{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZSBT3R7BJJWVVLJV2HVCRCSZJ6","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":"316841687303ec5c83414d4578f2a1445e72f529ef74c020477c9b7dfbdfc07f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T16:45:51Z","title_canon_sha256":"d4546a7af4f07b22ae9371715a71544ebb51298e64734bd05c9439c27b487fbc"},"schema_version":"1.0","source":{"id":"2505.09546","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.09546","created_at":"2026-07-05T11:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.09546v1","created_at":"2026-07-05T11:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09546","created_at":"2026-07-05T11:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"ZSBT3R7BJJWV","created_at":"2026-07-05T11:03:10Z"},{"alias_kind":"pith_short_16","alias_value":"ZSBT3R7BJJWVVLJV","created_at":"2026-07-05T11:03:10Z"},{"alias_kind":"pith_short_8","alias_value":"ZSBT3R7B","created_at":"2026-07-05T11:03:10Z"}],"graph_snapshots":[{"event_id":"sha256:4001097813a943a1df5f9f9a9bc8361cf6dcb0aa93b67fdfe639769aa82f1833","target":"graph","created_at":"2026-07-05T11:03:10Z","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/2505.09546/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study policy distillation under privileged information, where a student policy with only partial observations must learn from a teacher with full-state access. A key challenge is information asymmetry: the student cannot directly access the teacher's state space, leading to distributional shifts and policy degradation. Existing approaches either modify the teacher to produce realizable but sub-optimal demonstrations or rely on the student to explore missing information independently, both of which are inefficient. Our key insight is that the student should strategically interact with the te","authors_text":"Arnav Vasudev, Nathaniel Chin, Sanjiban Choudhury, Yujin Kim","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T16:45:51Z","title":"Distilling Realizable Students from Unrealizable Teachers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09546","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":"sha256:07eea8480247a5372713d2b9a44482b134661e5fd887d67629d74fecd22a4b19","target":"record","created_at":"2026-07-05T11:03:10Z","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":"316841687303ec5c83414d4578f2a1445e72f529ef74c020477c9b7dfbdfc07f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T16:45:51Z","title_canon_sha256":"d4546a7af4f07b22ae9371715a71544ebb51298e64734bd05c9439c27b487fbc"},"schema_version":"1.0","source":{"id":"2505.09546","kind":"arxiv","version":1}},"canonical_sha256":"cc833dc7e14a6d5aad35d1ea288a594fa883124678e7ca195c92aa917a3edab2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc833dc7e14a6d5aad35d1ea288a594fa883124678e7ca195c92aa917a3edab2","first_computed_at":"2026-07-05T11:03:10.242253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:10.242253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vUiBBnfE8laFeODO5tZFQdkFilU7w6LC4jNmLbKF2jbkdDwrMDi7yXm8UMpl1P0N1Lun/NBBl+aYPlIyfQcsCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:10.242741Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.09546","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07eea8480247a5372713d2b9a44482b134661e5fd887d67629d74fecd22a4b19","sha256:4001097813a943a1df5f9f9a9bc8361cf6dcb0aa93b67fdfe639769aa82f1833"],"state_sha256":"0af59c9fb180c6d0bb19faa8670c70b8fe76530c04ad5b344a90beb6173742ea"}