{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4LKICJW4RHRGRYEDQGHX5YEIIZ","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":"e39cf1da2b1fdeabfb653cf171f234743bea9456b3a63621993fc4aed94e498c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T07:37:10Z","title_canon_sha256":"6962ffbbaa8f56bba09892341ff47074b20b8107c063ed5b2b12ae3450b12dea"},"schema_version":"1.0","source":{"id":"2607.02592","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02592","created_at":"2026-07-07T00:16:02Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02592v1","created_at":"2026-07-07T00:16:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02592","created_at":"2026-07-07T00:16:02Z"},{"alias_kind":"pith_short_12","alias_value":"4LKICJW4RHRG","created_at":"2026-07-07T00:16:02Z"},{"alias_kind":"pith_short_16","alias_value":"4LKICJW4RHRGRYED","created_at":"2026-07-07T00:16:02Z"},{"alias_kind":"pith_short_8","alias_value":"4LKICJW4","created_at":"2026-07-07T00:16:02Z"}],"graph_snapshots":[{"event_id":"sha256:12d0db072fde116b481fe381e9c09c7b154435a944fdb800bca3e408365c7f2a","target":"graph","created_at":"2026-07-07T00:16:02Z","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/2607.02592/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation (OPD) has recently emerged as an effective post-training paradigm by providing supervision on student-generated trajectories. However, existing OPD methods for multimodal reasoning usually rely on a static teacher routing, assigning each sample to a single teacher based on modality or task type. This ignores that visual grounding and abstract reasoning may dominate different decoding steps, making a single teacher insufficient for the full trajectory. To this end, H-OPD is proposed as a confidence-aware heterogeneous multi-teacher OPD framework for multimodal reasoning. ","authors_text":"Fei Su, Huanjin Yao, Jianghao Chen, Min Yang, Qixiang Yin, Yuchen Cai, Zhicheng Zhao, Ziyi Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T07:37:10Z","title":"H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02592","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:f9becf6127f3c1e11dba396ebeea425873efcd7c0e84e467a3fe3c79d7066a80","target":"record","created_at":"2026-07-07T00:16:02Z","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":"e39cf1da2b1fdeabfb653cf171f234743bea9456b3a63621993fc4aed94e498c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T07:37:10Z","title_canon_sha256":"6962ffbbaa8f56bba09892341ff47074b20b8107c063ed5b2b12ae3450b12dea"},"schema_version":"1.0","source":{"id":"2607.02592","kind":"arxiv","version":1}},"canonical_sha256":"e2d48126dc89e268e083818f7ee0884664cc1780d292160409aaa829e70f2589","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2d48126dc89e268e083818f7ee0884664cc1780d292160409aaa829e70f2589","first_computed_at":"2026-07-07T00:16:02.092127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T00:16:02.092127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vphrZT7rfShxI6lbxvxWfBONXOoVL3Ico9H9ePgkCl5EetdGraJd/PrsLElzjcEK1q2d5ifdZDGNHcNwzYfpCg==","signature_status":"signed_v1","signed_at":"2026-07-07T00:16:02.092825Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02592","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9becf6127f3c1e11dba396ebeea425873efcd7c0e84e467a3fe3c79d7066a80","sha256:12d0db072fde116b481fe381e9c09c7b154435a944fdb800bca3e408365c7f2a"],"state_sha256":"ff1ab6baf90eab97da292a9b630969205017937b687fbf18f4201aba363ec2fb"}