{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CTVDYX2UTTJQPNQCVLYG4OFABT","short_pith_number":"pith:CTVDYX2U","canonical_record":{"source":{"id":"2607.06624","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T11:27:43Z","cross_cats_sorted":["cs.LG","cs.SE"],"title_canon_sha256":"cde13dae08f5bfb84ef4e2ee711bc65c69efdf66d1b890b0d928b6bbb688a7aa","abstract_canon_sha256":"5452f052e18d85e867fb9d2a3fe9fbb7fc964cf44b869400b1efd736fe8dcea3"},"schema_version":"1.0"},"canonical_sha256":"14ea3c5f549cd307b602aaf06e38a00cc64a6ab5f43b070921d5c9c9ba165ca5","source":{"kind":"arxiv","id":"2607.06624","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06624","created_at":"2026-07-09T00:19:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06624v1","created_at":"2026-07-09T00:19:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06624","created_at":"2026-07-09T00:19:20Z"},{"alias_kind":"pith_short_12","alias_value":"CTVDYX2UTTJQ","created_at":"2026-07-09T00:19:20Z"},{"alias_kind":"pith_short_16","alias_value":"CTVDYX2UTTJQPNQC","created_at":"2026-07-09T00:19:20Z"},{"alias_kind":"pith_short_8","alias_value":"CTVDYX2U","created_at":"2026-07-09T00:19:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CTVDYX2UTTJQPNQCVLYG4OFABT","target":"record","payload":{"canonical_record":{"source":{"id":"2607.06624","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T11:27:43Z","cross_cats_sorted":["cs.LG","cs.SE"],"title_canon_sha256":"cde13dae08f5bfb84ef4e2ee711bc65c69efdf66d1b890b0d928b6bbb688a7aa","abstract_canon_sha256":"5452f052e18d85e867fb9d2a3fe9fbb7fc964cf44b869400b1efd736fe8dcea3"},"schema_version":"1.0"},"canonical_sha256":"14ea3c5f549cd307b602aaf06e38a00cc64a6ab5f43b070921d5c9c9ba165ca5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T00:19:20.780424Z","signature_b64":"hrlEFNbXXZnIkmjyiat1qHZuCBuIVKzKKqYUat2jYuNMAsXAd20O7fSQKLbx5MqMV0lAJVV3KNWCegIXfsUvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14ea3c5f549cd307b602aaf06e38a00cc64a6ab5f43b070921d5c9c9ba165ca5","last_reissued_at":"2026-07-09T00:19:20.779916Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T00:19:20.779916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.06624","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":"2026-07-09T00:19:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nUkDGxv4lGoOmsbUSLgpI8T3+ESAUWVBfq6l0xWDge4/K6lKSgJQHS6KWLsJWxrHXycljLaRfciTVcY+gB/3Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T17:44:48.426146Z"},"content_sha256":"fe88403f0fe0379ea1e012ad11e85a7130eb69b247982e9b255137355cabe56a","schema_version":"1.0","event_id":"sha256:fe88403f0fe0379ea1e012ad11e85a7130eb69b247982e9b255137355cabe56a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CTVDYX2UTTJQPNQCVLYG4OFABT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.AI","authors_text":"Andrey Podivilov, Maksim Parshin, Matvei Startsev, Roman Pozharskiy, Sergey Nikolenko, Sergey Savin, Vadim Lomshakov","submitted_at":"2026-07-07T11:27:43Z","abstract_excerpt":"We present AgentLens, a production-assessed benchmark for interactive code agents. Most code-agent benchmarks reduce a run to a single bit -- did the task pass? -- but the people who actually use these agents experience the entire trajectory: how the agent follows instructions, uses its tools, verifies its own work, recovers from mistakes, and talks to them along the way. AgentLens evaluates that whole trajectory. It pairs formal verification, where an objective check exists, with LLM-written trajectory reviews and side-by-side comparisons, so that each run yields a readable explanation of why"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06624","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/2607.06624/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":"2026-07-09T00:19:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8eT7XqjPJCgyYII7dAZs2yDTKeXrGHXA0VafXjENkPUaErxoqpk0fabhdWXlHg/h2rK849N6eZFBQDfhmDXWDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T17:44:48.426670Z"},"content_sha256":"c2dbd5498f270c6a42558a5d23fbade759dbb0d69f95049cc57fe2901599d2cb","schema_version":"1.0","event_id":"sha256:c2dbd5498f270c6a42558a5d23fbade759dbb0d69f95049cc57fe2901599d2cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CTVDYX2UTTJQPNQCVLYG4OFABT/bundle.json","state_url":"https://pith.science/pith/CTVDYX2UTTJQPNQCVLYG4OFABT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CTVDYX2UTTJQPNQCVLYG4OFABT/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":"2026-08-01T17:44:48Z","links":{"resolver":"https://pith.science/pith/CTVDYX2UTTJQPNQCVLYG4OFABT","bundle":"https://pith.science/pith/CTVDYX2UTTJQPNQCVLYG4OFABT/bundle.json","state":"https://pith.science/pith/CTVDYX2UTTJQPNQCVLYG4OFABT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CTVDYX2UTTJQPNQCVLYG4OFABT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CTVDYX2UTTJQPNQCVLYG4OFABT","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":"5452f052e18d85e867fb9d2a3fe9fbb7fc964cf44b869400b1efd736fe8dcea3","cross_cats_sorted":["cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T11:27:43Z","title_canon_sha256":"cde13dae08f5bfb84ef4e2ee711bc65c69efdf66d1b890b0d928b6bbb688a7aa"},"schema_version":"1.0","source":{"id":"2607.06624","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06624","created_at":"2026-07-09T00:19:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06624v1","created_at":"2026-07-09T00:19:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06624","created_at":"2026-07-09T00:19:20Z"},{"alias_kind":"pith_short_12","alias_value":"CTVDYX2UTTJQ","created_at":"2026-07-09T00:19:20Z"},{"alias_kind":"pith_short_16","alias_value":"CTVDYX2UTTJQPNQC","created_at":"2026-07-09T00:19:20Z"},{"alias_kind":"pith_short_8","alias_value":"CTVDYX2U","created_at":"2026-07-09T00:19:20Z"}],"graph_snapshots":[{"event_id":"sha256:c2dbd5498f270c6a42558a5d23fbade759dbb0d69f95049cc57fe2901599d2cb","target":"graph","created_at":"2026-07-09T00:19:20Z","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/2607.06624/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present AgentLens, a production-assessed benchmark for interactive code agents. Most code-agent benchmarks reduce a run to a single bit -- did the task pass? -- but the people who actually use these agents experience the entire trajectory: how the agent follows instructions, uses its tools, verifies its own work, recovers from mistakes, and talks to them along the way. AgentLens evaluates that whole trajectory. It pairs formal verification, where an objective check exists, with LLM-written trajectory reviews and side-by-side comparisons, so that each run yields a readable explanation of why","authors_text":"Andrey Podivilov, Maksim Parshin, Matvei Startsev, Roman Pozharskiy, Sergey Nikolenko, Sergey Savin, Vadim Lomshakov","cross_cats":["cs.LG","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T11:27:43Z","title":"AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06624","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:fe88403f0fe0379ea1e012ad11e85a7130eb69b247982e9b255137355cabe56a","target":"record","created_at":"2026-07-09T00:19:20Z","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":"5452f052e18d85e867fb9d2a3fe9fbb7fc964cf44b869400b1efd736fe8dcea3","cross_cats_sorted":["cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T11:27:43Z","title_canon_sha256":"cde13dae08f5bfb84ef4e2ee711bc65c69efdf66d1b890b0d928b6bbb688a7aa"},"schema_version":"1.0","source":{"id":"2607.06624","kind":"arxiv","version":1}},"canonical_sha256":"14ea3c5f549cd307b602aaf06e38a00cc64a6ab5f43b070921d5c9c9ba165ca5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14ea3c5f549cd307b602aaf06e38a00cc64a6ab5f43b070921d5c9c9ba165ca5","first_computed_at":"2026-07-09T00:19:20.779916Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T00:19:20.779916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hrlEFNbXXZnIkmjyiat1qHZuCBuIVKzKKqYUat2jYuNMAsXAd20O7fSQKLbx5MqMV0lAJVV3KNWCegIXfsUvCg==","signature_status":"signed_v1","signed_at":"2026-07-09T00:19:20.780424Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.06624","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe88403f0fe0379ea1e012ad11e85a7130eb69b247982e9b255137355cabe56a","sha256:c2dbd5498f270c6a42558a5d23fbade759dbb0d69f95049cc57fe2901599d2cb"],"state_sha256":"cc8a21f1f888af45d99f7bb87e2b09e421a813be9baebfbe8f2e04d97709900c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b7gEygr3NzaSeP4aJenev7IEaDtKBJhrMnarO35o2QyFwGtlzzTWeEnXhUEbAJU61QYsLQ7LLDWqXyxldfl2Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T17:44:48.432063Z","bundle_sha256":"68185d14d27e5802fbc6eadad9e741f4a03c91f7aa8c08b866580f5dd346f515"}}