{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OAIQSWFK3ILCVKY2TYXTVFKJWR","short_pith_number":"pith:OAIQSWFK","canonical_record":{"source":{"id":"2606.30271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-06-29T13:18:42Z","cross_cats_sorted":[],"title_canon_sha256":"9070928e768e8f4f9c681f92a1f27d5f297da1bd867eb2b3f1894a864d0c7827","abstract_canon_sha256":"2fae12409c2373f0b6e5d2f58e491e25d6c547ebff6fc8da959b1975aefb9d71"},"schema_version":"1.0"},"canonical_sha256":"70110958aada162aab1a9e2f3a9549b478f95449b0910007c9f734456d255809","source":{"kind":"arxiv","id":"2606.30271","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30271","created_at":"2026-06-30T02:17:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30271v1","created_at":"2026-06-30T02:17:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30271","created_at":"2026-06-30T02:17:56Z"},{"alias_kind":"pith_short_12","alias_value":"OAIQSWFK3ILC","created_at":"2026-06-30T02:17:56Z"},{"alias_kind":"pith_short_16","alias_value":"OAIQSWFK3ILCVKY2","created_at":"2026-06-30T02:17:56Z"},{"alias_kind":"pith_short_8","alias_value":"OAIQSWFK","created_at":"2026-06-30T02:17:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OAIQSWFK3ILCVKY2TYXTVFKJWR","target":"record","payload":{"canonical_record":{"source":{"id":"2606.30271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-06-29T13:18:42Z","cross_cats_sorted":[],"title_canon_sha256":"9070928e768e8f4f9c681f92a1f27d5f297da1bd867eb2b3f1894a864d0c7827","abstract_canon_sha256":"2fae12409c2373f0b6e5d2f58e491e25d6c547ebff6fc8da959b1975aefb9d71"},"schema_version":"1.0"},"canonical_sha256":"70110958aada162aab1a9e2f3a9549b478f95449b0910007c9f734456d255809","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:56.899085Z","signature_b64":"dWzcTfLnI/X7QaV/O7kzG8zEnva+mTzQKKuxgsL8+k0bWpd6Z+FrrlrxQ3GKeGFEAQEBN+nN/xAIik4xOhb+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70110958aada162aab1a9e2f3a9549b478f95449b0910007c9f734456d255809","last_reissued_at":"2026-06-30T02:17:56.898486Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:56.898486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.30271","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T02:17:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6uo2SL3cO47VJXAcVwrWkK/4EGqV5lHA1Z3czQ09M4NN/o49Ud2QAEPAq4+YGWkB7l0PeU90Y6M2IU5z8j26Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T14:51:12.157706Z"},"content_sha256":"c724d9ca3e48f0901cb882b128b0d863d9bcc822539f0df3d686b68ed871b19f","schema_version":"1.0","event_id":"sha256:c724d9ca3e48f0901cb882b128b0d863d9bcc822539f0df3d686b68ed871b19f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OAIQSWFK3ILCVKY2TYXTVFKJWR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Preference-Based Reward Learning under Partial Observability with Inexact Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Reza Zolnouri, Semih Cayci","submitted_at":"2026-06-29T13:18:42Z","abstract_excerpt":"In this paper, we study how partial observability and inexact latent-state inference affect reward learning from preferences. To that end, we study preference-based reward learning under partial observability, where the learner forms latent-state estimates using an inexact learned POMDP model, so model error can accumulate over time. For finite log-linear POMDPs, we characterize this error term by establishing the stability of the belief filter to parametric model error under certain mixing conditions, yielding bounds on the belief mismatch in expectation and in high probability. We further ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30271","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/2606.30271/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T02:17:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yIMNtjaJXltaqkssWfJ9DeXAZVMw9XhBDRUT6lLqLdvYj6+gEcVhve7u2c7E1bB6pf2W50q0knVRT/1MKgqcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T14:51:12.158087Z"},"content_sha256":"35ae7d2bb97b8affb30364d2c473285bae67694fc126f13767be3e0d2f473337","schema_version":"1.0","event_id":"sha256:35ae7d2bb97b8affb30364d2c473285bae67694fc126f13767be3e0d2f473337"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OAIQSWFK3ILCVKY2TYXTVFKJWR/bundle.json","state_url":"https://pith.science/pith/OAIQSWFK3ILCVKY2TYXTVFKJWR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OAIQSWFK3ILCVKY2TYXTVFKJWR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-30T14:51:12Z","links":{"resolver":"https://pith.science/pith/OAIQSWFK3ILCVKY2TYXTVFKJWR","bundle":"https://pith.science/pith/OAIQSWFK3ILCVKY2TYXTVFKJWR/bundle.json","state":"https://pith.science/pith/OAIQSWFK3ILCVKY2TYXTVFKJWR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OAIQSWFK3ILCVKY2TYXTVFKJWR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OAIQSWFK3ILCVKY2TYXTVFKJWR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2fae12409c2373f0b6e5d2f58e491e25d6c547ebff6fc8da959b1975aefb9d71","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-06-29T13:18:42Z","title_canon_sha256":"9070928e768e8f4f9c681f92a1f27d5f297da1bd867eb2b3f1894a864d0c7827"},"schema_version":"1.0","source":{"id":"2606.30271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30271","created_at":"2026-06-30T02:17:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30271v1","created_at":"2026-06-30T02:17:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30271","created_at":"2026-06-30T02:17:56Z"},{"alias_kind":"pith_short_12","alias_value":"OAIQSWFK3ILC","created_at":"2026-06-30T02:17:56Z"},{"alias_kind":"pith_short_16","alias_value":"OAIQSWFK3ILCVKY2","created_at":"2026-06-30T02:17:56Z"},{"alias_kind":"pith_short_8","alias_value":"OAIQSWFK","created_at":"2026-06-30T02:17:56Z"}],"graph_snapshots":[{"event_id":"sha256:35ae7d2bb97b8affb30364d2c473285bae67694fc126f13767be3e0d2f473337","target":"graph","created_at":"2026-06-30T02:17:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.30271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study how partial observability and inexact latent-state inference affect reward learning from preferences. To that end, we study preference-based reward learning under partial observability, where the learner forms latent-state estimates using an inexact learned POMDP model, so model error can accumulate over time. For finite log-linear POMDPs, we characterize this error term by establishing the stability of the belief filter to parametric model error under certain mixing conditions, yielding bounds on the belief mismatch in expectation and in high probability. We further ex","authors_text":"Reza Zolnouri, Semih Cayci","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-06-29T13:18:42Z","title":"Preference-Based Reward Learning under Partial Observability with Inexact Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30271","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c724d9ca3e48f0901cb882b128b0d863d9bcc822539f0df3d686b68ed871b19f","target":"record","created_at":"2026-06-30T02:17:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2fae12409c2373f0b6e5d2f58e491e25d6c547ebff6fc8da959b1975aefb9d71","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-06-29T13:18:42Z","title_canon_sha256":"9070928e768e8f4f9c681f92a1f27d5f297da1bd867eb2b3f1894a864d0c7827"},"schema_version":"1.0","source":{"id":"2606.30271","kind":"arxiv","version":1}},"canonical_sha256":"70110958aada162aab1a9e2f3a9549b478f95449b0910007c9f734456d255809","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70110958aada162aab1a9e2f3a9549b478f95449b0910007c9f734456d255809","first_computed_at":"2026-06-30T02:17:56.898486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:56.898486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dWzcTfLnI/X7QaV/O7kzG8zEnva+mTzQKKuxgsL8+k0bWpd6Z+FrrlrxQ3GKeGFEAQEBN+nN/xAIik4xOhb+CQ==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:56.899085Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c724d9ca3e48f0901cb882b128b0d863d9bcc822539f0df3d686b68ed871b19f","sha256:35ae7d2bb97b8affb30364d2c473285bae67694fc126f13767be3e0d2f473337"],"state_sha256":"27f722b7327a2687fce9dab583322f8df554c7fd4a5d7649397d0a9794f43f17"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eUnDg5I3rC3QeNGChyUCxdeeGcgrsxy1shdyYxvTloHaJTi8PMaebhKO7nzMbhbfUxUDFnetxIs2sZBT9txTDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T14:51:12.160143Z","bundle_sha256":"9b0f252a5d99b765d87bdd67ba7cd66aed582fa2e43b7e3f1a4f4a5df7d64bae"}}