{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:W35LIN2S3RC4V4VLOIIVC3UJAV","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":"2c7b0f93b650d6ae195254120b6960ba7672ef726c1cdc8dbebf701b904ef135","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"physics.bio-ph","submitted_at":"2026-05-15T13:19:26Z","title_canon_sha256":"a471c6d221b3f865599833e585ad0c893b127f8011ae63939b9e40f90ebe0af0"},"schema_version":"1.0","source":{"id":"2605.15938","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15938","created_at":"2026-05-20T00:01:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15938v1","created_at":"2026-05-20T00:01:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15938","created_at":"2026-05-20T00:01:45Z"},{"alias_kind":"pith_short_12","alias_value":"W35LIN2S3RC4","created_at":"2026-05-20T00:01:45Z"},{"alias_kind":"pith_short_16","alias_value":"W35LIN2S3RC4V4VL","created_at":"2026-05-20T00:01:45Z"},{"alias_kind":"pith_short_8","alias_value":"W35LIN2S","created_at":"2026-05-20T00:01:45Z"}],"graph_snapshots":[{"event_id":"sha256:7cc31213b534ce5ac5bf51807b5e24b58e55ca9c16db36ed48ec0edea22fdfec","target":"graph","created_at":"2026-05-20T00:01:45Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The agent learns an interpretable strategy to recover the plume which combines well-known behaviors observed in insects: surging, casting, and a return downwind. While achieving good performance on data from direct numerical simulations of turbulence, the agent is limited by an inability to adapt its strategy to the local intermittency level; we show that providing more flexibility improves robustness."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a single running clock since the last whiff supplies enough state information for tabular Q-learning to converge on a robust recovery policy across varying turbulence intermittency levels."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A tabular Q-learning agent with clock-state memory learns surging, casting, and downwind return to recover odor plumes in turbulent flows from direct numerical simulations."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A running clock since the last odor whiff lets a Q-learning agent learn surging, casting and downwind return to recover plumes in turbulence."}],"snapshot_sha256":"d06873dce44d5c6dd6c8ee82540c8be486836bb8b37b253b6982c6ab2983a20c"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T18:01:18.546166Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T17:36:25.318165Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:46.535698Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T17:01:55.729910Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.15938/integrity.json","findings":[],"snapshot_sha256":"f2865797bfd1b74c9ed1edd3c5e2968743a00d2094d1ce9cf191ae4a83de2e7b","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Finding an odor source in a turbulent flow requires effectively leveraging the history of olfactory observations into a robust navigation strategy. In this work, we use tabular Q-learning to train an olfactory search agent with a minimal memory of past observations: only a running clock since the last whiff. This agent learns an interpretable strategy to recover the plume which combines well-known behaviors observed in insects: surging, casting, and a return downwind. While achieving good performance on data from direct numerical simulations of turbulence, the agent is limited by an inability ","authors_text":"Agnese Seminara, Marco Rando, Robin A. Heinonen, Yujia Qi","cross_cats":["cs.LG"],"headline":"A running clock since the last odor whiff lets a Q-learning agent learn surging, casting and downwind return to recover plumes in turbulence.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"physics.bio-ph","submitted_at":"2026-05-15T13:19:26Z","title":"Clock-state olfactory search in turbulent flows using Q-learning: The geometry of plume recovery"},"references":{"count":46,"internal_anchors":0,"resolved_work":46,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Elementary sensory-motor transfor- mations underlying olfactory navigation in walking fruit- flies.Elife, 7:e37815, 2018","work_id":"c253cc45-23dc-450a-a57d-fd98320105f7","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"T. C. Baker. Upwind flight and casting flight: com- plementary and tonic systems used for location of sex pheromone sources by male moths.Proc. 10 th Intl Sym- posium on Olfaction and Taste, 13:18, 19","work_id":"eaad9319-4733-4e39-b5fe-24a127f2d19c","year":1990},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Manoeuvres used by flying male oriental fruit moths to relocate a sex pheromone plume in an experimentally shifted wind-field","work_id":"45ac64d6-f1aa-4aa9-a5de-6cdcb7e3b0a0","year":1987},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Olfactory search at high Reynolds number.Proceedings of the na- tional academy of sciences, 99(20):12589–12593, 2002","work_id":"79c1978c-57c3-4b8a-8e31-021445a2e6d7","year":2002},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"W. J. Bell and E. Kramer. Search and anemotaxis in insects.J. Insect Physiol, 25:631–640, 1979","work_id":"49638bd7-2d3b-442c-afef-2b87ad020902","year":1979}],"snapshot_sha256":"ede11630c2f807c9704fd9a236107e8b9ee810f8b699839dea5bc85cd5da3de3"},"source":{"id":"2605.15938","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T17:30:50.526306Z","id":"e726d64a-9753-48a2-84b2-f0a64a8e4495","model_set":{"reader":"grok-4.3"},"one_line_summary":"A tabular Q-learning agent with clock-state memory learns surging, casting, and downwind return to recover odor plumes in turbulent flows from direct numerical simulations.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A running clock since the last odor whiff lets a Q-learning agent learn surging, casting and downwind return to recover plumes in turbulence.","strongest_claim":"The agent learns an interpretable strategy to recover the plume which combines well-known behaviors observed in insects: surging, casting, and a return downwind. While achieving good performance on data from direct numerical simulations of turbulence, the agent is limited by an inability to adapt its strategy to the local intermittency level; we show that providing more flexibility improves robustness.","weakest_assumption":"That a single running clock since the last whiff supplies enough state information for tabular Q-learning to converge on a robust recovery policy across varying turbulence intermittency levels."}},"verdict_id":"e726d64a-9753-48a2-84b2-f0a64a8e4495"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7d8cc696ff8d78bacec186abf9a2d521604c5d4c92c3a2fd185ec1ebb7831dde","target":"record","created_at":"2026-05-20T00:01:45Z","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":"2c7b0f93b650d6ae195254120b6960ba7672ef726c1cdc8dbebf701b904ef135","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"physics.bio-ph","submitted_at":"2026-05-15T13:19:26Z","title_canon_sha256":"a471c6d221b3f865599833e585ad0c893b127f8011ae63939b9e40f90ebe0af0"},"schema_version":"1.0","source":{"id":"2605.15938","kind":"arxiv","version":1}},"canonical_sha256":"b6fab43752dc45caf2ab7211516e89055f5f55103f1c0f829a874d8db1ccff45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6fab43752dc45caf2ab7211516e89055f5f55103f1c0f829a874d8db1ccff45","first_computed_at":"2026-05-20T00:01:45.827183Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:45.827183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lzni6fymWeyPX4ljWkO4RUrXOgYT9R8k/lsEgiWwAXGTmtItSxWnMGBfgl61U5TZksoccTeZs/O435KRQS1GAQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:45.827734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15938","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d8cc696ff8d78bacec186abf9a2d521604c5d4c92c3a2fd185ec1ebb7831dde","sha256:7cc31213b534ce5ac5bf51807b5e24b58e55ca9c16db36ed48ec0edea22fdfec"],"state_sha256":"3ca8f4b21c86a8123876e037e5b30bac659ecab7837160cfacd02934314944ce"}