{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UXIAYISG3ESZTRIOQCLUTODVVP","short_pith_number":"pith:UXIAYISG","schema_version":"1.0","canonical_sha256":"a5d00c2246d92599c50e809749b875abd8a4fd47e60628772bbd221eac07ad63","source":{"kind":"arxiv","id":"2602.02806","version":3},"attestation_state":"computed","paper":{"title":"De-Linearizing Agent Traces: Bayesian Inference of Latent Partial Orders for Efficient Execution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Dongqing Li, Geoff K. Nicholls, Quyu Kong, Zheqiao Cheng","submitted_at":"2026-02-02T21:03:30Z","abstract_excerpt":"AI agents increasingly execute procedural workflows as sequential action traces, which obscures latent concurrency and induces repeated step-by-step reasoning. We introduce BPOP, a Bayesianframework that infers a latent dependency partial order from noisy linearized traces. BPOP models traces as stochastic linear extensions of an underlying graph and performs efficient MCMC inference via a tractable frontier-softmax likelihood that avoids #P-hard marginalization over linear extensions. We evaluate on our open-sourced Cloud-IaC-6, a suite of cloud provisioning tasks with heterogeneous LLM-gener"},"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":"2602.02806","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2026-02-02T21:03:30Z","cross_cats_sorted":[],"title_canon_sha256":"adab29b638e396c358cff5d60b778c640389d44914335de751c1d3e172d8566f","abstract_canon_sha256":"c7846fac3a28da8b6df7c1038ed69dee7daf26b8999c2daef260e07a18ebd4cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:04.505942Z","signature_b64":"aFlasm/5Gl3/+6ucJmx825VA/5Jd3axKod3T1iQ42KQ/I9JNh4OOS4oszjEIDpc7X2Q5b+Q61WuTpPbzhIAYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5d00c2246d92599c50e809749b875abd8a4fd47e60628772bbd221eac07ad63","last_reissued_at":"2026-05-26T02:04:04.505224Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:04.505224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"De-Linearizing Agent Traces: Bayesian Inference of Latent Partial Orders for Efficient Execution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Dongqing Li, Geoff K. Nicholls, Quyu Kong, Zheqiao Cheng","submitted_at":"2026-02-02T21:03:30Z","abstract_excerpt":"AI agents increasingly execute procedural workflows as sequential action traces, which obscures latent concurrency and induces repeated step-by-step reasoning. We introduce BPOP, a Bayesianframework that infers a latent dependency partial order from noisy linearized traces. BPOP models traces as stochastic linear extensions of an underlying graph and performs efficient MCMC inference via a tractable frontier-softmax likelihood that avoids #P-hard marginalization over linear extensions. We evaluate on our open-sourced Cloud-IaC-6, a suite of cloud provisioning tasks with heterogeneous LLM-gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02806","kind":"arxiv","version":3},"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/2602.02806/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":"2602.02806","created_at":"2026-05-26T02:04:04.505327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.02806v3","created_at":"2026-05-26T02:04:04.505327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02806","created_at":"2026-05-26T02:04:04.505327+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXIAYISG3ESZ","created_at":"2026-05-26T02:04:04.505327+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXIAYISG3ESZTRIO","created_at":"2026-05-26T02:04:04.505327+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXIAYISG","created_at":"2026-05-26T02:04:04.505327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.06976","citing_title":"A Differentiable Bayesian Relaxation for Latent Partial-Order Inference","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UXIAYISG3ESZTRIOQCLUTODVVP","json":"https://pith.science/pith/UXIAYISG3ESZTRIOQCLUTODVVP.json","graph_json":"https://pith.science/api/pith-number/UXIAYISG3ESZTRIOQCLUTODVVP/graph.json","events_json":"https://pith.science/api/pith-number/UXIAYISG3ESZTRIOQCLUTODVVP/events.json","paper":"https://pith.science/paper/UXIAYISG"},"agent_actions":{"view_html":"https://pith.science/pith/UXIAYISG3ESZTRIOQCLUTODVVP","download_json":"https://pith.science/pith/UXIAYISG3ESZTRIOQCLUTODVVP.json","view_paper":"https://pith.science/paper/UXIAYISG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.02806&json=true","fetch_graph":"https://pith.science/api/pith-number/UXIAYISG3ESZTRIOQCLUTODVVP/graph.json","fetch_events":"https://pith.science/api/pith-number/UXIAYISG3ESZTRIOQCLUTODVVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXIAYISG3ESZTRIOQCLUTODVVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXIAYISG3ESZTRIOQCLUTODVVP/action/storage_attestation","attest_author":"https://pith.science/pith/UXIAYISG3ESZTRIOQCLUTODVVP/action/author_attestation","sign_citation":"https://pith.science/pith/UXIAYISG3ESZTRIOQCLUTODVVP/action/citation_signature","submit_replication":"https://pith.science/pith/UXIAYISG3ESZTRIOQCLUTODVVP/action/replication_record"}},"created_at":"2026-05-26T02:04:04.505327+00:00","updated_at":"2026-05-26T02:04:04.505327+00:00"}