{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZSBT3R7BJJWVVLJV2HVCRCSZJ6","short_pith_number":"pith:ZSBT3R7B","schema_version":"1.0","canonical_sha256":"cc833dc7e14a6d5aad35d1ea288a594fa883124678e7ca195c92aa917a3edab2","source":{"kind":"arxiv","id":"2505.09546","version":1},"attestation_state":"computed","paper":{"title":"Distilling Realizable Students from Unrealizable Teachers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Arnav Vasudev, Nathaniel Chin, Sanjiban Choudhury, Yujin Kim","submitted_at":"2025-05-14T16:45:51Z","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"},"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":"2505.09546","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T16:45:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d4546a7af4f07b22ae9371715a71544ebb51298e64734bd05c9439c27b487fbc","abstract_canon_sha256":"316841687303ec5c83414d4578f2a1445e72f529ef74c020477c9b7dfbdfc07f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:10.242741Z","signature_b64":"vUiBBnfE8laFeODO5tZFQdkFilU7w6LC4jNmLbKF2jbkdDwrMDi7yXm8UMpl1P0N1Lun/NBBl+aYPlIyfQcsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc833dc7e14a6d5aad35d1ea288a594fa883124678e7ca195c92aa917a3edab2","last_reissued_at":"2026-07-05T11:03:10.242253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:10.242253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilling Realizable Students from Unrealizable Teachers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Arnav Vasudev, Nathaniel Chin, Sanjiban Choudhury, Yujin Kim","submitted_at":"2025-05-14T16:45:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09546","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/2505.09546/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":"2505.09546","created_at":"2026-07-05T11:03:10.242309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09546v1","created_at":"2026-07-05T11:03:10.242309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09546","created_at":"2026-07-05T11:03:10.242309+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSBT3R7BJJWV","created_at":"2026-07-05T11:03:10.242309+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSBT3R7BJJWVVLJV","created_at":"2026-07-05T11:03:10.242309+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSBT3R7B","created_at":"2026-07-05T11:03:10.242309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26478","citing_title":"Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZSBT3R7BJJWVVLJV2HVCRCSZJ6","json":"https://pith.science/pith/ZSBT3R7BJJWVVLJV2HVCRCSZJ6.json","graph_json":"https://pith.science/api/pith-number/ZSBT3R7BJJWVVLJV2HVCRCSZJ6/graph.json","events_json":"https://pith.science/api/pith-number/ZSBT3R7BJJWVVLJV2HVCRCSZJ6/events.json","paper":"https://pith.science/paper/ZSBT3R7B"},"agent_actions":{"view_html":"https://pith.science/pith/ZSBT3R7BJJWVVLJV2HVCRCSZJ6","download_json":"https://pith.science/pith/ZSBT3R7BJJWVVLJV2HVCRCSZJ6.json","view_paper":"https://pith.science/paper/ZSBT3R7B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09546&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSBT3R7BJJWVVLJV2HVCRCSZJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSBT3R7BJJWVVLJV2HVCRCSZJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSBT3R7BJJWVVLJV2HVCRCSZJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSBT3R7BJJWVVLJV2HVCRCSZJ6/action/storage_attestation","attest_author":"https://pith.science/pith/ZSBT3R7BJJWVVLJV2HVCRCSZJ6/action/author_attestation","sign_citation":"https://pith.science/pith/ZSBT3R7BJJWVVLJV2HVCRCSZJ6/action/citation_signature","submit_replication":"https://pith.science/pith/ZSBT3R7BJJWVVLJV2HVCRCSZJ6/action/replication_record"}},"created_at":"2026-07-05T11:03:10.242309+00:00","updated_at":"2026-07-05T11:03:10.242309+00:00"}