{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:462PYM6MLD6BGXPKZRJOQKO3H5","short_pith_number":"pith:462PYM6M","canonical_record":{"source":{"id":"2605.21384","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-05-20T16:41:51Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f51e68cfc0d6aa5149652d348ca89ceff2678b4a8aeffb570c2b410a6af95e2c","abstract_canon_sha256":"bc8d77e41b653f4f21e6e11b79ac5d0d45d4151e6b8479d21ce5fbdd7520067a"},"schema_version":"1.0"},"canonical_sha256":"e7b4fc33cc58fc135deacc52e829db3f6be5c367cb1a889ca4af23f305f99993","source":{"kind":"arxiv","id":"2605.21384","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21384","created_at":"2026-05-21T02:05:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21384v1","created_at":"2026-05-21T02:05:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21384","created_at":"2026-05-21T02:05:32Z"},{"alias_kind":"pith_short_12","alias_value":"462PYM6MLD6B","created_at":"2026-05-21T02:05:32Z"},{"alias_kind":"pith_short_16","alias_value":"462PYM6MLD6BGXPK","created_at":"2026-05-21T02:05:32Z"},{"alias_kind":"pith_short_8","alias_value":"462PYM6M","created_at":"2026-05-21T02:05:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:462PYM6MLD6BGXPKZRJOQKO3H5","target":"record","payload":{"canonical_record":{"source":{"id":"2605.21384","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-05-20T16:41:51Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f51e68cfc0d6aa5149652d348ca89ceff2678b4a8aeffb570c2b410a6af95e2c","abstract_canon_sha256":"bc8d77e41b653f4f21e6e11b79ac5d0d45d4151e6b8479d21ce5fbdd7520067a"},"schema_version":"1.0"},"canonical_sha256":"e7b4fc33cc58fc135deacc52e829db3f6be5c367cb1a889ca4af23f305f99993","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:32.115391Z","signature_b64":"NO2MVu8dZVufAL3+solIMsSy5d7DbJ7XCpZtQyb5ojYsLN84pNB18BritUicXU4XQDoGV38Obz08caXdYmFsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7b4fc33cc58fc135deacc52e829db3f6be5c367cb1a889ca4af23f305f99993","last_reissued_at":"2026-05-21T02:05:32.114637Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:32.114637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.21384","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":"2026-05-21T02:05:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"chcpKEDO98yo6UAGVmqOmrF3Gz5xYYie3+Srugk6Ho4q72fkIcn0R+Xq9Pzv8opg358AcWJlxDhTmeXm3oZ2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T12:36:08.558607Z"},"content_sha256":"15b569a72b4e5ac35abbe2556ce776a7b3394f52651d43d6a09798c8af7a18f5","schema_version":"1.0","event_id":"sha256:15b569a72b4e5ac35abbe2556ce776a7b3394f52651d43d6a09798c8af7a18f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:462PYM6MLD6BGXPKZRJOQKO3H5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Bingchen Zhao, Dhruv Srikanth, Yuxiang WU, Zhengyao Jiang","submitted_at":"2026-05-20T16:41:51Z","abstract_excerpt":"As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test suite. Reward hacking naturally arises in this setup, as the agent optimizes for passing tests while deviating from the users true goal. We study this reward hacking phenomenon by decompose software engineering tasks into three parts: (i) a natural language description of the specification (ii) visible validation tests that exercise specified features in isolation, and (iii) held-out tests that compose those same features to simulate real-world usage. Bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21384","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/2605.21384/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":"2026-05-21T02:05:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SPd5QInDJATlkJ4B4KoScKq4OGaJZFb+mNjmHAsq4NplaHgJxoXbkdELD1OVbUhtojKwDCkJjT0r7zP2eo5XDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T12:36:08.558993Z"},"content_sha256":"0fe35d690b69b7283fd83090b9fb684a39a8c2ce6be60d2062d783cb201663ff","schema_version":"1.0","event_id":"sha256:0fe35d690b69b7283fd83090b9fb684a39a8c2ce6be60d2062d783cb201663ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/462PYM6MLD6BGXPKZRJOQKO3H5/bundle.json","state_url":"https://pith.science/pith/462PYM6MLD6BGXPKZRJOQKO3H5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/462PYM6MLD6BGXPKZRJOQKO3H5/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":"2026-06-02T12:36:08Z","links":{"resolver":"https://pith.science/pith/462PYM6MLD6BGXPKZRJOQKO3H5","bundle":"https://pith.science/pith/462PYM6MLD6BGXPKZRJOQKO3H5/bundle.json","state":"https://pith.science/pith/462PYM6MLD6BGXPKZRJOQKO3H5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/462PYM6MLD6BGXPKZRJOQKO3H5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:462PYM6MLD6BGXPKZRJOQKO3H5","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":"bc8d77e41b653f4f21e6e11b79ac5d0d45d4151e6b8479d21ce5fbdd7520067a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-05-20T16:41:51Z","title_canon_sha256":"f51e68cfc0d6aa5149652d348ca89ceff2678b4a8aeffb570c2b410a6af95e2c"},"schema_version":"1.0","source":{"id":"2605.21384","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21384","created_at":"2026-05-21T02:05:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21384v1","created_at":"2026-05-21T02:05:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21384","created_at":"2026-05-21T02:05:32Z"},{"alias_kind":"pith_short_12","alias_value":"462PYM6MLD6B","created_at":"2026-05-21T02:05:32Z"},{"alias_kind":"pith_short_16","alias_value":"462PYM6MLD6BGXPK","created_at":"2026-05-21T02:05:32Z"},{"alias_kind":"pith_short_8","alias_value":"462PYM6M","created_at":"2026-05-21T02:05:32Z"}],"graph_snapshots":[{"event_id":"sha256:0fe35d690b69b7283fd83090b9fb684a39a8c2ce6be60d2062d783cb201663ff","target":"graph","created_at":"2026-05-21T02:05:32Z","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/2605.21384/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test suite. Reward hacking naturally arises in this setup, as the agent optimizes for passing tests while deviating from the users true goal. We study this reward hacking phenomenon by decompose software engineering tasks into three parts: (i) a natural language description of the specification (ii) visible validation tests that exercise specified features in isolation, and (iii) held-out tests that compose those same features to simulate real-world usage. Bas","authors_text":"Bingchen Zhao, Dhruv Srikanth, Yuxiang WU, Zhengyao Jiang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-05-20T16:41:51Z","title":"SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21384","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":"sha256:15b569a72b4e5ac35abbe2556ce776a7b3394f52651d43d6a09798c8af7a18f5","target":"record","created_at":"2026-05-21T02:05:32Z","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":"bc8d77e41b653f4f21e6e11b79ac5d0d45d4151e6b8479d21ce5fbdd7520067a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-05-20T16:41:51Z","title_canon_sha256":"f51e68cfc0d6aa5149652d348ca89ceff2678b4a8aeffb570c2b410a6af95e2c"},"schema_version":"1.0","source":{"id":"2605.21384","kind":"arxiv","version":1}},"canonical_sha256":"e7b4fc33cc58fc135deacc52e829db3f6be5c367cb1a889ca4af23f305f99993","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7b4fc33cc58fc135deacc52e829db3f6be5c367cb1a889ca4af23f305f99993","first_computed_at":"2026-05-21T02:05:32.114637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T02:05:32.114637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NO2MVu8dZVufAL3+solIMsSy5d7DbJ7XCpZtQyb5ojYsLN84pNB18BritUicXU4XQDoGV38Obz08caXdYmFsCw==","signature_status":"signed_v1","signed_at":"2026-05-21T02:05:32.115391Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21384","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15b569a72b4e5ac35abbe2556ce776a7b3394f52651d43d6a09798c8af7a18f5","sha256:0fe35d690b69b7283fd83090b9fb684a39a8c2ce6be60d2062d783cb201663ff"],"state_sha256":"3c78ea0e4d1734dbea6ba813444163210907d2ecebe13e3f2173fc1a5a9f35ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K0oF2E4ffU8xhJcPZQDUsY8YCl6S6C26LtKQfJjapD2RrONZzQrVe8NbD3i70/FH6sNnIcyAb4sy6vcosy6kBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T12:36:08.561422Z","bundle_sha256":"86e80c3a01ebfa9e0ed42643f0dbb14fb2ae55a54f9f10984c10f3f420e6260f"}}