{"paper":{"title":"Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"DySIB recovers the two-dimensional phase space of a pendulum from high-dimensional video data by maximizing predictive mutual information in latent space.","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"physics.data-an","authors_text":"Eslam Abdelaleem, Ilya Nemenman, K. Michael Martini, Paarth Gulati","submitted_at":"2026-04-27T16:24:45Z","abstract_excerpt":"Identifying the dynamical state variables of a system from high-dimensional observations is a central problem across physical sciences. The challenge is that the state variables are not directly observable and must be inferred from raw high-dimensional data without supervision. Here we introduce DySIB (Dynamical Symmetric Information Bottleneck) as a method to learn low-dimensional representations of time-series data by maximizing predictive mutual information between past and future observation windows while penalizing representation complexity. This objective operates entirely in latent spac"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The method, with hyperparameters of the learning architecture set self-consistently by the data, recovers a two-dimensional representation that matches the dimensionality, topology, and geometry of the pendulum phase space, with the learned coordinates aligning smoothly with the canonical angle and angular velocity.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That maximizing predictive mutual information between past and future observation windows in latent space is sufficient to recover the true underlying dynamical state variables without additional supervision or reconstruction.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DySIB recovers a two-dimensional representation matching the phase space of a physical pendulum from high-dimensional video data by maximizing predictive mutual information in latent space.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"DySIB recovers the two-dimensional phase space of a pendulum from high-dimensional video data by maximizing predictive mutual information in latent space.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5019af967f58abac85dd826f8832f5b1347dfacc5cbcf43b5133d098136a6013"},"source":{"id":"2604.24662","kind":"arxiv","version":2},"verdict":{"id":"32404756-0bdf-4287-80e9-e86701de331a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T16:59:02.162121Z","strongest_claim":"The method, with hyperparameters of the learning architecture set self-consistently by the data, recovers a two-dimensional representation that matches the dimensionality, topology, and geometry of the pendulum phase space, with the learned coordinates aligning smoothly with the canonical angle and angular velocity.","one_line_summary":"DySIB recovers a two-dimensional representation matching the phase space of a physical pendulum from high-dimensional video data by maximizing predictive mutual information in latent space.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That maximizing predictive mutual information between past and future observation windows in latent space is sufficient to recover the true underlying dynamical state variables without additional supervision or reconstruction.","pith_extraction_headline":"DySIB recovers the two-dimensional phase space of a pendulum from high-dimensional video data by maximizing predictive mutual information in latent space."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.24662/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T06:36:08.062119Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T21:52:49.776024Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"11a3a5fecc67573e46b5de181691f51c39abf62c23eb1236bc9131a89c142545"},"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"}