{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NHDTNCCPYZQMQVE27SG6SKEICF","short_pith_number":"pith:NHDTNCCP","schema_version":"1.0","canonical_sha256":"69c736884fc660c8549afc8de92888116b291627bc82816907f74c2b63dcb970","source":{"kind":"arxiv","id":"2606.20104","version":1},"attestation_state":"computed","paper":{"title":"Sensorimotor World Models: Perception for Action via Inverse Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bernhard Sch\\\"olkopf, Petr Ivashkov, Randall Balestriero","submitted_at":"2026-06-18T11:25:16Z","abstract_excerpt":"Perception for action suggests that representations of the world should be shaped not by visual fidelity alone, but by their relevance for actions. At the same time, latent JEPA-style world models advocate learning compact predictive states from high-dimensional observations to facilitate the prediction of future states, but end-to-end training of these models is nontrivial because representations may collapse if our only goal is to construct a latent state that is easy to predict. We introduce a sensorimotor world model (SMWM): a latent world model trained end-to-end with inverse dynamics reg"},"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":"2606.20104","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-18T11:25:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"29f90f16c5cd1d7ebeda644e098643da10a5a069b2f57e79b1a5d6966718f47f","abstract_canon_sha256":"26cb55ed825bb25eb700eb186b1e4427a107b58e9a6feb08d4f6956a46e4b2f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:02.964185Z","signature_b64":"TsVBuLsL38n7ONwhB1tp41hopFGJYQ8QFmPljczkTAXufAVwU/98MIaTz1Ob2xV+Kb+ThJ6D4144fwjGmXmhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69c736884fc660c8549afc8de92888116b291627bc82816907f74c2b63dcb970","last_reissued_at":"2026-06-19T16:13:02.963834Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:02.963834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sensorimotor World Models: Perception for Action via Inverse Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bernhard Sch\\\"olkopf, Petr Ivashkov, Randall Balestriero","submitted_at":"2026-06-18T11:25:16Z","abstract_excerpt":"Perception for action suggests that representations of the world should be shaped not by visual fidelity alone, but by their relevance for actions. At the same time, latent JEPA-style world models advocate learning compact predictive states from high-dimensional observations to facilitate the prediction of future states, but end-to-end training of these models is nontrivial because representations may collapse if our only goal is to construct a latent state that is easy to predict. We introduce a sensorimotor world model (SMWM): a latent world model trained end-to-end with inverse dynamics reg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20104","kind":"arxiv","version":1},"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/2606.20104/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":"2606.20104","created_at":"2026-06-19T16:13:02.963896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20104v1","created_at":"2026-06-19T16:13:02.963896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20104","created_at":"2026-06-19T16:13:02.963896+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHDTNCCPYZQM","created_at":"2026-06-19T16:13:02.963896+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHDTNCCPYZQMQVE2","created_at":"2026-06-19T16:13:02.963896+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHDTNCCP","created_at":"2026-06-19T16:13:02.963896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.30068","citing_title":"Predictive Objectives Discard Exogenous Control-Relevant Features: A Controlled Mechanistic Study","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHDTNCCPYZQMQVE27SG6SKEICF","json":"https://pith.science/pith/NHDTNCCPYZQMQVE27SG6SKEICF.json","graph_json":"https://pith.science/api/pith-number/NHDTNCCPYZQMQVE27SG6SKEICF/graph.json","events_json":"https://pith.science/api/pith-number/NHDTNCCPYZQMQVE27SG6SKEICF/events.json","paper":"https://pith.science/paper/NHDTNCCP"},"agent_actions":{"view_html":"https://pith.science/pith/NHDTNCCPYZQMQVE27SG6SKEICF","download_json":"https://pith.science/pith/NHDTNCCPYZQMQVE27SG6SKEICF.json","view_paper":"https://pith.science/paper/NHDTNCCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20104&json=true","fetch_graph":"https://pith.science/api/pith-number/NHDTNCCPYZQMQVE27SG6SKEICF/graph.json","fetch_events":"https://pith.science/api/pith-number/NHDTNCCPYZQMQVE27SG6SKEICF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHDTNCCPYZQMQVE27SG6SKEICF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHDTNCCPYZQMQVE27SG6SKEICF/action/storage_attestation","attest_author":"https://pith.science/pith/NHDTNCCPYZQMQVE27SG6SKEICF/action/author_attestation","sign_citation":"https://pith.science/pith/NHDTNCCPYZQMQVE27SG6SKEICF/action/citation_signature","submit_replication":"https://pith.science/pith/NHDTNCCPYZQMQVE27SG6SKEICF/action/replication_record"}},"created_at":"2026-06-19T16:13:02.963896+00:00","updated_at":"2026-06-19T16:13:02.963896+00:00"}