{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LY2CT3VU4N4BAGJU5H24J4Q5QA","short_pith_number":"pith:LY2CT3VU","canonical_record":{"source":{"id":"2509.22310","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-26T13:14:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8dee3cb3024c6e9615d8b8a48ee510bd5c586585048616edba15a79490d9ee26","abstract_canon_sha256":"1fd96662393f71b669954c28a588c0227dbe88f5079416b5291149f82b27f5f6"},"schema_version":"1.0"},"canonical_sha256":"5e3429eeb4e378101934e9f5c4f21d8038dd236234df99b9c382021dee6d0864","source":{"kind":"arxiv","id":"2509.22310","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.22310","created_at":"2026-08-03T01:25:44Z"},{"alias_kind":"arxiv_version","alias_value":"2509.22310v2","created_at":"2026-08-03T01:25:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.22310","created_at":"2026-08-03T01:25:44Z"},{"alias_kind":"pith_short_12","alias_value":"LY2CT3VU4N4B","created_at":"2026-08-03T01:25:44Z"},{"alias_kind":"pith_short_16","alias_value":"LY2CT3VU4N4BAGJU","created_at":"2026-08-03T01:25:44Z"},{"alias_kind":"pith_short_8","alias_value":"LY2CT3VU","created_at":"2026-08-03T01:25:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LY2CT3VU4N4BAGJU5H24J4Q5QA","target":"record","payload":{"canonical_record":{"source":{"id":"2509.22310","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-26T13:14:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8dee3cb3024c6e9615d8b8a48ee510bd5c586585048616edba15a79490d9ee26","abstract_canon_sha256":"1fd96662393f71b669954c28a588c0227dbe88f5079416b5291149f82b27f5f6"},"schema_version":"1.0"},"canonical_sha256":"5e3429eeb4e378101934e9f5c4f21d8038dd236234df99b9c382021dee6d0864","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:25:44.464309Z","signature_b64":"j3UWdO/238zfWpjAk5j2z9Bhj8O/JLmjVW2Nj/lY9HzQzfBZb6i4ZvyJ+snaTkPxcveSToTWqphtR9IPFnVwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e3429eeb4e378101934e9f5c4f21d8038dd236234df99b9c382021dee6d0864","last_reissued_at":"2026-08-03T01:25:44.462556Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:25:44.462556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.22310","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-03T01:25:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aumCAKwaGvvKmlRJo+oCjiKEmSLwALnagGrHk1EhALZxpHPTcW8rbkXH01Zh1TW4izyGA+jbS5D3ir0mFMBcCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:10:27.670546Z"},"content_sha256":"036e860fe893c16285ef30ad518803748d837df68c69df887c5f419473676e57","schema_version":"1.0","event_id":"sha256:036e860fe893c16285ef30ad518803748d837df68c69df887c5f419473676e57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LY2CT3VU4N4BAGJU5H24J4Q5QA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Policy Backbone via Shared Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bumgeun Park, Donghwan Lee","submitted_at":"2025-09-26T13:14:03Z","abstract_excerpt":"Reinforcement learning (RL) has achieved impressive results across domains, yet learning an optimal policy typically requires extensive interaction data, limiting practical deployment. A common remedy is to leverage priors, such as pre-collected datasets or reference policies, but their utility degrades under task mismatch between training and deployment. While prior work has sought to address this mismatch, it has largely been restricted to in-distribution settings. To address this challenge, we propose Adaptive Policy Backbone (APB), a meta-transfer RL method that inserts lightweight linear "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.22310","kind":"arxiv","version":2},"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/2509.22310/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":"2026-08-03T01:25:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/7pxqmwGJrZnjlBBrstfLd54RDCc2qKqyEKkFYQ8m5uhNWe+ljcuvCjONZ5eUOVYEMVPNiWApIl8Zi1W2MahDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:10:27.671409Z"},"content_sha256":"d5d90e27a8f007db5c96e143f7818fd68d1f2dd3c5119681349b575ccda6e9e1","schema_version":"1.0","event_id":"sha256:d5d90e27a8f007db5c96e143f7818fd68d1f2dd3c5119681349b575ccda6e9e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LY2CT3VU4N4BAGJU5H24J4Q5QA/bundle.json","state_url":"https://pith.science/pith/LY2CT3VU4N4BAGJU5H24J4Q5QA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LY2CT3VU4N4BAGJU5H24J4Q5QA/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":"2026-08-18T01:10:27Z","links":{"resolver":"https://pith.science/pith/LY2CT3VU4N4BAGJU5H24J4Q5QA","bundle":"https://pith.science/pith/LY2CT3VU4N4BAGJU5H24J4Q5QA/bundle.json","state":"https://pith.science/pith/LY2CT3VU4N4BAGJU5H24J4Q5QA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LY2CT3VU4N4BAGJU5H24J4Q5QA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LY2CT3VU4N4BAGJU5H24J4Q5QA","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":"1fd96662393f71b669954c28a588c0227dbe88f5079416b5291149f82b27f5f6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-26T13:14:03Z","title_canon_sha256":"8dee3cb3024c6e9615d8b8a48ee510bd5c586585048616edba15a79490d9ee26"},"schema_version":"1.0","source":{"id":"2509.22310","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.22310","created_at":"2026-08-03T01:25:44Z"},{"alias_kind":"arxiv_version","alias_value":"2509.22310v2","created_at":"2026-08-03T01:25:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.22310","created_at":"2026-08-03T01:25:44Z"},{"alias_kind":"pith_short_12","alias_value":"LY2CT3VU4N4B","created_at":"2026-08-03T01:25:44Z"},{"alias_kind":"pith_short_16","alias_value":"LY2CT3VU4N4BAGJU","created_at":"2026-08-03T01:25:44Z"},{"alias_kind":"pith_short_8","alias_value":"LY2CT3VU","created_at":"2026-08-03T01:25:44Z"}],"graph_snapshots":[{"event_id":"sha256:d5d90e27a8f007db5c96e143f7818fd68d1f2dd3c5119681349b575ccda6e9e1","target":"graph","created_at":"2026-08-03T01:25:44Z","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/2509.22310/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has achieved impressive results across domains, yet learning an optimal policy typically requires extensive interaction data, limiting practical deployment. A common remedy is to leverage priors, such as pre-collected datasets or reference policies, but their utility degrades under task mismatch between training and deployment. While prior work has sought to address this mismatch, it has largely been restricted to in-distribution settings. To address this challenge, we propose Adaptive Policy Backbone (APB), a meta-transfer RL method that inserts lightweight linear ","authors_text":"Bumgeun Park, Donghwan Lee","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-26T13:14:03Z","title":"Adaptive Policy Backbone via Shared Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.22310","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":"sha256:036e860fe893c16285ef30ad518803748d837df68c69df887c5f419473676e57","target":"record","created_at":"2026-08-03T01:25:44Z","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":"1fd96662393f71b669954c28a588c0227dbe88f5079416b5291149f82b27f5f6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-26T13:14:03Z","title_canon_sha256":"8dee3cb3024c6e9615d8b8a48ee510bd5c586585048616edba15a79490d9ee26"},"schema_version":"1.0","source":{"id":"2509.22310","kind":"arxiv","version":2}},"canonical_sha256":"5e3429eeb4e378101934e9f5c4f21d8038dd236234df99b9c382021dee6d0864","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e3429eeb4e378101934e9f5c4f21d8038dd236234df99b9c382021dee6d0864","first_computed_at":"2026-08-03T01:25:44.462556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T01:25:44.462556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j3UWdO/238zfWpjAk5j2z9Bhj8O/JLmjVW2Nj/lY9HzQzfBZb6i4ZvyJ+snaTkPxcveSToTWqphtR9IPFnVwAA==","signature_status":"signed_v1","signed_at":"2026-08-03T01:25:44.464309Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.22310","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:036e860fe893c16285ef30ad518803748d837df68c69df887c5f419473676e57","sha256:d5d90e27a8f007db5c96e143f7818fd68d1f2dd3c5119681349b575ccda6e9e1"],"state_sha256":"a18cb0ceb7bfadef69eb4ae46aefec05a08255e2b17eebc1262e2267fca574f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wws752VgwKQy7dn5BQWNbnwyzPw1c/Gs5fi1LHAlNpyMhyYclh30gpSAmH9iFI5iiZ4yx7+jmU8JpYbxb8QeBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T01:10:27.685460Z","bundle_sha256":"2797e14e67d81bfab2ccc6b1e2ba9fa6180d04d07ba95073fd62740391aad9ff"}}