{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T3O5A7XNDKKJ6PYEAWCPYKLCXQ","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":"0d7ec35da7f1051d74a1fd48b722fab8df6b95e70bc13aec31c75ffc91679761","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-20T13:03:21Z","title_canon_sha256":"b3c6bbdc55481c0b59073c1afc5de6f22c664adee583f06fcbea43f5fbdd5a4f"},"schema_version":"1.0","source":{"id":"2606.22027","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22027","created_at":"2026-06-23T02:13:05Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22027v1","created_at":"2026-06-23T02:13:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22027","created_at":"2026-06-23T02:13:05Z"},{"alias_kind":"pith_short_12","alias_value":"T3O5A7XNDKKJ","created_at":"2026-06-23T02:13:05Z"},{"alias_kind":"pith_short_16","alias_value":"T3O5A7XNDKKJ6PYE","created_at":"2026-06-23T02:13:05Z"},{"alias_kind":"pith_short_8","alias_value":"T3O5A7XN","created_at":"2026-06-23T02:13:05Z"}],"graph_snapshots":[{"event_id":"sha256:b1f1baa3ad8e7cfc91e75eb0570820ebe08c934ae07fbbaeb521f3e11d7d9658","target":"graph","created_at":"2026-06-23T02:13:05Z","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/2606.22027/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning for robot manipulation is often bottlenecked by reward design, especially in long-horizon tasks: sparse success rewards provide weak supervision, while hand-crafted dense rewards are tedious to design and generalize poorly across tasks. Progress-based reward models offer a promising alternative by estimating how far an observation has advanced toward task completion, but existing approaches often require task-specific demonstrations or progress labels, and can assign high rewards to visually plausible but physically incorrect states. We introduce the Reference-Anchored R","authors_text":"Fan Shi, Kehan Wen, Minghao Fu, Pengyu Jing, Pengzhi Yang, Xin Liu, Xinyu Wang, Yaheng Shen, Yiduo Qu, Zhenhao Huang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-20T13:03:21Z","title":"RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22027","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":"sha256:1d0e6b714cffb39ab4f9f7dab4677a91a1379b789d2bdbb7202b971d779be47b","target":"record","created_at":"2026-06-23T02:13:05Z","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":"0d7ec35da7f1051d74a1fd48b722fab8df6b95e70bc13aec31c75ffc91679761","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-20T13:03:21Z","title_canon_sha256":"b3c6bbdc55481c0b59073c1afc5de6f22c664adee583f06fcbea43f5fbdd5a4f"},"schema_version":"1.0","source":{"id":"2606.22027","kind":"arxiv","version":1}},"canonical_sha256":"9eddd07eed1a949f3f040584fc2962bc30c25860c27c5313ea8009009651e49e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9eddd07eed1a949f3f040584fc2962bc30c25860c27c5313ea8009009651e49e","first_computed_at":"2026-06-23T02:13:05.924444Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:05.924444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C6v8CSOtlh50nXY2sP4AjSRFGg5JO0D4bRUnwyV+oE2wP+4KDM//bcXOdu2gTVOQBlXZe1SQcfHBG4xp1JAHCw==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:05.924850Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22027","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d0e6b714cffb39ab4f9f7dab4677a91a1379b789d2bdbb7202b971d779be47b","sha256:b1f1baa3ad8e7cfc91e75eb0570820ebe08c934ae07fbbaeb521f3e11d7d9658"],"state_sha256":"1f83e06d4f0b83844eb5fa6ee56d47e61f262507246135e4a3d856c6632b6366"}