{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:A2QJYIRZCW7DYJPUALTGS576UI","short_pith_number":"pith:A2QJYIRZ","schema_version":"1.0","canonical_sha256":"06a09c223915be3c25f402e66977fea220ac009f8367038db710e628eb66db8a","source":{"kind":"arxiv","id":"2605.26998","version":1},"attestation_state":"computed","paper":{"title":"Probabilistic Recurrent Intention Switching Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.NC"],"primary_cat":"cs.LG","authors_text":"Hao Zhu, Joschka Boedecker, Wenyuan Sheng","submitted_at":"2026-05-26T13:19:00Z","abstract_excerpt":"Inverse reinforcement learning (IRL) recovers reward functions from observed behavior, yet traditional methods assume a single stationary reward that cannot capture goal switching within an episode. Recent multi-intention IRL methods address this by segmenting trajectories, but model intention transitions as either a memoryless Markov chain or via manual state augmentation with a fixed history window. We propose the Probabilistic Recurrent Intention Switching Model (PRISM), which replaces both mechanisms with a lightweight recurrent network that maps observation history to a per-step intention"},"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":"2605.26998","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T13:19:00Z","cross_cats_sorted":["q-bio.NC"],"title_canon_sha256":"d2d6befda8a930722167695ad24d9108ecbd85df22212fdbb291cacd0cbc6be4","abstract_canon_sha256":"a36209fe4343ad1d276f2812b2be6d6cca5dc0d7a5d7db6eabc6c14fbe021188"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:23.492010Z","signature_b64":"bHGM2ZL/fvPGbbgzvpNj8/pqtZPgkpStvdjNbVTFuPWkiyXEp8azZuseYXWEjvZ+/jcoX8YVXoKCPaHOpBcbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06a09c223915be3c25f402e66977fea220ac009f8367038db710e628eb66db8a","last_reissued_at":"2026-05-27T01:06:23.491509Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:23.491509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic Recurrent Intention Switching Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.NC"],"primary_cat":"cs.LG","authors_text":"Hao Zhu, Joschka Boedecker, Wenyuan Sheng","submitted_at":"2026-05-26T13:19:00Z","abstract_excerpt":"Inverse reinforcement learning (IRL) recovers reward functions from observed behavior, yet traditional methods assume a single stationary reward that cannot capture goal switching within an episode. Recent multi-intention IRL methods address this by segmenting trajectories, but model intention transitions as either a memoryless Markov chain or via manual state augmentation with a fixed history window. We propose the Probabilistic Recurrent Intention Switching Model (PRISM), which replaces both mechanisms with a lightweight recurrent network that maps observation history to a per-step intention"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26998","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/2605.26998/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":"2605.26998","created_at":"2026-05-27T01:06:23.491581+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26998v1","created_at":"2026-05-27T01:06:23.491581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26998","created_at":"2026-05-27T01:06:23.491581+00:00"},{"alias_kind":"pith_short_12","alias_value":"A2QJYIRZCW7D","created_at":"2026-05-27T01:06:23.491581+00:00"},{"alias_kind":"pith_short_16","alias_value":"A2QJYIRZCW7DYJPU","created_at":"2026-05-27T01:06:23.491581+00:00"},{"alias_kind":"pith_short_8","alias_value":"A2QJYIRZ","created_at":"2026-05-27T01:06:23.491581+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/A2QJYIRZCW7DYJPUALTGS576UI","json":"https://pith.science/pith/A2QJYIRZCW7DYJPUALTGS576UI.json","graph_json":"https://pith.science/api/pith-number/A2QJYIRZCW7DYJPUALTGS576UI/graph.json","events_json":"https://pith.science/api/pith-number/A2QJYIRZCW7DYJPUALTGS576UI/events.json","paper":"https://pith.science/paper/A2QJYIRZ"},"agent_actions":{"view_html":"https://pith.science/pith/A2QJYIRZCW7DYJPUALTGS576UI","download_json":"https://pith.science/pith/A2QJYIRZCW7DYJPUALTGS576UI.json","view_paper":"https://pith.science/paper/A2QJYIRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26998&json=true","fetch_graph":"https://pith.science/api/pith-number/A2QJYIRZCW7DYJPUALTGS576UI/graph.json","fetch_events":"https://pith.science/api/pith-number/A2QJYIRZCW7DYJPUALTGS576UI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A2QJYIRZCW7DYJPUALTGS576UI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A2QJYIRZCW7DYJPUALTGS576UI/action/storage_attestation","attest_author":"https://pith.science/pith/A2QJYIRZCW7DYJPUALTGS576UI/action/author_attestation","sign_citation":"https://pith.science/pith/A2QJYIRZCW7DYJPUALTGS576UI/action/citation_signature","submit_replication":"https://pith.science/pith/A2QJYIRZCW7DYJPUALTGS576UI/action/replication_record"}},"created_at":"2026-05-27T01:06:23.491581+00:00","updated_at":"2026-05-27T01:06:23.491581+00:00"}