{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TYLGOZM72PIF3LXQIRCEGGDXFZ","short_pith_number":"pith:TYLGOZM7","schema_version":"1.0","canonical_sha256":"9e1667659fd3d05daef044444318772e46f8f879ab899258ec382300aee736ed","source":{"kind":"arxiv","id":"2606.28751","version":1},"attestation_state":"computed","paper":{"title":"A Path-Space Formulation of Prediction in World Models: From a Single Action to Prediction, Planning, and Irreversibility","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech"],"primary_cat":"cs.LG","authors_text":"Gunn Kim","submitted_at":"2026-06-27T06:00:09Z","abstract_excerpt":"We propose a path-space formulation of prediction in AI world models. Rather than sequences of one-step conditional distributions, we argue that a world model implicitly defines a probability measure over future trajectories. In the local regime where latent dynamics admit an effective Markovian description, this path measure takes the Onsager-Machlup form. Within this framework, prediction (most probable trajectory), planning (constrained optimization), and uncertainty (fluctuations) emerge as operations on a single action functional. We decompose the latent dynamics into reversible and irrev"},"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":"2606.28751","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-27T06:00:09Z","cross_cats_sorted":["cond-mat.stat-mech"],"title_canon_sha256":"141b9d7622bae7051ab7d0bdf9bf2226e923c95ccc4cfab40cb26cc4ea91bdc6","abstract_canon_sha256":"549f6c97b11e19da04b81c875de0f4164fa983567d1d40d1376824ed2c4384ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:50.341653Z","signature_b64":"MfPqFc49hA5+tuXf6dyoVwLYBJMGMR/jDlNQYb9dv7HgLg2aKnduaK7xhpDhi8qs1Lh8fB2q1YTqBSylEuIlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e1667659fd3d05daef044444318772e46f8f879ab899258ec382300aee736ed","last_reissued_at":"2026-06-30T01:16:50.340855Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:50.340855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Path-Space Formulation of Prediction in World Models: From a Single Action to Prediction, Planning, and Irreversibility","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech"],"primary_cat":"cs.LG","authors_text":"Gunn Kim","submitted_at":"2026-06-27T06:00:09Z","abstract_excerpt":"We propose a path-space formulation of prediction in AI world models. Rather than sequences of one-step conditional distributions, we argue that a world model implicitly defines a probability measure over future trajectories. In the local regime where latent dynamics admit an effective Markovian description, this path measure takes the Onsager-Machlup form. Within this framework, prediction (most probable trajectory), planning (constrained optimization), and uncertainty (fluctuations) emerge as operations on a single action functional. We decompose the latent dynamics into reversible and irrev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28751","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/2606.28751/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":"2606.28751","created_at":"2026-06-30T01:16:50.340986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28751v1","created_at":"2026-06-30T01:16:50.340986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28751","created_at":"2026-06-30T01:16:50.340986+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYLGOZM72PIF","created_at":"2026-06-30T01:16:50.340986+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYLGOZM72PIF3LXQ","created_at":"2026-06-30T01:16:50.340986+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYLGOZM7","created_at":"2026-06-30T01:16:50.340986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.02154","citing_title":"Path-Measure Dynamics of Attention-Driven World Models: A Nonlocal Onsager--Machlup Approach","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYLGOZM72PIF3LXQIRCEGGDXFZ","json":"https://pith.science/pith/TYLGOZM72PIF3LXQIRCEGGDXFZ.json","graph_json":"https://pith.science/api/pith-number/TYLGOZM72PIF3LXQIRCEGGDXFZ/graph.json","events_json":"https://pith.science/api/pith-number/TYLGOZM72PIF3LXQIRCEGGDXFZ/events.json","paper":"https://pith.science/paper/TYLGOZM7"},"agent_actions":{"view_html":"https://pith.science/pith/TYLGOZM72PIF3LXQIRCEGGDXFZ","download_json":"https://pith.science/pith/TYLGOZM72PIF3LXQIRCEGGDXFZ.json","view_paper":"https://pith.science/paper/TYLGOZM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28751&json=true","fetch_graph":"https://pith.science/api/pith-number/TYLGOZM72PIF3LXQIRCEGGDXFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TYLGOZM72PIF3LXQIRCEGGDXFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYLGOZM72PIF3LXQIRCEGGDXFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYLGOZM72PIF3LXQIRCEGGDXFZ/action/storage_attestation","attest_author":"https://pith.science/pith/TYLGOZM72PIF3LXQIRCEGGDXFZ/action/author_attestation","sign_citation":"https://pith.science/pith/TYLGOZM72PIF3LXQIRCEGGDXFZ/action/citation_signature","submit_replication":"https://pith.science/pith/TYLGOZM72PIF3LXQIRCEGGDXFZ/action/replication_record"}},"created_at":"2026-06-30T01:16:50.340986+00:00","updated_at":"2026-06-30T01:16:50.340986+00:00"}