{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:G7K23BUA4CTJTTX5N3UHNJC4LZ","short_pith_number":"pith:G7K23BUA","canonical_record":{"source":{"id":"2605.18583","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-18T16:00:41Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CR"],"title_canon_sha256":"d16c6844d02a61e8b4b048b8f98aa1c6b8c53a3a47f352b829888185d3065a9e","abstract_canon_sha256":"14537eb2ee94313e079e21ae4df82586ecd7b2f7d8e09c7d6bba109adc3f736d"},"schema_version":"1.0"},"canonical_sha256":"37d5ad8680e0a699cefd6ee876a45c5e7c5668559ce447c4eb2f1beee9f98cf6","source":{"kind":"arxiv","id":"2605.18583","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18583","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18583v1","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18583","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"G7K23BUA4CTJ","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"G7K23BUA4CTJTTX5","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"G7K23BUA","created_at":"2026-05-20T00:06:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:G7K23BUA4CTJTTX5N3UHNJC4LZ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18583","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-18T16:00:41Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CR"],"title_canon_sha256":"d16c6844d02a61e8b4b048b8f98aa1c6b8c53a3a47f352b829888185d3065a9e","abstract_canon_sha256":"14537eb2ee94313e079e21ae4df82586ecd7b2f7d8e09c7d6bba109adc3f736d"},"schema_version":"1.0"},"canonical_sha256":"37d5ad8680e0a699cefd6ee876a45c5e7c5668559ce447c4eb2f1beee9f98cf6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:09.079196Z","signature_b64":"6p/m+mjIyIuih4bW5L4+jnAk3Aw0eFrUg7V5G4D9JgNY6eSkiQGJ0dfW85quv6o2rbnFGXYz7w5VJT2gxaGHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37d5ad8680e0a699cefd6ee876a45c5e7c5668559ce447c4eb2f1beee9f98cf6","last_reissued_at":"2026-05-20T00:06:09.078451Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:09.078451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18583","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":"2026-05-20T00:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ufpAos05dxqSAvnOo4wuIqYIeBrJqOHEP3Rnawt8HVez+9/jDa86AKya5HbBTGThjhXtCVU87W0clxLcnZBYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T22:27:26.374177Z"},"content_sha256":"cd774131a82a082d3e75a26f856141d43815a07e8438d476515e9e97ab1ee42e","schema_version":"1.0","event_id":"sha256:cd774131a82a082d3e75a26f856141d43815a07e8438d476515e9e97ab1ee42e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:G7K23BUA4CTJTTX5N3UHNJC4LZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CR"],"primary_cat":"cs.SE","authors_text":"Gelei Deng, Leo Yu Zhang, Yanjun Zhang, Yi Liu, Ying Zhang, Yubin Qu, Yuekang Li","submitted_at":"2026-05-18T16:00:41Z","abstract_excerpt":"Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated files, wipes a stale credentials backup, or rewrites configuration the user never mentioned. We call these scope expansions overeager actions, an authorization problem distinct from capability failures, prompt injection, or sandbox escapes.\n  We present OverEager-Gen, a benchmark dedicated to overeager behavior on benign tasks. Building it surfaces a measurement-validity issue: if a benchmark spells out the authorized s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18583","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/2605.18583/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.304162Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"f830a06d7edec6ba00cc3ee776edfadce8c2d8ed225138d727df4623927a3758"},"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":"2026-05-20T00:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1hoXgV79guxHgWXKHJ1QEbfwYxHAOX+Wwzq+LYtNh2oRXPHIqVjjTgFjduFpPRrcvqt/iw6kpVNXi4LshznXBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T22:27:26.374602Z"},"content_sha256":"de9231eeec43978d68d48358909387fb9402755274e3c7cfba22dcc2163c09e0","schema_version":"1.0","event_id":"sha256:de9231eeec43978d68d48358909387fb9402755274e3c7cfba22dcc2163c09e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G7K23BUA4CTJTTX5N3UHNJC4LZ/bundle.json","state_url":"https://pith.science/pith/G7K23BUA4CTJTTX5N3UHNJC4LZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G7K23BUA4CTJTTX5N3UHNJC4LZ/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":"2026-05-21T22:27:26Z","links":{"resolver":"https://pith.science/pith/G7K23BUA4CTJTTX5N3UHNJC4LZ","bundle":"https://pith.science/pith/G7K23BUA4CTJTTX5N3UHNJC4LZ/bundle.json","state":"https://pith.science/pith/G7K23BUA4CTJTTX5N3UHNJC4LZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G7K23BUA4CTJTTX5N3UHNJC4LZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G7K23BUA4CTJTTX5N3UHNJC4LZ","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":"14537eb2ee94313e079e21ae4df82586ecd7b2f7d8e09c7d6bba109adc3f736d","cross_cats_sorted":["cs.AI","cs.CL","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-18T16:00:41Z","title_canon_sha256":"d16c6844d02a61e8b4b048b8f98aa1c6b8c53a3a47f352b829888185d3065a9e"},"schema_version":"1.0","source":{"id":"2605.18583","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18583","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18583v1","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18583","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"G7K23BUA4CTJ","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"G7K23BUA4CTJTTX5","created_at":"2026-05-20T00:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"G7K23BUA","created_at":"2026-05-20T00:06:09Z"}],"graph_snapshots":[{"event_id":"sha256:de9231eeec43978d68d48358909387fb9402755274e3c7cfba22dcc2163c09e0","target":"graph","created_at":"2026-05-20T00:06:09Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.304162Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18583/integrity.json","findings":[],"snapshot_sha256":"f830a06d7edec6ba00cc3ee776edfadce8c2d8ed225138d727df4623927a3758","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated files, wipes a stale credentials backup, or rewrites configuration the user never mentioned. We call these scope expansions overeager actions, an authorization problem distinct from capability failures, prompt injection, or sandbox escapes.\n  We present OverEager-Gen, a benchmark dedicated to overeager behavior on benign tasks. Building it surfaces a measurement-validity issue: if a benchmark spells out the authorized s","authors_text":"Gelei Deng, Leo Yu Zhang, Yanjun Zhang, Yi Liu, Ying Zhang, Yubin Qu, Yuekang Li","cross_cats":["cs.AI","cs.CL","cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-18T16:00:41Z","title":"Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18583","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:cd774131a82a082d3e75a26f856141d43815a07e8438d476515e9e97ab1ee42e","target":"record","created_at":"2026-05-20T00:06:09Z","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":"14537eb2ee94313e079e21ae4df82586ecd7b2f7d8e09c7d6bba109adc3f736d","cross_cats_sorted":["cs.AI","cs.CL","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-18T16:00:41Z","title_canon_sha256":"d16c6844d02a61e8b4b048b8f98aa1c6b8c53a3a47f352b829888185d3065a9e"},"schema_version":"1.0","source":{"id":"2605.18583","kind":"arxiv","version":1}},"canonical_sha256":"37d5ad8680e0a699cefd6ee876a45c5e7c5668559ce447c4eb2f1beee9f98cf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37d5ad8680e0a699cefd6ee876a45c5e7c5668559ce447c4eb2f1beee9f98cf6","first_computed_at":"2026-05-20T00:06:09.078451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:09.078451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6p/m+mjIyIuih4bW5L4+jnAk3Aw0eFrUg7V5G4D9JgNY6eSkiQGJ0dfW85quv6o2rbnFGXYz7w5VJT2gxaGHBg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:09.079196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18583","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd774131a82a082d3e75a26f856141d43815a07e8438d476515e9e97ab1ee42e","sha256:de9231eeec43978d68d48358909387fb9402755274e3c7cfba22dcc2163c09e0"],"state_sha256":"989d8a5db4d4f06aef643b614230a47c22fee3a6f92496380aa770ba3f1890e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ExTxReJviUpmBLDx0QBsPnXtBOH6PiUJXQVSohmQw6A6DhgQK9JMV7wOO2aW0lwook3kdiOqw3fcss5yyZAaAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T22:27:26.377358Z","bundle_sha256":"9b31753027e3534a68e6a3cce693fc59d6a53b07599f2792470d42a0a733ba3e"}}