{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NJ7JATU3EC4XJNIRBDRXYPE3IJ","short_pith_number":"pith:NJ7JATU3","schema_version":"1.0","canonical_sha256":"6a7e904e9b20b974b51108e37c3c9b427e2847209a1c9bcd7d5bae997822f14f","source":{"kind":"arxiv","id":"2608.06595","version":1},"attestation_state":"computed","paper":{"title":"Flowing Through States: Neural ODE Regularization for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bernd Finkbeiner, Mohamed Ghanem","submitted_at":"2026-08-06T21:11:16Z","abstract_excerpt":"Neural networks applied to sequential decision-making tasks typically rely on latent representations of environment states. While environment dynamics dictate how semantic states evolve, the corresponding latent transitions are usually left implicit, creating a potential misalignment between the two. We propose to model latent dynamics explicitly by drawing an analogy between Markov decision process (MDP) trajectories and ordinary differential equation (ODE) flows: in both cases, the current state fully determines its successors. Building on this view, we introduce a neural ODE-based regulariz"},"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":"2608.06595","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T21:11:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"819c29f26d869ed813bfea1bbfca29f0b58b297dd66f3137c3872b333eb25f8d","abstract_canon_sha256":"5481c8371d90179707bfcd3674cb065a3237d8a3d3c2999744a21016f6f2c9bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:11:26.568195Z","signature_b64":"JcH6xelxuPCsw6V88iallB9thMzV3NWKNRUP/OvXcPX/PrB0jEjTlrvfkn5IrHBXk2okPbbOFJQEsDjUwpn2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a7e904e9b20b974b51108e37c3c9b427e2847209a1c9bcd7d5bae997822f14f","last_reissued_at":"2026-08-10T01:11:26.565695Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:11:26.565695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flowing Through States: Neural ODE Regularization for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bernd Finkbeiner, Mohamed Ghanem","submitted_at":"2026-08-06T21:11:16Z","abstract_excerpt":"Neural networks applied to sequential decision-making tasks typically rely on latent representations of environment states. While environment dynamics dictate how semantic states evolve, the corresponding latent transitions are usually left implicit, creating a potential misalignment between the two. We propose to model latent dynamics explicitly by drawing an analogy between Markov decision process (MDP) trajectories and ordinary differential equation (ODE) flows: in both cases, the current state fully determines its successors. Building on this view, we introduce a neural ODE-based regulariz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06595","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/2608.06595/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":"2608.06595","created_at":"2026-08-10T01:11:26.566757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06595v1","created_at":"2026-08-10T01:11:26.566757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06595","created_at":"2026-08-10T01:11:26.566757+00:00"},{"alias_kind":"pith_short_12","alias_value":"NJ7JATU3EC4X","created_at":"2026-08-10T01:11:26.566757+00:00"},{"alias_kind":"pith_short_16","alias_value":"NJ7JATU3EC4XJNIR","created_at":"2026-08-10T01:11:26.566757+00:00"},{"alias_kind":"pith_short_8","alias_value":"NJ7JATU3","created_at":"2026-08-10T01:11:26.566757+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/NJ7JATU3EC4XJNIRBDRXYPE3IJ","json":"https://pith.science/pith/NJ7JATU3EC4XJNIRBDRXYPE3IJ.json","graph_json":"https://pith.science/api/pith-number/NJ7JATU3EC4XJNIRBDRXYPE3IJ/graph.json","events_json":"https://pith.science/api/pith-number/NJ7JATU3EC4XJNIRBDRXYPE3IJ/events.json","paper":"https://pith.science/paper/NJ7JATU3"},"agent_actions":{"view_html":"https://pith.science/pith/NJ7JATU3EC4XJNIRBDRXYPE3IJ","download_json":"https://pith.science/pith/NJ7JATU3EC4XJNIRBDRXYPE3IJ.json","view_paper":"https://pith.science/paper/NJ7JATU3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06595&json=true","fetch_graph":"https://pith.science/api/pith-number/NJ7JATU3EC4XJNIRBDRXYPE3IJ/graph.json","fetch_events":"https://pith.science/api/pith-number/NJ7JATU3EC4XJNIRBDRXYPE3IJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NJ7JATU3EC4XJNIRBDRXYPE3IJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NJ7JATU3EC4XJNIRBDRXYPE3IJ/action/storage_attestation","attest_author":"https://pith.science/pith/NJ7JATU3EC4XJNIRBDRXYPE3IJ/action/author_attestation","sign_citation":"https://pith.science/pith/NJ7JATU3EC4XJNIRBDRXYPE3IJ/action/citation_signature","submit_replication":"https://pith.science/pith/NJ7JATU3EC4XJNIRBDRXYPE3IJ/action/replication_record"}},"created_at":"2026-08-10T01:11:26.566757+00:00","updated_at":"2026-08-10T01:11:26.566757+00:00"}