{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UDTFEBXBTWBUSFLNZWJGPRB7MY","short_pith_number":"pith:UDTFEBXB","schema_version":"1.0","canonical_sha256":"a0e65206e19d8349156dcd9267c43f661e6bc259fe80b7d4233824f69c6cb24c","source":{"kind":"arxiv","id":"2605.08550","version":3},"attestation_state":"computed","paper":{"title":"A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Wasserstein Lagrangian Mechanics learns second-order population dynamics directly from observed marginals without specifying the Lagrangian.","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kirill Neklyudov, Lazar Atanackovic, Vincent Guan","submitted_at":"2026-05-08T23:21:17Z","abstract_excerpt":"The population dynamics of molecules, cells, and organisms are governed by a number of unknown forces. In the last decade, population dynamics have predominantly been modeled with Wasserstein gradient flows. However, since gradient flows minimize free energy, they fail to capture important dynamical properties, such as periodicity. In this work, we propose a change in perspective by considering dynamics that minimize a population-level action under a damped Wasserstein Lagrangian. By deriving the corresponding Hamiltonian equations of motion, we formalize Wasserstein Lagrangian Mechanics, a st"},"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":"2605.08550","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-08T23:21:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0e2e0c5b3586732c24850c70092404de1885fdf22d04331e593d3f0538b663c3","abstract_canon_sha256":"a6c75cadde9fda76efe73c240afb120e90fc11055778cb8b6a39ecb8df7af207"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:15.292570Z","signature_b64":"c6OJEg+uxsSFLUEDsfBXbGdh20gaIjuhdmsnaxulzN3xvX4ZS7cGhyvrY6cp7F2+OtvYYi0/qWbNrdVTMdNkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0e65206e19d8349156dcd9267c43f661e6bc259fe80b7d4233824f69c6cb24c","last_reissued_at":"2026-05-20T00:03:15.291626Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:15.291626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Wasserstein Lagrangian Mechanics learns second-order population dynamics directly from observed marginals without specifying the Lagrangian.","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kirill Neklyudov, Lazar Atanackovic, Vincent Guan","submitted_at":"2026-05-08T23:21:17Z","abstract_excerpt":"The population dynamics of molecules, cells, and organisms are governed by a number of unknown forces. In the last decade, population dynamics have predominantly been modeled with Wasserstein gradient flows. However, since gradient flows minimize free energy, they fail to capture important dynamical properties, such as periodicity. In this work, we propose a change in perspective by considering dynamics that minimize a population-level action under a damped Wasserstein Lagrangian. By deriving the corresponding Hamiltonian equations of motion, we formalize Wasserstein Lagrangian Mechanics, a st"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"WLM is the first algorithm that learns these second-order dynamics from observed marginals, without specifying the Lagrangian.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That population dynamics of interest can be accurately described as minimizing a population-level action under a damped Wasserstein Lagrangian.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Wasserstein Lagrangian Mechanics learns second-order population dynamics from observed marginals without specifying the Lagrangian and outperforms gradient flow methods on periodic dynamics like vortex motion and flocking.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Wasserstein Lagrangian Mechanics learns second-order population dynamics directly from observed marginals without specifying the Lagrangian.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b6e6483e0e25d2e324625b425f2d6b7ff91a9345c4c3e8c00c4eb54abfedee29"},"source":{"id":"2605.08550","kind":"arxiv","version":3},"verdict":{"id":"25229518-598b-47e7-bce4-a4f253befcca","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:46:01.086949Z","strongest_claim":"WLM is the first algorithm that learns these second-order dynamics from observed marginals, without specifying the Lagrangian.","one_line_summary":"Wasserstein Lagrangian Mechanics learns second-order population dynamics from observed marginals without specifying the Lagrangian and outperforms gradient flow methods on periodic dynamics like vortex motion and flocking.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That population dynamics of interest can be accurately described as minimizing a population-level action under a damped Wasserstein Lagrangian.","pith_extraction_headline":"Wasserstein Lagrangian Mechanics learns second-order population dynamics directly from observed marginals without specifying the Lagrangian."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.08550/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T14:31:18.434325Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T11:00:22.932878Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"f161d9a0add4443c13e337bdd08fa1db19dd8598332a9e51c8cdd5702f6053b0"},"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":"2605.08550","created_at":"2026-05-20T00:03:15.291753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.08550v3","created_at":"2026-05-20T00:03:15.291753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08550","created_at":"2026-05-20T00:03:15.291753+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDTFEBXBTWBU","created_at":"2026-05-20T00:03:15.291753+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDTFEBXBTWBUSFLN","created_at":"2026-05-20T00:03:15.291753+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDTFEBXB","created_at":"2026-05-20T00:03:15.291753+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/UDTFEBXBTWBUSFLNZWJGPRB7MY","json":"https://pith.science/pith/UDTFEBXBTWBUSFLNZWJGPRB7MY.json","graph_json":"https://pith.science/api/pith-number/UDTFEBXBTWBUSFLNZWJGPRB7MY/graph.json","events_json":"https://pith.science/api/pith-number/UDTFEBXBTWBUSFLNZWJGPRB7MY/events.json","paper":"https://pith.science/paper/UDTFEBXB"},"agent_actions":{"view_html":"https://pith.science/pith/UDTFEBXBTWBUSFLNZWJGPRB7MY","download_json":"https://pith.science/pith/UDTFEBXBTWBUSFLNZWJGPRB7MY.json","view_paper":"https://pith.science/paper/UDTFEBXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.08550&json=true","fetch_graph":"https://pith.science/api/pith-number/UDTFEBXBTWBUSFLNZWJGPRB7MY/graph.json","fetch_events":"https://pith.science/api/pith-number/UDTFEBXBTWBUSFLNZWJGPRB7MY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDTFEBXBTWBUSFLNZWJGPRB7MY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDTFEBXBTWBUSFLNZWJGPRB7MY/action/storage_attestation","attest_author":"https://pith.science/pith/UDTFEBXBTWBUSFLNZWJGPRB7MY/action/author_attestation","sign_citation":"https://pith.science/pith/UDTFEBXBTWBUSFLNZWJGPRB7MY/action/citation_signature","submit_replication":"https://pith.science/pith/UDTFEBXBTWBUSFLNZWJGPRB7MY/action/replication_record"}},"created_at":"2026-05-20T00:03:15.291753+00:00","updated_at":"2026-05-20T00:03:15.291753+00:00"}