{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NGJABKURGL5JM36CX6RWQFD4AW","short_pith_number":"pith:NGJABKUR","schema_version":"1.0","canonical_sha256":"699200aa9132fa966fc2bfa368147c0593b0dd8466d21608d2880eec31b2abc8","source":{"kind":"arxiv","id":"2608.04195","version":1},"attestation_state":"computed","paper":{"title":"SONAR: Task-Aware Code Summary Evaluation for LLM Consumers Without References","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Matthew B. Dwyer, Simantika Bhattacharjee Dristi","submitted_at":"2026-08-04T19:54:45Z","abstract_excerpt":"Source code summaries have traditionally been evaluated from a human developer's perspective, with quality determined by how closely they resemble developer-written references and how well they align with human preferences. But this overlooks a growing reality: LLM-based tools and agents increasingly consume code summaries as inputs for software engineering (SE) tasks, and what makes a summary useful for a consuming agent on a task remains largely unexplored. To bridge this gap, we propose SONAR, a reference-free framework that evaluates source code summaries along four dimensions: Correctness"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.04195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-04T19:54:45Z","cross_cats_sorted":[],"title_canon_sha256":"089501135ce7acf5f249b43220d5b2e140cc64d9187a6a8b59d070a112b7e85e","abstract_canon_sha256":"ac4a1688c708308f9c4c8f33ac3538ec7157bb9b25f488353552baefb14ced7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:31:21.952007Z","signature_b64":"pHly+eLRgo1jyKoawVOl16aX29bwPcnI48oGqvQFKhtwEEM0ADewX+kQIosT0bLAut5WdOE4N9D46oB471ViDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"699200aa9132fa966fc2bfa368147c0593b0dd8466d21608d2880eec31b2abc8","last_reissued_at":"2026-08-06T01:31:21.950462Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:31:21.950462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SONAR: Task-Aware Code Summary Evaluation for LLM Consumers Without References","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Matthew B. Dwyer, Simantika Bhattacharjee Dristi","submitted_at":"2026-08-04T19:54:45Z","abstract_excerpt":"Source code summaries have traditionally been evaluated from a human developer's perspective, with quality determined by how closely they resemble developer-written references and how well they align with human preferences. But this overlooks a growing reality: LLM-based tools and agents increasingly consume code summaries as inputs for software engineering (SE) tasks, and what makes a summary useful for a consuming agent on a task remains largely unexplored. To bridge this gap, we propose SONAR, a reference-free framework that evaluates source code summaries along four dimensions: Correctness"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04195","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/2608.04195/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.04195","created_at":"2026-08-06T01:31:21.952322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04195v1","created_at":"2026-08-06T01:31:21.952322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04195","created_at":"2026-08-06T01:31:21.952322+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGJABKURGL5J","created_at":"2026-08-06T01:31:21.952322+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGJABKURGL5JM36C","created_at":"2026-08-06T01:31:21.952322+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGJABKUR","created_at":"2026-08-06T01:31:21.952322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NGJABKURGL5JM36CX6RWQFD4AW","json":"https://pith.science/pith/NGJABKURGL5JM36CX6RWQFD4AW.json","graph_json":"https://pith.science/api/pith-number/NGJABKURGL5JM36CX6RWQFD4AW/graph.json","events_json":"https://pith.science/api/pith-number/NGJABKURGL5JM36CX6RWQFD4AW/events.json","paper":"https://pith.science/paper/NGJABKUR"},"agent_actions":{"view_html":"https://pith.science/pith/NGJABKURGL5JM36CX6RWQFD4AW","download_json":"https://pith.science/pith/NGJABKURGL5JM36CX6RWQFD4AW.json","view_paper":"https://pith.science/paper/NGJABKUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04195&json=true","fetch_graph":"https://pith.science/api/pith-number/NGJABKURGL5JM36CX6RWQFD4AW/graph.json","fetch_events":"https://pith.science/api/pith-number/NGJABKURGL5JM36CX6RWQFD4AW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGJABKURGL5JM36CX6RWQFD4AW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGJABKURGL5JM36CX6RWQFD4AW/action/storage_attestation","attest_author":"https://pith.science/pith/NGJABKURGL5JM36CX6RWQFD4AW/action/author_attestation","sign_citation":"https://pith.science/pith/NGJABKURGL5JM36CX6RWQFD4AW/action/citation_signature","submit_replication":"https://pith.science/pith/NGJABKURGL5JM36CX6RWQFD4AW/action/replication_record"}},"created_at":"2026-08-06T01:31:21.952322+00:00","updated_at":"2026-08-06T01:31:21.952322+00:00"}