{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XLVOGR74UBGGO4ORFMO66NZJUJ","short_pith_number":"pith:XLVOGR74","canonical_record":{"source":{"id":"2607.26451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-29T04:04:54Z","cross_cats_sorted":[],"title_canon_sha256":"3809b104afed44644431dfb88682385a9b5edea3d44dc7f7b996c1a8cd258f77","abstract_canon_sha256":"25962a2e4508e591f0410accfbbc9c4b655e85b72f030587515232dddf9c1b98"},"schema_version":"1.0"},"canonical_sha256":"baeae347fca04c6771d12b1def3729a2798317502450c038af0c221603372159","source":{"kind":"arxiv","id":"2607.26451","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26451","created_at":"2026-07-30T01:20:32Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26451v1","created_at":"2026-07-30T01:20:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26451","created_at":"2026-07-30T01:20:32Z"},{"alias_kind":"pith_short_12","alias_value":"XLVOGR74UBGG","created_at":"2026-07-30T01:20:32Z"},{"alias_kind":"pith_short_16","alias_value":"XLVOGR74UBGGO4OR","created_at":"2026-07-30T01:20:32Z"},{"alias_kind":"pith_short_8","alias_value":"XLVOGR74","created_at":"2026-07-30T01:20:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XLVOGR74UBGGO4ORFMO66NZJUJ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.26451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-29T04:04:54Z","cross_cats_sorted":[],"title_canon_sha256":"3809b104afed44644431dfb88682385a9b5edea3d44dc7f7b996c1a8cd258f77","abstract_canon_sha256":"25962a2e4508e591f0410accfbbc9c4b655e85b72f030587515232dddf9c1b98"},"schema_version":"1.0"},"canonical_sha256":"baeae347fca04c6771d12b1def3729a2798317502450c038af0c221603372159","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"baeae347fca04c6771d12b1def3729a2798317502450c038af0c221603372159","last_reissued_at":"2026-07-30T01:20:32.447568Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:20:32.447568Z"},"source_kind":"arxiv","source_id":"2607.26451","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":"2026-07-30T01:20:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bPns85drbpTrDruQ/3iMNkkWnUDSEEOhWfWF+jgn/mbzVeT8HKh3uM2zzserfax/5jhCPca8Jx7DMRe1agAiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T20:57:17.965765Z"},"content_sha256":"10214bca278cf93601dcabb43e6d5b9e0f3981b3a5939bb3195ee05cc367d5ff","schema_version":"1.0","event_id":"sha256:10214bca278cf93601dcabb43e6d5b9e0f3981b3a5939bb3195ee05cc367d5ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XLVOGR74UBGGO4ORFMO66NZJUJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ExplainBench: Evaluating Code Explanations from Agents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Abhik Roychoudhury, Imam Nur Bani Yusuf, Sungmin Kang, Zhiyuan Pan","submitted_at":"2026-07-29T04:04:54Z","abstract_excerpt":"Large Language Model (LLM) agents have seen rapid adoption in software engineering. As agents take a greater role in the actual generation of code, they are making larger changes, spanning tens to hundreds of lines. This makes manual review of agent results increasingly infeasible, leading developers to turn to explanations to understand enacted changes. Despite this, there are no benchmarks that evaluate the trustworthiness of agent-generated explanations. To bridge this gap, we propose ExplainBench, a benchmark to automatically evaluate explanations from coding agents. ExplainBench is based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26451","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/2607.26451/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":"2026-07-30T01:20:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YzfS3yLBJ0Sw0HlHTY8DkQcv92ZjB6RRz+Fb4chhg9/FjZtvqcIAdifqktfuychJguMFHfx+bmtmtXNg7H/AAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T20:57:17.966153Z"},"content_sha256":"552f2983273f7902208bf0164bbba5a825e72740029a726ce792dd631705dd0e","schema_version":"1.0","event_id":"sha256:552f2983273f7902208bf0164bbba5a825e72740029a726ce792dd631705dd0e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XLVOGR74UBGGO4ORFMO66NZJUJ/bundle.json","state_url":"https://pith.science/pith/XLVOGR74UBGGO4ORFMO66NZJUJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XLVOGR74UBGGO4ORFMO66NZJUJ/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":"2026-08-02T20:57:17Z","links":{"resolver":"https://pith.science/pith/XLVOGR74UBGGO4ORFMO66NZJUJ","bundle":"https://pith.science/pith/XLVOGR74UBGGO4ORFMO66NZJUJ/bundle.json","state":"https://pith.science/pith/XLVOGR74UBGGO4ORFMO66NZJUJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XLVOGR74UBGGO4ORFMO66NZJUJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XLVOGR74UBGGO4ORFMO66NZJUJ","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":"25962a2e4508e591f0410accfbbc9c4b655e85b72f030587515232dddf9c1b98","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-29T04:04:54Z","title_canon_sha256":"3809b104afed44644431dfb88682385a9b5edea3d44dc7f7b996c1a8cd258f77"},"schema_version":"1.0","source":{"id":"2607.26451","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26451","created_at":"2026-07-30T01:20:32Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26451v1","created_at":"2026-07-30T01:20:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26451","created_at":"2026-07-30T01:20:32Z"},{"alias_kind":"pith_short_12","alias_value":"XLVOGR74UBGG","created_at":"2026-07-30T01:20:32Z"},{"alias_kind":"pith_short_16","alias_value":"XLVOGR74UBGGO4OR","created_at":"2026-07-30T01:20:32Z"},{"alias_kind":"pith_short_8","alias_value":"XLVOGR74","created_at":"2026-07-30T01:20:32Z"}],"graph_snapshots":[{"event_id":"sha256:552f2983273f7902208bf0164bbba5a825e72740029a726ce792dd631705dd0e","target":"graph","created_at":"2026-07-30T01:20:32Z","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/2607.26451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Model (LLM) agents have seen rapid adoption in software engineering. As agents take a greater role in the actual generation of code, they are making larger changes, spanning tens to hundreds of lines. This makes manual review of agent results increasingly infeasible, leading developers to turn to explanations to understand enacted changes. Despite this, there are no benchmarks that evaluate the trustworthiness of agent-generated explanations. To bridge this gap, we propose ExplainBench, a benchmark to automatically evaluate explanations from coding agents. ExplainBench is based ","authors_text":"Abhik Roychoudhury, Imam Nur Bani Yusuf, Sungmin Kang, Zhiyuan Pan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-29T04:04:54Z","title":"ExplainBench: Evaluating Code Explanations from Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26451","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":"sha256:10214bca278cf93601dcabb43e6d5b9e0f3981b3a5939bb3195ee05cc367d5ff","target":"record","created_at":"2026-07-30T01:20:32Z","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":"25962a2e4508e591f0410accfbbc9c4b655e85b72f030587515232dddf9c1b98","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-29T04:04:54Z","title_canon_sha256":"3809b104afed44644431dfb88682385a9b5edea3d44dc7f7b996c1a8cd258f77"},"schema_version":"1.0","source":{"id":"2607.26451","kind":"arxiv","version":1}},"canonical_sha256":"baeae347fca04c6771d12b1def3729a2798317502450c038af0c221603372159","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"baeae347fca04c6771d12b1def3729a2798317502450c038af0c221603372159","first_computed_at":"2026-07-30T01:20:32.447568Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:20:32.447568Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26451","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10214bca278cf93601dcabb43e6d5b9e0f3981b3a5939bb3195ee05cc367d5ff","sha256:552f2983273f7902208bf0164bbba5a825e72740029a726ce792dd631705dd0e"],"state_sha256":"3c05a3aa4e95cc00c3d3b249d1af0ce8a53493cc23b72c85e11a0852da1bb5f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mHrdcs1Tdlce9sx0zL/a7JbknUkcOBrLslmMPs2l106SxjbVcsXSrKgVjwlOnaJBkiJtAyq+n/SDucAZU9oMAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T20:57:17.968807Z","bundle_sha256":"fc02a141f584f4f88dbd0b55b307d2d6cf4022f7f5fb8228e699364bafe3ab15"}}