{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HY4YKJGFHXYTQZD323GJVX46OE","short_pith_number":"pith:HY4YKJGF","canonical_record":{"source":{"id":"2502.04349","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T15:47:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b3fc482542917383cb0b567526a09ca13b9bf2e4582ed59cf6cab623c145e0bc","abstract_canon_sha256":"1361b87e240a6667db0df27b274927020553e3c10f8b59760cc64bf48fac67ff"},"schema_version":"1.0"},"canonical_sha256":"3e398524c53df138647bd6cc9adf9e71111fc2f0902e1ba66f8a266bf74fddb5","source":{"kind":"arxiv","id":"2502.04349","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04349","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04349v1","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04349","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_12","alias_value":"HY4YKJGFHXYT","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_16","alias_value":"HY4YKJGFHXYTQZD3","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_8","alias_value":"HY4YKJGF","created_at":"2026-07-05T10:10:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HY4YKJGFHXYTQZD323GJVX46OE","target":"record","payload":{"canonical_record":{"source":{"id":"2502.04349","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T15:47:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b3fc482542917383cb0b567526a09ca13b9bf2e4582ed59cf6cab623c145e0bc","abstract_canon_sha256":"1361b87e240a6667db0df27b274927020553e3c10f8b59760cc64bf48fac67ff"},"schema_version":"1.0"},"canonical_sha256":"3e398524c53df138647bd6cc9adf9e71111fc2f0902e1ba66f8a266bf74fddb5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:50.073382Z","signature_b64":"FUYv7CZQln0jPtc455xMF8+qHjEbi2d1wiuONRTxc/YFcPf0VQ7xnICsjkK+tkL6WjZyg6fUSpI7UgOJDy6XCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e398524c53df138647bd6cc9adf9e71111fc2f0902e1ba66f8a266bf74fddb5","last_reissued_at":"2026-07-05T10:10:50.072920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:50.072920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.04349","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":"2026-07-05T10:10:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dul1qsxZgj/qH3fOdsGP9KOlxjDgs0n2F7/eByXfeIW7pgzi8obQGw7bEyurlOqELg2djY8pDYxv8UuxD9chCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T07:39:20.697656Z"},"content_sha256":"148d6b0192bcfe335093d8f2b2ce9e0eb9a73338a832c583c667c7bf5c4f1a67","schema_version":"1.0","event_id":"sha256:148d6b0192bcfe335093d8f2b2ce9e0eb9a73338a832c583c667c7bf5c4f1a67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HY4YKJGFHXYTQZD323GJVX46OE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic benchmarking framework for LLM-based conversational data capture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Marya Bazzi, Matt Arderne, Patrick Zietkiewicz, Pietro Alessandro Aluffi, Vladimirs Murevics","submitted_at":"2025-02-04T15:47:47Z","abstract_excerpt":"The rapid evolution of large language models (LLMs) has transformed conversational agents, enabling complex human-machine interactions. However, evaluation frameworks often focus on single tasks, failing to capture the dynamic nature of multi-turn dialogues. This paper introduces a dynamic benchmarking framework to assess LLM-based conversational agents through interactions with synthetic users. The framework integrates generative agent simulation to evaluate performance on key dimensions: information extraction, context awareness, and adaptive engagement. By simulating various aspects of user"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04349","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/2502.04349/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":"2026-07-05T10:10:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yweLOYTbqccullSr+BdoVLB6bXjTr+3BHIfqJ3Nf0uHygspERaEE6L8+ZKs21h0Knvhuh1hkNKnk0fX5Lxa1AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T07:39:20.698227Z"},"content_sha256":"ae1b62fa5764e3f8eb990b0fe38f36f70c0ff7672938ce92be5ba09b4b38a907","schema_version":"1.0","event_id":"sha256:ae1b62fa5764e3f8eb990b0fe38f36f70c0ff7672938ce92be5ba09b4b38a907"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HY4YKJGFHXYTQZD323GJVX46OE/bundle.json","state_url":"https://pith.science/pith/HY4YKJGFHXYTQZD323GJVX46OE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HY4YKJGFHXYTQZD323GJVX46OE/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":"2026-08-20T07:39:20Z","links":{"resolver":"https://pith.science/pith/HY4YKJGFHXYTQZD323GJVX46OE","bundle":"https://pith.science/pith/HY4YKJGFHXYTQZD323GJVX46OE/bundle.json","state":"https://pith.science/pith/HY4YKJGFHXYTQZD323GJVX46OE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HY4YKJGFHXYTQZD323GJVX46OE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HY4YKJGFHXYTQZD323GJVX46OE","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":"1361b87e240a6667db0df27b274927020553e3c10f8b59760cc64bf48fac67ff","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T15:47:47Z","title_canon_sha256":"b3fc482542917383cb0b567526a09ca13b9bf2e4582ed59cf6cab623c145e0bc"},"schema_version":"1.0","source":{"id":"2502.04349","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04349","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04349v1","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04349","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_12","alias_value":"HY4YKJGFHXYT","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_16","alias_value":"HY4YKJGFHXYTQZD3","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_8","alias_value":"HY4YKJGF","created_at":"2026-07-05T10:10:50Z"}],"graph_snapshots":[{"event_id":"sha256:ae1b62fa5764e3f8eb990b0fe38f36f70c0ff7672938ce92be5ba09b4b38a907","target":"graph","created_at":"2026-07-05T10:10:50Z","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/2502.04349/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid evolution of large language models (LLMs) has transformed conversational agents, enabling complex human-machine interactions. However, evaluation frameworks often focus on single tasks, failing to capture the dynamic nature of multi-turn dialogues. This paper introduces a dynamic benchmarking framework to assess LLM-based conversational agents through interactions with synthetic users. The framework integrates generative agent simulation to evaluate performance on key dimensions: information extraction, context awareness, and adaptive engagement. By simulating various aspects of user","authors_text":"Marya Bazzi, Matt Arderne, Patrick Zietkiewicz, Pietro Alessandro Aluffi, Vladimirs Murevics","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T15:47:47Z","title":"Dynamic benchmarking framework for LLM-based conversational data capture"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04349","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":"sha256:148d6b0192bcfe335093d8f2b2ce9e0eb9a73338a832c583c667c7bf5c4f1a67","target":"record","created_at":"2026-07-05T10:10:50Z","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":"1361b87e240a6667db0df27b274927020553e3c10f8b59760cc64bf48fac67ff","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T15:47:47Z","title_canon_sha256":"b3fc482542917383cb0b567526a09ca13b9bf2e4582ed59cf6cab623c145e0bc"},"schema_version":"1.0","source":{"id":"2502.04349","kind":"arxiv","version":1}},"canonical_sha256":"3e398524c53df138647bd6cc9adf9e71111fc2f0902e1ba66f8a266bf74fddb5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e398524c53df138647bd6cc9adf9e71111fc2f0902e1ba66f8a266bf74fddb5","first_computed_at":"2026-07-05T10:10:50.072920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:50.072920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FUYv7CZQln0jPtc455xMF8+qHjEbi2d1wiuONRTxc/YFcPf0VQ7xnICsjkK+tkL6WjZyg6fUSpI7UgOJDy6XCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:50.073382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04349","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:148d6b0192bcfe335093d8f2b2ce9e0eb9a73338a832c583c667c7bf5c4f1a67","sha256:ae1b62fa5764e3f8eb990b0fe38f36f70c0ff7672938ce92be5ba09b4b38a907"],"state_sha256":"d145e955bf258cf9299ca31588dec55355be37a63503c241f8687902dd097438"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6mNKOGPFrLmCdiMBRM7NkeM43PgL0FyyUzU8xc2tP57J3EabxA5CLJLObQWZr1so/kk0IQ4IOpEufbH53hnLCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T07:39:20.703870Z","bundle_sha256":"4efe81b0f44e7b085210d7f5cb4d8a01972a3934ac578f481e3a2fdb363af37d"}}