{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OUNPRBWC5PAOMYXVT326XKMLWF","short_pith_number":"pith:OUNPRBWC","canonical_record":{"source":{"id":"2608.08413","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-09T02:08:34Z","cross_cats_sorted":[],"title_canon_sha256":"3b5ad489c0d3737c2cb7cd19d622f62f5207c3a6f7c32ce2d6fc216d8245a1d0","abstract_canon_sha256":"b691ac474e27ec580775da39fc007f531a6921b13d612fe079974a1dd3b75921"},"schema_version":"1.0"},"canonical_sha256":"751af886c2ebc0e662f59ef5eba98bb17c090cdaaf921b4fcfe91b5a7b46b08f","source":{"kind":"arxiv","id":"2608.08413","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08413","created_at":"2026-08-11T01:22:34Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08413v1","created_at":"2026-08-11T01:22:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08413","created_at":"2026-08-11T01:22:34Z"},{"alias_kind":"pith_short_12","alias_value":"OUNPRBWC5PAO","created_at":"2026-08-11T01:22:34Z"},{"alias_kind":"pith_short_16","alias_value":"OUNPRBWC5PAOMYXV","created_at":"2026-08-11T01:22:34Z"},{"alias_kind":"pith_short_8","alias_value":"OUNPRBWC","created_at":"2026-08-11T01:22:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OUNPRBWC5PAOMYXVT326XKMLWF","target":"record","payload":{"canonical_record":{"source":{"id":"2608.08413","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-09T02:08:34Z","cross_cats_sorted":[],"title_canon_sha256":"3b5ad489c0d3737c2cb7cd19d622f62f5207c3a6f7c32ce2d6fc216d8245a1d0","abstract_canon_sha256":"b691ac474e27ec580775da39fc007f531a6921b13d612fe079974a1dd3b75921"},"schema_version":"1.0"},"canonical_sha256":"751af886c2ebc0e662f59ef5eba98bb17c090cdaaf921b4fcfe91b5a7b46b08f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:22:34.823848Z","signature_b64":"btjGNXzk/U6rWD+5HKmnzAOG5CgxyXzdS3xjT+bY4Df5N1I77AF1V9XBTeQAlD7ZESYgaz9k5phJspM+D545Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"751af886c2ebc0e662f59ef5eba98bb17c090cdaaf921b4fcfe91b5a7b46b08f","last_reissued_at":"2026-08-11T01:22:34.821375Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:22:34.821375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.08413","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":"2026-08-11T01:22:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6uRC5hT/5usyJACYvEZlL3dWN12xBZqRAzSVuGGZuZeySOpws4Tjc5Qp0vYcKQ0JzLQz8IIQzkIlK3EQAOkqAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:23:23.126052Z"},"content_sha256":"e6591a2ac367a74eb2dcf5248893c00ebcb630e9ee850ff1c941976b0702a9cb","schema_version":"1.0","event_id":"sha256:e6591a2ac367a74eb2dcf5248893c00ebcb630e9ee850ff1c941976b0702a9cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OUNPRBWC5PAOMYXVT326XKMLWF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tangent: An Empirical Study of Testing Practices for LLM-Based Agent Applications","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Alessandro Orso, Bridget McGinn, Divya Sankar, Maja Vukovic, Raju Pavuluri, Rangeet Pan, Saurabh Sinha, Tyler Stennett","submitted_at":"2026-08-09T02:08:34Z","abstract_excerpt":"Agents built on large language models (LLMs) are increasingly used to build applications that perform complex, multi-step tasks involving reasoning, tool use, and interaction with external environments. Despite rapid progress in benchmarking LLM-based agents, very few studies have attempted to understand how such systems are tested in practice. In particular, testing levels, objectives, data patterns, test complexity, and validation strategies for agent applications remain underexplored. In this paper, we present an empirical study of testing practices in LLM-based agent applications using a l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08413","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/2608.08413/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":"2026-08-11T01:22:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QnUdpVseReqCpSQiuLE0gvvJ4g1uEFci4KUW3owbG/kqcJLIcykt+sJXT44dc0FAFyJhN8MpK+zT/94EHDm9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:23:23.126624Z"},"content_sha256":"93e3b133151be82d40da9dae5e369be4a86cee8a29e54d2771cf05e7ef7fee42","schema_version":"1.0","event_id":"sha256:93e3b133151be82d40da9dae5e369be4a86cee8a29e54d2771cf05e7ef7fee42"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:OUNPRBWC5PAOMYXVT326XKMLWF","target":"integrity","payload":{"note":"DOI is split by whitespace or line breaks in the printed bibliography. Reconstructed DOI 10.1145/62959.62963 resolves to 'The evaluation of program-based software test data adequacy criteria'. A reader following the printed text alone cannot reach it.","snippet":"E. J. Weyuker. 1988. The evaluation of program-based software test data ade- quacy criteria. Commun. ACM 31, 6 (June 1988), 668–675. doi:10.1145/62959. 62963","arxiv_id":"2608.08413","detector":"doi_compliance","evidence":{"ref_index":91,"verdict_class":"incontrovertible","resolved_title":"The evaluation of program-based software test data adequacy criteria","printed_excerpt":"10.1145/62959","reconstructed_doi":"10.1145/62959.62963"},"severity":"advisory","ref_index":91,"audited_at":"2026-08-14T05:29:18.961625Z","event_type":"pith.integrity.v1","detected_doi":"10.1145/62959.62963","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"339395fa40aae0091ae8cd8d1394fea9640c8c70d31f7f38c1aaff8240dae4ab","paper_version":1,"verdict_class":"incontrovertible","resolved_title":"The evaluation of program-based software test data adequacy criteria","detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":19674,"payload_sha256":"eb19f2072c1038f78e25ec0b39b96ec405ec3449c24a4e2a838a8cbc4709666c","signature_b64":"JQBdUxaIdzA0fTthJamfS7zZqz5jhGlJJ8P3L0EisY3obQkVI712Av7AeuzgIfEb20kY6qd7XH/e0s7IlxXTAA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-14T05:33:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S5Dpy6X0Ibg5TcC6BEwmpGDYGNKGD2zxoiE0Hk8wn7TCiGut2Xj1f07dO5vlqV59aXCSLfFh/E9CfoTSMT+DCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:23:23.131247Z"},"content_sha256":"94709b6be586d003cae240281b25e91796d2b23f99df432570a5d0c7fd45d261","schema_version":"1.0","event_id":"sha256:94709b6be586d003cae240281b25e91796d2b23f99df432570a5d0c7fd45d261"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OUNPRBWC5PAOMYXVT326XKMLWF/bundle.json","state_url":"https://pith.science/pith/OUNPRBWC5PAOMYXVT326XKMLWF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OUNPRBWC5PAOMYXVT326XKMLWF/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":"2026-08-14T13:23:23Z","links":{"resolver":"https://pith.science/pith/OUNPRBWC5PAOMYXVT326XKMLWF","bundle":"https://pith.science/pith/OUNPRBWC5PAOMYXVT326XKMLWF/bundle.json","state":"https://pith.science/pith/OUNPRBWC5PAOMYXVT326XKMLWF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OUNPRBWC5PAOMYXVT326XKMLWF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OUNPRBWC5PAOMYXVT326XKMLWF","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b691ac474e27ec580775da39fc007f531a6921b13d612fe079974a1dd3b75921","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-09T02:08:34Z","title_canon_sha256":"3b5ad489c0d3737c2cb7cd19d622f62f5207c3a6f7c32ce2d6fc216d8245a1d0"},"schema_version":"1.0","source":{"id":"2608.08413","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08413","created_at":"2026-08-11T01:22:34Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08413v1","created_at":"2026-08-11T01:22:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08413","created_at":"2026-08-11T01:22:34Z"},{"alias_kind":"pith_short_12","alias_value":"OUNPRBWC5PAO","created_at":"2026-08-11T01:22:34Z"},{"alias_kind":"pith_short_16","alias_value":"OUNPRBWC5PAOMYXV","created_at":"2026-08-11T01:22:34Z"},{"alias_kind":"pith_short_8","alias_value":"OUNPRBWC","created_at":"2026-08-11T01:22:34Z"}],"graph_snapshots":[{"event_id":"sha256:93e3b133151be82d40da9dae5e369be4a86cee8a29e54d2771cf05e7ef7fee42","target":"graph","created_at":"2026-08-11T01:22:34Z","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/2608.08413/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agents built on large language models (LLMs) are increasingly used to build applications that perform complex, multi-step tasks involving reasoning, tool use, and interaction with external environments. Despite rapid progress in benchmarking LLM-based agents, very few studies have attempted to understand how such systems are tested in practice. In particular, testing levels, objectives, data patterns, test complexity, and validation strategies for agent applications remain underexplored. In this paper, we present an empirical study of testing practices in LLM-based agent applications using a l","authors_text":"Alessandro Orso, Bridget McGinn, Divya Sankar, Maja Vukovic, Raju Pavuluri, Rangeet Pan, Saurabh Sinha, Tyler Stennett","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-09T02:08:34Z","title":"Tangent: An Empirical Study of Testing Practices for LLM-Based Agent Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08413","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:e6591a2ac367a74eb2dcf5248893c00ebcb630e9ee850ff1c941976b0702a9cb","target":"record","created_at":"2026-08-11T01:22:34Z","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":"b691ac474e27ec580775da39fc007f531a6921b13d612fe079974a1dd3b75921","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-09T02:08:34Z","title_canon_sha256":"3b5ad489c0d3737c2cb7cd19d622f62f5207c3a6f7c32ce2d6fc216d8245a1d0"},"schema_version":"1.0","source":{"id":"2608.08413","kind":"arxiv","version":1}},"canonical_sha256":"751af886c2ebc0e662f59ef5eba98bb17c090cdaaf921b4fcfe91b5a7b46b08f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"751af886c2ebc0e662f59ef5eba98bb17c090cdaaf921b4fcfe91b5a7b46b08f","first_computed_at":"2026-08-11T01:22:34.821375Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:22:34.821375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"btjGNXzk/U6rWD+5HKmnzAOG5CgxyXzdS3xjT+bY4Df5N1I77AF1V9XBTeQAlD7ZESYgaz9k5phJspM+D545Bw==","signature_status":"signed_v1","signed_at":"2026-08-11T01:22:34.823848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08413","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6591a2ac367a74eb2dcf5248893c00ebcb630e9ee850ff1c941976b0702a9cb","sha256:93e3b133151be82d40da9dae5e369be4a86cee8a29e54d2771cf05e7ef7fee42","sha256:94709b6be586d003cae240281b25e91796d2b23f99df432570a5d0c7fd45d261"],"state_sha256":"03a85fd41dcab7693f5d287356646aa0e5ce8ad318b54e51f3bede0679c7dc02"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XctWx9/0LEN8aTJEPMSV3mBWRIOaqdUQlGH9uCVSVifwPkjSPXtzbh9+VvlVVIif2AsODF+OfeAMKFat4o0dAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T13:23:23.133864Z","bundle_sha256":"b520634a4ac3da18d77dfcace80c6d09b1a0348775bf8c5f4839aac6d8529e8c"}}