":"pith_short_8","alias_value":"XJEZ6PAK","created_at":"2026-07-29T00:25:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XJEZ6PAK2B4LNUY74AQ76VWE4D","target":"record","payload":{"canonical_record":{"source":{"id":"2607.25152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T23:52:15Z","cross_cats_sorted":[],"title_canon_sha256":"82f3b7cc62e7695b343173e0edf1bcc75328ee62e653c5b3970137e9380bd97b","abstract_canon_sha256":"ba7af8db24b9d2799c146ba3f25224c5922cc71047f6795555f17726ab7b8826"},"schema_version":"1.0"},"canonical_sha256":"ba499f3c0ad078b6d31fe021ff56c4e0d07584aded5253a59c26d0ea04691051","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:25:05.586152Z","signature_b64":"wKeZac2Bibqp64IQcVe61CUGcvFVN9W2xiQfU3goMO0XJL1jVTg+UBCROCVnZWJMMFtrhug5NjAzkiYuPjLRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba499f3c0ad078b6d31fe021ff56c4e0d07584aded5253a59c26d0ea04691051","last_reissued_at":"2026-07-29T00:25:05.585277Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:25:05.585277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.25152","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":"2026-07-29T00:25:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MeYglU28LQZvpBW94Mmta6P1iQJOy020UZrUCP/SOa4NuvBiixsUOWZ+DN21eiYTdCT8PnoBM9Ore2C21AnSBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:34:47.014107Z"},"content_sha256":"1fcbb37bf12998ba8b5e2c689551329bc934a6a788950ce91175a1321c86086a","schema_version":"1.0","event_id":"sha256:1fcbb37bf12998ba8b5e2c689551329bc934a6a788950ce91175a1321c86086a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XJEZ6PAK2B4LNUY74AQ76VWE4D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Byungho Choi, Hyundoo Park","submitted_at":"2026-07-27T23:52:15Z","abstract_excerpt":"Long-running autonomous agents plan, act, and judge their own completion without human intervention. When an agent grades its own work, self-evaluation bias takes hold: plausible changes are accepted as progress while real-world outcomes stagnate or regress. We name this failure mode the progress mirage and show, with controlled measurement, that it is a question of what the evaluator is grounded in. We built a testbed that holds the agent and its tool surface fixed and manipulates only the information-channel type of the evaluator that gates the loop. A world-state oracle, unfakeable in princ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25152","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/2607.25152/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":"2026-07-29T00:25:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K575jAjqHkKzgBzCGSUQY6qu3DcDJMNPQqaZRP+DpUQ3dMXw6LeZFy8X7ayjGpe5oV8x0O/mhT6mHe5mK3ZDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:34:47.014695Z"},"content_sha256":"9cdf282482c3f67aaa1e6ff1467c57a36537989072b883a58a36547006e4fbd6","schema_version":"1.0","event_id":"sha256:9cdf282482c3f67aaa1e6ff1467c57a36537989072b883a58a36547006e4fbd6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XJEZ6PAK2B4LNUY74AQ76VWE4D/bundle.json","state_url":"https://pith.science/pith/XJEZ6PAK2B4LNUY74AQ76VWE4D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XJEZ6PAK2B4LNUY74AQ76VWE4D/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":"2026-08-19T08:34:47Z","links":{"resolver":"https://pith.science/pith/XJEZ6PAK2B4LNUY74AQ76VWE4D","bundle":"https://pith.science/pith/XJEZ6PAK2B4LNUY74AQ76VWE4D/bundle.json","state":"https://pith.science/pith/XJEZ6PAK2B4LNUY74AQ76VWE4D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XJEZ6PAK2B4LNUY74AQ76VWE4D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XJEZ6PAK2B4LNUY74AQ76VWE4D","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":"ba7af8db24b9d2799c146ba3f25224c5922cc71047f6795555f17726ab7b8826","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T23:52:15Z","title_canon_sha256":"82f3b7cc62e7695b343173e0edf1bcc75328ee62e653c5b3970137e9380bd97b"},"schema_version":"1.0","source":{"id":"2607.25152","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.25152","created_at":"2026-07-29T00:25:05Z"},{"alias_kind":"arxiv_version","alias_value":"2607.25152v1","created_at":"2026-07-29T00:25:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25152","created_at":"2026-07-29T00:25:05Z"},{"alias_kind":"pith_short_12","alias_value":"XJEZ6PAK2B4L","created_at":"2026-07-29T00:25:05Z"},{"alias_kind":"pith_short_16","alias_value":"XJEZ6PAK2B4LNUY7","created_at":"2026-07-29T00:25:05Z"},{"alias_kind":"pith_short_8","alias_value":"XJEZ6PAK","created_at":"2026-07-29T00:25:05Z"}],"graph_snapshots":[{"event_id":"sha256:9cdf282482c3f67aaa1e6ff1467c57a36537989072b883a58a36547006e4fbd6","target":"graph","created_at":"2026-07-29T00:25:05Z","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/2607.25152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-running autonomous agents plan, act, and judge their own completion without human intervention. When an agent grades its own work, self-evaluation bias takes hold: plausible changes are accepted as progress while real-world outcomes stagnate or regress. We name this failure mode the progress mirage and show, with controlled measurement, that it is a question of what the evaluator is grounded in. We built a testbed that holds the agent and its tool surface fixed and manipulates only the information-channel type of the evaluator that gates the loop. A world-state oracle, unfakeable in princ","authors_text":"Byungho Choi, Hyundoo Park","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T23:52:15Z","title":"When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25152","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":"sha256:1fcbb37bf12998ba8b5e2c689551329bc934a6a788950ce91175a1321c86086a","target":"record","created_at":"2026-07-29T00:25:05Z","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":"ba7af8db24b9d2799c146ba3f25224c5922cc71047f6795555f17726ab7b8826","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T23:52:15Z","title_canon_sha256":"82f3b7cc62e7695b343173e0edf1bcc75328ee62e653c5b3970137e9380bd97b"},"schema_version":"1.0","source":{"id":"2607.25152","kind":"arxiv","version":1}},"canonical_sha256":"ba499f3c0ad078b6d31fe021ff56c4e0d07584aded5253a59c26d0ea04691051","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba499f3c0ad078b6d31fe021ff56c4e0d07584aded5253a59c26d0ea04691051","first_computed_at":"2026-07-29T00:25:05.585277Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T00:25:05.585277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wKeZac2Bibqp64IQcVe61CUGcvFVN9W2xiQfU3goMO0XJL1jVTg+UBCROCVnZWJMMFtrhug5NjAzkiYuPjLRDA==","signature_status":"signed_v1","signed_at":"2026-07-29T00:25:05.586152Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.25152","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fcbb37bf12998ba8b5e2c689551329bc934a6a788950ce91175a1321c86086a","sha256:9cdf282482c3f67aaa1e6ff1467c57a36537989072b883a58a36547006e4fbd6"],"state_sha256":"7b1d971d2b80b22fecc1ac115014e9e24abe1a360724be18b980b1f619f1fa5b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L+WE3yXrjRu5Wys6IUy0y4kChpmPviBX7kKt/i7BupSVwAbAnvOOac7oNRyWKM8NSLQJ94FXF5bDKB2ce+82AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T08:34:47.020271Z","bundle_sha256":"84069c41c07963655041cb30b34cec1b11dfce2856932f430178863fa9d1c2fa"}}