{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ERMQVHD3ZTZKO5QRQHXMSKYQHB","short_pith_number":"pith:ERMQVHD3","schema_version":"1.0","canonical_sha256":"24590a9c7bccf2a7761181eec92b103872bbf13bc414a22af39f033b7919070c","source":{"kind":"arxiv","id":"2603.24139","version":2},"attestation_state":"computed","paper":{"title":"Tutor-Student Reinforcement Learning: A Dynamic Curriculum for Robust Deepfake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Baojin Huang, Chao Liang, Dengpan Ye, Jikang Cheng, Yuhong Yang, Zhanhe Lei, Zhen Han, Zhongyuan Wang","submitted_at":"2026-03-25T10:04:42Z","abstract_excerpt":"Standard supervised training for deepfake detection treats all samples with uniform importance, which can be suboptimal for learning robust and generalizable features. In this work, we propose a novel Tutor-Student Reinforcement Learning (TSRL) framework to dynamically optimize the training curriculum. Our method models the training process as a Markov Decision Process where a ``Tutor'' agent learns to guide a ``Student'' (the deepfake detector). The Tutor, implemented as a Proximal Policy Optimization (PPO) agent, observes a rich state representation for each training sample, encapsulating no"},"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":"2603.24139","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-25T10:04:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2cb111995fd8c6719a92ca321f6f4a8e8ee410abb31835e54adccad568c8f55e","abstract_canon_sha256":"9d288c3899e088846b24cc1819e97a52cacf5cc67ae466443a778add713ae52b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:01.640950Z","signature_b64":"9vS2TqYEdzRHBvOlq8w0ocfeB6T5vgKTwxQYw5osfArVSXzG33haYB/yo9/noRWN0/NR2hjrE7MbpRyT6wmTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24590a9c7bccf2a7761181eec92b103872bbf13bc414a22af39f033b7919070c","last_reissued_at":"2026-05-21T02:05:01.640175Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:01.640175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tutor-Student Reinforcement Learning: A Dynamic Curriculum for Robust Deepfake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Baojin Huang, Chao Liang, Dengpan Ye, Jikang Cheng, Yuhong Yang, Zhanhe Lei, Zhen Han, Zhongyuan Wang","submitted_at":"2026-03-25T10:04:42Z","abstract_excerpt":"Standard supervised training for deepfake detection treats all samples with uniform importance, which can be suboptimal for learning robust and generalizable features. In this work, we propose a novel Tutor-Student Reinforcement Learning (TSRL) framework to dynamically optimize the training curriculum. Our method models the training process as a Markov Decision Process where a ``Tutor'' agent learns to guide a ``Student'' (the deepfake detector). The Tutor, implemented as a Proximal Policy Optimization (PPO) agent, observes a rich state representation for each training sample, encapsulating no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.24139","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/2603.24139/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":"2603.24139","created_at":"2026-05-21T02:05:01.640281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.24139v2","created_at":"2026-05-21T02:05:01.640281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.24139","created_at":"2026-05-21T02:05:01.640281+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERMQVHD3ZTZK","created_at":"2026-05-21T02:05:01.640281+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERMQVHD3ZTZKO5QR","created_at":"2026-05-21T02:05:01.640281+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERMQVHD3","created_at":"2026-05-21T02:05:01.640281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERMQVHD3ZTZKO5QRQHXMSKYQHB","json":"https://pith.science/pith/ERMQVHD3ZTZKO5QRQHXMSKYQHB.json","graph_json":"https://pith.science/api/pith-number/ERMQVHD3ZTZKO5QRQHXMSKYQHB/graph.json","events_json":"https://pith.science/api/pith-number/ERMQVHD3ZTZKO5QRQHXMSKYQHB/events.json","paper":"https://pith.science/paper/ERMQVHD3"},"agent_actions":{"view_html":"https://pith.science/pith/ERMQVHD3ZTZKO5QRQHXMSKYQHB","download_json":"https://pith.science/pith/ERMQVHD3ZTZKO5QRQHXMSKYQHB.json","view_paper":"https://pith.science/paper/ERMQVHD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.24139&json=true","fetch_graph":"https://pith.science/api/pith-number/ERMQVHD3ZTZKO5QRQHXMSKYQHB/graph.json","fetch_events":"https://pith.science/api/pith-number/ERMQVHD3ZTZKO5QRQHXMSKYQHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERMQVHD3ZTZKO5QRQHXMSKYQHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERMQVHD3ZTZKO5QRQHXMSKYQHB/action/storage_attestation","attest_author":"https://pith.science/pith/ERMQVHD3ZTZKO5QRQHXMSKYQHB/action/author_attestation","sign_citation":"https://pith.science/pith/ERMQVHD3ZTZKO5QRQHXMSKYQHB/action/citation_signature","submit_replication":"https://pith.science/pith/ERMQVHD3ZTZKO5QRQHXMSKYQHB/action/replication_record"}},"created_at":"2026-05-21T02:05:01.640281+00:00","updated_at":"2026-05-21T02:05:01.640281+00:00"}