{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T3O5A7XNDKKJ6PYEAWCPYKLCXQ","short_pith_number":"pith:T3O5A7XN","schema_version":"1.0","canonical_sha256":"9eddd07eed1a949f3f040584fc2962bc30c25860c27c5313ea8009009651e49e","source":{"kind":"arxiv","id":"2606.22027","version":1},"attestation_state":"computed","paper":{"title":"RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Fan Shi, Kehan Wen, Minghao Fu, Pengyu Jing, Pengzhi Yang, Xin Liu, Xinyu Wang, Yaheng Shen, Yiduo Qu, Zhenhao Huang","submitted_at":"2026-06-20T13:03:21Z","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"},"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":"2606.22027","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-20T13:03:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b3c6bbdc55481c0b59073c1afc5de6f22c664adee583f06fcbea43f5fbdd5a4f","abstract_canon_sha256":"0d7ec35da7f1051d74a1fd48b722fab8df6b95e70bc13aec31c75ffc91679761"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:05.924850Z","signature_b64":"C6v8CSOtlh50nXY2sP4AjSRFGg5JO0D4bRUnwyV+oE2wP+4KDM//bcXOdu2gTVOQBlXZe1SQcfHBG4xp1JAHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9eddd07eed1a949f3f040584fc2962bc30c25860c27c5313ea8009009651e49e","last_reissued_at":"2026-06-23T02:13:05.924444Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:05.924444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Fan Shi, Kehan Wen, Minghao Fu, Pengyu Jing, Pengzhi Yang, Xin Liu, Xinyu Wang, Yaheng Shen, Yiduo Qu, Zhenhao Huang","submitted_at":"2026-06-20T13:03:21Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22027","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/2606.22027/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":"2606.22027","created_at":"2026-06-23T02:13:05.924501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22027v1","created_at":"2026-06-23T02:13:05.924501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22027","created_at":"2026-06-23T02:13:05.924501+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3O5A7XNDKKJ","created_at":"2026-06-23T02:13:05.924501+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3O5A7XNDKKJ6PYE","created_at":"2026-06-23T02:13:05.924501+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3O5A7XN","created_at":"2026-06-23T02:13:05.924501+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/T3O5A7XNDKKJ6PYEAWCPYKLCXQ","json":"https://pith.science/pith/T3O5A7XNDKKJ6PYEAWCPYKLCXQ.json","graph_json":"https://pith.science/api/pith-number/T3O5A7XNDKKJ6PYEAWCPYKLCXQ/graph.json","events_json":"https://pith.science/api/pith-number/T3O5A7XNDKKJ6PYEAWCPYKLCXQ/events.json","paper":"https://pith.science/paper/T3O5A7XN"},"agent_actions":{"view_html":"https://pith.science/pith/T3O5A7XNDKKJ6PYEAWCPYKLCXQ","download_json":"https://pith.science/pith/T3O5A7XNDKKJ6PYEAWCPYKLCXQ.json","view_paper":"https://pith.science/paper/T3O5A7XN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22027&json=true","fetch_graph":"https://pith.science/api/pith-number/T3O5A7XNDKKJ6PYEAWCPYKLCXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/T3O5A7XNDKKJ6PYEAWCPYKLCXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3O5A7XNDKKJ6PYEAWCPYKLCXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3O5A7XNDKKJ6PYEAWCPYKLCXQ/action/storage_attestation","attest_author":"https://pith.science/pith/T3O5A7XNDKKJ6PYEAWCPYKLCXQ/action/author_attestation","sign_citation":"https://pith.science/pith/T3O5A7XNDKKJ6PYEAWCPYKLCXQ/action/citation_signature","submit_replication":"https://pith.science/pith/T3O5A7XNDKKJ6PYEAWCPYKLCXQ/action/replication_record"}},"created_at":"2026-06-23T02:13:05.924501+00:00","updated_at":"2026-06-23T02:13:05.924501+00:00"}