{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:53BPAAPVG7YNLUOQQVOV2KI4BY","short_pith_number":"pith:53BPAAPV","schema_version":"1.0","canonical_sha256":"eec2f001f537f0d5d1d0855d5d291c0e24cdfc268b073a193a4137b7376c9773","source":{"kind":"arxiv","id":"2606.01725","version":1},"attestation_state":"computed","paper":{"title":"Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simulation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Donghwan Kim, Jongryool Kim, Jongse Park, Kiwan Maeng, Prakhar Singh, Younghoon Min","submitted_at":"2026-06-01T05:43:16Z","abstract_excerpt":"Agentic AI completes tasks through iterative planning, tool use, and reasoning based on observed outcomes. Despite its popularity, its system-level behavior remains poorly understood, particularly for complex datasets and agent architectures-owing to highly non-deterministic execution, prohibitive evaluation costs, and limited visibility into proprietary models. This paper presents GAIATrace, the first token-level trace dataset of two state-of-the-art agentic systems (MiroThinker and OWL) running GAIA, a benchmark composed of a heterogeneous mix of general-purpose tasks. Unlike prior trace dat"},"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":"2606.01725","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T05:43:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a9989519822b17d85db72ece1912b381aa27c4ede7bf08d8e24bdbe3bdf9f1c2","abstract_canon_sha256":"56deede2105ba64e58dc433bdc43b5b0fc947b482f41d1bdee23bbd869827424"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:55.112602Z","signature_b64":"b7hWUSS4O4zOCGjhlW9UjTI4O+mkK7UDTK9YV+VfuFdZ5OY/bCCwbIjip9mf2aIvRm5lYRTNNQDGaX1M+gu3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eec2f001f537f0d5d1d0855d5d291c0e24cdfc268b073a193a4137b7376c9773","last_reissued_at":"2026-06-02T02:04:55.112104Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:55.112104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simulation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Donghwan Kim, Jongryool Kim, Jongse Park, Kiwan Maeng, Prakhar Singh, Younghoon Min","submitted_at":"2026-06-01T05:43:16Z","abstract_excerpt":"Agentic AI completes tasks through iterative planning, tool use, and reasoning based on observed outcomes. Despite its popularity, its system-level behavior remains poorly understood, particularly for complex datasets and agent architectures-owing to highly non-deterministic execution, prohibitive evaluation costs, and limited visibility into proprietary models. This paper presents GAIATrace, the first token-level trace dataset of two state-of-the-art agentic systems (MiroThinker and OWL) running GAIA, a benchmark composed of a heterogeneous mix of general-purpose tasks. Unlike prior trace dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01725","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/2606.01725/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":"2606.01725","created_at":"2026-06-02T02:04:55.112164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01725v1","created_at":"2026-06-02T02:04:55.112164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01725","created_at":"2026-06-02T02:04:55.112164+00:00"},{"alias_kind":"pith_short_12","alias_value":"53BPAAPVG7YN","created_at":"2026-06-02T02:04:55.112164+00:00"},{"alias_kind":"pith_short_16","alias_value":"53BPAAPVG7YNLUOQ","created_at":"2026-06-02T02:04:55.112164+00:00"},{"alias_kind":"pith_short_8","alias_value":"53BPAAPV","created_at":"2026-06-02T02:04:55.112164+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/53BPAAPVG7YNLUOQQVOV2KI4BY","json":"https://pith.science/pith/53BPAAPVG7YNLUOQQVOV2KI4BY.json","graph_json":"https://pith.science/api/pith-number/53BPAAPVG7YNLUOQQVOV2KI4BY/graph.json","events_json":"https://pith.science/api/pith-number/53BPAAPVG7YNLUOQQVOV2KI4BY/events.json","paper":"https://pith.science/paper/53BPAAPV"},"agent_actions":{"view_html":"https://pith.science/pith/53BPAAPVG7YNLUOQQVOV2KI4BY","download_json":"https://pith.science/pith/53BPAAPVG7YNLUOQQVOV2KI4BY.json","view_paper":"https://pith.science/paper/53BPAAPV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01725&json=true","fetch_graph":"https://pith.science/api/pith-number/53BPAAPVG7YNLUOQQVOV2KI4BY/graph.json","fetch_events":"https://pith.science/api/pith-number/53BPAAPVG7YNLUOQQVOV2KI4BY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53BPAAPVG7YNLUOQQVOV2KI4BY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53BPAAPVG7YNLUOQQVOV2KI4BY/action/storage_attestation","attest_author":"https://pith.science/pith/53BPAAPVG7YNLUOQQVOV2KI4BY/action/author_attestation","sign_citation":"https://pith.science/pith/53BPAAPVG7YNLUOQQVOV2KI4BY/action/citation_signature","submit_replication":"https://pith.science/pith/53BPAAPVG7YNLUOQQVOV2KI4BY/action/replication_record"}},"created_at":"2026-06-02T02:04:55.112164+00:00","updated_at":"2026-06-02T02:04:55.112164+00:00"}