{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EE4GJ4QH7BJJGQYHBHD6BCJ3F6","short_pith_number":"pith:EE4GJ4QH","canonical_record":{"source":{"id":"2604.07789","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-04-09T04:37:24Z","cross_cats_sorted":["cs.CL","cs.SE"],"title_canon_sha256":"fc9fcf02cc8a477b5ae738b369d31e19308b2043ae7b8e5d1c65e59cf33b5641","abstract_canon_sha256":"ecb1ee58f75ae6650058a15e0d74739ee37c69b21bfcaaac6283bbe96b3d978f"},"schema_version":"1.0"},"canonical_sha256":"213864f207f85293430709c7e0893b2f918eb32a02aa4af1394e876c7487ef56","source":{"kind":"arxiv","id":"2604.07789","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.07789","created_at":"2026-05-29T01:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2604.07789v2","created_at":"2026-05-29T01:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.07789","created_at":"2026-05-29T01:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"EE4GJ4QH7BJJ","created_at":"2026-05-29T01:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"EE4GJ4QH7BJJGQYH","created_at":"2026-05-29T01:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"EE4GJ4QH","created_at":"2026-05-29T01:05:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EE4GJ4QH7BJJGQYHBHD6BCJ3F6","target":"record","payload":{"canonical_record":{"source":{"id":"2604.07789","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-04-09T04:37:24Z","cross_cats_sorted":["cs.CL","cs.SE"],"title_canon_sha256":"fc9fcf02cc8a477b5ae738b369d31e19308b2043ae7b8e5d1c65e59cf33b5641","abstract_canon_sha256":"ecb1ee58f75ae6650058a15e0d74739ee37c69b21bfcaaac6283bbe96b3d978f"},"schema_version":"1.0"},"canonical_sha256":"213864f207f85293430709c7e0893b2f918eb32a02aa4af1394e876c7487ef56","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:09.005707Z","signature_b64":"hNL4fOkqHDo+mMmL49Hw5SzM/jr7D5JUw5wmoc7BEJjex1DnETKIh5LU7UmMLZ0dShCaSABlVzrfST5uBjB1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"213864f207f85293430709c7e0893b2f918eb32a02aa4af1394e876c7487ef56","last_reissued_at":"2026-05-29T01:05:09.004828Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:09.004828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.07789","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lXf5+rrwFvOnujIxJLuEovav+1yOdwRuvelvPJcYNV5bb0kTOSnBxF9YfCoDjx0QTyf2en90hdmuKsBBic9DBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:16:53.766751Z"},"content_sha256":"a54beacf2f8ec91e56d6d42932b4f3df39c62cd94fb9e8f896858fcc2f0848ac","schema_version":"1.0","event_id":"sha256:a54beacf2f8ec91e56d6d42932b4f3df39c62cd94fb9e8f896858fcc2f0848ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EE4GJ4QH7BJJGQYHBHD6BCJ3F6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ORACLE-SWE: Quantifying the Contribution of Oracle Information Signals on SWE Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Oracle-SWE isolates perfect versions of key signals from SWE benchmarks to measure their separate effects on agent success rates.","cross_cats":["cs.CL","cs.SE"],"primary_cat":"cs.MA","authors_text":"Chaoyun Zhang, Dongmei Zhang, Elsie Nallipogu, Kenan Li, Liao Zhu, Qingwei Lin, Qirui Jin, Saravan Rajmohan, Wenke Lee, Xiaosong Huang, Xin Zhang, Yijia Wu, Yikai Zhang, Yufan Huang, Yu Kang, Zijian Jin","submitted_at":"2026-04-09T04:37:24Z","abstract_excerpt":"Recent advances in language model (LM) agents have significantly improved automated software engineering (SWE). Prior work has proposed various agentic workflows and training strategies as well as analyzed failure modes of agentic systems on SWE tasks, focusing on several contextual information signals: Reproduction Test, Regression Test, Edit Location, Execution Context, and API Usage. However, the individual contribution of each signal to overall success remains underexplored, particularly their ideal contribution when intermediate information is perfectly obtained. To address this gap, we i"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We introduce Oracle-SWE, a unified method to isolate and extract oracle information signals from SWE benchmarks and quantify the impact of each signal on agent performance.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That isolating signals as perfect oracles and measuring performance gains accurately reflects their real-world contribution where signals are noisy, interdependent, and obtained imperfectly by agents.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ORACLE-SWE isolates oracle signals such as reproduction tests, regression tests, edit locations, execution context, and API usage from SWE benchmarks to quantify their individual contributions to agent performance.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Oracle-SWE isolates perfect versions of key signals from SWE benchmarks to measure their separate effects on agent success rates.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4d289a90ce624868bb0b240eb5234dcb49ed21e00ea5a5a2b374729888a7c9f0"},"source":{"id":"2604.07789","kind":"arxiv","version":2},"verdict":{"id":"d3c15309-9eb5-4a26-8654-262d73ce82c6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T18:25:22.271917Z","strongest_claim":"We introduce Oracle-SWE, a unified method to isolate and extract oracle information signals from SWE benchmarks and quantify the impact of each signal on agent performance.","one_line_summary":"ORACLE-SWE isolates oracle signals such as reproduction tests, regression tests, edit locations, execution context, and API usage from SWE benchmarks to quantify their individual contributions to agent performance.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That isolating signals as perfect oracles and measuring performance gains accurately reflects their real-world contribution where signals are noisy, interdependent, and obtained imperfectly by agents.","pith_extraction_headline":"Oracle-SWE isolates perfect versions of key signals from SWE benchmarks to measure their separate effects on agent success rates."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.07789/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":"d3c15309-9eb5-4a26-8654-262d73ce82c6"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eLS19fUEWAfKULJBu+juiXXwL9G2I+7M+vJPuU5t2iUb6PHlMYJiUGCjBaeorj7CrMLJ3G4Idn4ldiuPkkJCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:16:53.767235Z"},"content_sha256":"012277a52a428ec6f52366b0ee718dd32b18e3fc97c41b8574aeb49c156b3350","schema_version":"1.0","event_id":"sha256:012277a52a428ec6f52366b0ee718dd32b18e3fc97c41b8574aeb49c156b3350"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EE4GJ4QH7BJJGQYHBHD6BCJ3F6/bundle.json","state_url":"https://pith.science/pith/EE4GJ4QH7BJJGQYHBHD6BCJ3F6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EE4GJ4QH7BJJGQYHBHD6BCJ3F6/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":"2026-05-30T11:16:53Z","links":{"resolver":"https://pith.science/pith/EE4GJ4QH7BJJGQYHBHD6BCJ3F6","bundle":"https://pith.science/pith/EE4GJ4QH7BJJGQYHBHD6BCJ3F6/bundle.json","state":"https://pith.science/pith/EE4GJ4QH7BJJGQYHBHD6BCJ3F6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EE4GJ4QH7BJJGQYHBHD6BCJ3F6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EE4GJ4QH7BJJGQYHBHD6BCJ3F6","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":"ecb1ee58f75ae6650058a15e0d74739ee37c69b21bfcaaac6283bbe96b3d978f","cross_cats_sorted":["cs.CL","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-04-09T04:37:24Z","title_canon_sha256":"fc9fcf02cc8a477b5ae738b369d31e19308b2043ae7b8e5d1c65e59cf33b5641"},"schema_version":"1.0","source":{"id":"2604.07789","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.07789","created_at":"2026-05-29T01:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2604.07789v2","created_at":"2026-05-29T01:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.07789","created_at":"2026-05-29T01:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"EE4GJ4QH7BJJ","created_at":"2026-05-29T01:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"EE4GJ4QH7BJJGQYH","created_at":"2026-05-29T01:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"EE4GJ4QH","created_at":"2026-05-29T01:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:012277a52a428ec6f52366b0ee718dd32b18e3fc97c41b8574aeb49c156b3350","target":"graph","created_at":"2026-05-29T01:05:09Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We introduce Oracle-SWE, a unified method to isolate and extract oracle information signals from SWE benchmarks and quantify the impact of each signal on agent performance."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That isolating signals as perfect oracles and measuring performance gains accurately reflects their real-world contribution where signals are noisy, interdependent, and obtained imperfectly by agents."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ORACLE-SWE isolates oracle signals such as reproduction tests, regression tests, edit locations, execution context, and API usage from SWE benchmarks to quantify their individual contributions to agent performance."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Oracle-SWE isolates perfect versions of key signals from SWE benchmarks to measure their separate effects on agent success rates."}],"snapshot_sha256":"4d289a90ce624868bb0b240eb5234dcb49ed21e00ea5a5a2b374729888a7c9f0"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.07789/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in language model (LM) agents have significantly improved automated software engineering (SWE). Prior work has proposed various agentic workflows and training strategies as well as analyzed failure modes of agentic systems on SWE tasks, focusing on several contextual information signals: Reproduction Test, Regression Test, Edit Location, Execution Context, and API Usage. However, the individual contribution of each signal to overall success remains underexplored, particularly their ideal contribution when intermediate information is perfectly obtained. To address this gap, we i","authors_text":"Chaoyun Zhang, Dongmei Zhang, Elsie Nallipogu, Kenan Li, Liao Zhu, Qingwei Lin, Qirui Jin, Saravan Rajmohan, Wenke Lee, Xiaosong Huang, Xin Zhang, Yijia Wu, Yikai Zhang, Yufan Huang, Yu Kang, Zijian Jin","cross_cats":["cs.CL","cs.SE"],"headline":"Oracle-SWE isolates perfect versions of key signals from SWE benchmarks to measure their separate effects on agent success rates.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-04-09T04:37:24Z","title":"ORACLE-SWE: Quantifying the Contribution of Oracle Information Signals on SWE Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.07789","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T18:25:22.271917Z","id":"d3c15309-9eb5-4a26-8654-262d73ce82c6","model_set":{"reader":"grok-4.3"},"one_line_summary":"ORACLE-SWE isolates oracle signals such as reproduction tests, regression tests, edit locations, execution context, and API usage from SWE benchmarks to quantify their individual contributions to agent performance.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Oracle-SWE isolates perfect versions of key signals from SWE benchmarks to measure their separate effects on agent success rates.","strongest_claim":"We introduce Oracle-SWE, a unified method to isolate and extract oracle information signals from SWE benchmarks and quantify the impact of each signal on agent performance.","weakest_assumption":"That isolating signals as perfect oracles and measuring performance gains accurately reflects their real-world contribution where signals are noisy, interdependent, and obtained imperfectly by agents."}},"verdict_id":"d3c15309-9eb5-4a26-8654-262d73ce82c6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a54beacf2f8ec91e56d6d42932b4f3df39c62cd94fb9e8f896858fcc2f0848ac","target":"record","created_at":"2026-05-29T01:05:09Z","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":"ecb1ee58f75ae6650058a15e0d74739ee37c69b21bfcaaac6283bbe96b3d978f","cross_cats_sorted":["cs.CL","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-04-09T04:37:24Z","title_canon_sha256":"fc9fcf02cc8a477b5ae738b369d31e19308b2043ae7b8e5d1c65e59cf33b5641"},"schema_version":"1.0","source":{"id":"2604.07789","kind":"arxiv","version":2}},"canonical_sha256":"213864f207f85293430709c7e0893b2f918eb32a02aa4af1394e876c7487ef56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"213864f207f85293430709c7e0893b2f918eb32a02aa4af1394e876c7487ef56","first_computed_at":"2026-05-29T01:05:09.004828Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:09.004828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hNL4fOkqHDo+mMmL49Hw5SzM/jr7D5JUw5wmoc7BEJjex1DnETKIh5LU7UmMLZ0dShCaSABlVzrfST5uBjB1BA==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:09.005707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.07789","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a54beacf2f8ec91e56d6d42932b4f3df39c62cd94fb9e8f896858fcc2f0848ac","sha256:012277a52a428ec6f52366b0ee718dd32b18e3fc97c41b8574aeb49c156b3350"],"state_sha256":"f925257357211e318ef956d8e433de48ad3ded58df61ead831d3afb315fda32d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l5Bv9sUC9X8RerE/4tiRf3enTDfGk+ohaOWdRcwG8/l57Xx4hYLMmelOnh+8FS2gO6yKa+M4znZl9atyWX0cDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T11:16:53.769774Z","bundle_sha256":"ec8bc9d2d8efd20d17b8fd96d29094a8b3185c27d4b3a197cbaa4f17390dd0af"}}