{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G56WN5Q6KVSZFVMVRTCD5RQY5Z","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":"632b9c4e0e414428d422e683223e0374c6afee63862ffa7e7311389f6accbdb6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-04T00:53:02Z","title_canon_sha256":"502cc7e8a1d4c768290b94841560a879575058e89e9af8587409fe605010b82e"},"schema_version":"1.0","source":{"id":"2509.03790","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.03790","created_at":"2026-07-05T12:07:11Z"},{"alias_kind":"arxiv_version","alias_value":"2509.03790v2","created_at":"2026-07-05T12:07:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03790","created_at":"2026-07-05T12:07:11Z"},{"alias_kind":"pith_short_12","alias_value":"G56WN5Q6KVSZ","created_at":"2026-07-05T12:07:11Z"},{"alias_kind":"pith_short_16","alias_value":"G56WN5Q6KVSZFVMV","created_at":"2026-07-05T12:07:11Z"},{"alias_kind":"pith_short_8","alias_value":"G56WN5Q6","created_at":"2026-07-05T12:07:11Z"}],"graph_snapshots":[{"event_id":"sha256:642d64de3cf21fd6c9a39061cc636bdc8b89cec3a9bc65226623cb59d3dfbaa5","target":"graph","created_at":"2026-07-05T12:07:11Z","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/2509.03790/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse-reward reinforcement learning (RL) remains fundamentally hard: without structure, any agent needs $\\Omega(|\\mathcal{S}||\\mathcal{A}|/p)$ samples to recover rewards. We introduce Policy-Aware Matrix Completion (PAMC) as a first concrete step toward a structural reward learning framework. Our key idea is to exploit approximate low-rank + sparse structure in the reward matrix, under policy-biased (MNAR) sampling. We prove recovery guarantees with inverse-propensity weighting, and establish a visitation-weighted error-to-regret bound linking completion error to control performance. Importan","authors_text":"Anuj Sharma, Ibne Farabi Shihab, Sanjeda Akter","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-04T00:53:02Z","title":"What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03790","kind":"arxiv","version":2},"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":"sha256:2074716b941dde33fe33a4a0274051703600cb8a9edf1e8b4f04ab6f87fb2b10","target":"record","created_at":"2026-07-05T12:07:11Z","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":"632b9c4e0e414428d422e683223e0374c6afee63862ffa7e7311389f6accbdb6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-04T00:53:02Z","title_canon_sha256":"502cc7e8a1d4c768290b94841560a879575058e89e9af8587409fe605010b82e"},"schema_version":"1.0","source":{"id":"2509.03790","kind":"arxiv","version":2}},"canonical_sha256":"377d66f61e556592d5958cc43ec618ee4fec428f3d74bcd92372b628b61e2b5a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"377d66f61e556592d5958cc43ec618ee4fec428f3d74bcd92372b628b61e2b5a","first_computed_at":"2026-07-05T12:07:11.698978Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:07:11.698978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NE+wAVQ/iMczk/1MmwhxfJCWV5jwHC6NbUMLXpo1JbCQBZPsjctGKDQmUnpUfv7h5YzyL1F2vR8RWMsskHa/CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:07:11.699404Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.03790","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2074716b941dde33fe33a4a0274051703600cb8a9edf1e8b4f04ab6f87fb2b10","sha256:642d64de3cf21fd6c9a39061cc636bdc8b89cec3a9bc65226623cb59d3dfbaa5"],"state_sha256":"51967c8b72313e4c9a25ceb83f51570c291d325e1c1f9b164d01e99cfe347554"}