{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6BYZOIHVWZLLXCVRAGWGAOFA7F","short_pith_number":"pith:6BYZOIHV","schema_version":"1.0","canonical_sha256":"f0719720f5b656bb8ab101ac6038a0f9497ee77ea491cec14660b427c3de7ca6","source":{"kind":"arxiv","id":"2604.24662","version":2},"attestation_state":"computed","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"},"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":"2604.24662","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.data-an","submitted_at":"2026-04-27T16:24:45Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"8e83c44754c65cf3e1edfeec4779d7c919f1d685b9eee7f61522ce51b637311f","abstract_canon_sha256":"8383d205a8deddba83bdb939606d16a6d4deff35d3165643c8340052c8f2213d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:36.690216Z","signature_b64":"imTkNn9qM8q1E9lE2rnkrHL4TGjCpdCCRpKNiRPLFNFfduJmGJT+tIts8wIB+lwh/WyVU4D1goZB3nsi3OepCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0719720f5b656bb8ab101ac6038a0f9497ee77ea491cec14660b427c3de7ca6","last_reissued_at":"2026-06-11T01:10:36.689383Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:36.689383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.24662","created_at":"2026-06-11T01:10:36.689510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.24662v2","created_at":"2026-06-11T01:10:36.689510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.24662","created_at":"2026-06-11T01:10:36.689510+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BYZOIHVWZLL","created_at":"2026-06-11T01:10:36.689510+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BYZOIHVWZLLXCVR","created_at":"2026-06-11T01:10:36.689510+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BYZOIHV","created_at":"2026-06-11T01:10:36.689510+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.07770","citing_title":"Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6BYZOIHVWZLLXCVRAGWGAOFA7F","json":"https://pith.science/pith/6BYZOIHVWZLLXCVRAGWGAOFA7F.json","graph_json":"https://pith.science/api/pith-number/6BYZOIHVWZLLXCVRAGWGAOFA7F/graph.json","events_json":"https://pith.science/api/pith-number/6BYZOIHVWZLLXCVRAGWGAOFA7F/events.json","paper":"https://pith.science/paper/6BYZOIHV"},"agent_actions":{"view_html":"https://pith.science/pith/6BYZOIHVWZLLXCVRAGWGAOFA7F","download_json":"https://pith.science/pith/6BYZOIHVWZLLXCVRAGWGAOFA7F.json","view_paper":"https://pith.science/paper/6BYZOIHV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.24662&json=true","fetch_graph":"https://pith.science/api/pith-number/6BYZOIHVWZLLXCVRAGWGAOFA7F/graph.json","fetch_events":"https://pith.science/api/pith-number/6BYZOIHVWZLLXCVRAGWGAOFA7F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BYZOIHVWZLLXCVRAGWGAOFA7F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BYZOIHVWZLLXCVRAGWGAOFA7F/action/storage_attestation","attest_author":"https://pith.science/pith/6BYZOIHVWZLLXCVRAGWGAOFA7F/action/author_attestation","sign_citation":"https://pith.science/pith/6BYZOIHVWZLLXCVRAGWGAOFA7F/action/citation_signature","submit_replication":"https://pith.science/pith/6BYZOIHVWZLLXCVRAGWGAOFA7F/action/replication_record"}},"created_at":"2026-06-11T01:10:36.689510+00:00","updated_at":"2026-06-11T01:10:36.689510+00:00"}