{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:T3O5A7XNDKKJ6PYEAWCPYKLCXQ","short_pith_number":"pith:T3O5A7XN","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"},"canonical_sha256":"9eddd07eed1a949f3f040584fc2962bc30c25860c27c5313ea8009009651e49e","source":{"kind":"arxiv","id":"2606.22027","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:T3O5A7XNDKKJ6PYEAWCPYKLCXQ","target":"record","payload":{"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"},"canonical_sha256":"9eddd07eed1a949f3f040584fc2962bc30c25860c27c5313ea8009009651e49e","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"},"source_kind":"arxiv","source_id":"2606.22027","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:13:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H3Q3r2NI30Rvw2ed/hfJrzC17E6fDYmtxf87mb1/iX3s+gzf/wa4A4a3b5ZWwqteTrXRFns2C65cK+q8v96DBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T20:45:03.740893Z"},"content_sha256":"1d0e6b714cffb39ab4f9f7dab4677a91a1379b789d2bdbb7202b971d779be47b","schema_version":"1.0","event_id":"sha256:1d0e6b714cffb39ab4f9f7dab4677a91a1379b789d2bdbb7202b971d779be47b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:T3O5A7XNDKKJ6PYEAWCPYKLCXQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:13:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MRlQ1U+xzvcRHn3lKbMO9YmMpZHn99RPZ3AvNSwsTDASbiyA56n7keB3DZ064M27Ct++see3XNVyzIJlwPKUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T20:45:03.741261Z"},"content_sha256":"b1f1baa3ad8e7cfc91e75eb0570820ebe08c934ae07fbbaeb521f3e11d7d9658","schema_version":"1.0","event_id":"sha256:b1f1baa3ad8e7cfc91e75eb0570820ebe08c934ae07fbbaeb521f3e11d7d9658"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T3O5A7XNDKKJ6PYEAWCPYKLCXQ/bundle.json","state_url":"https://pith.science/pith/T3O5A7XNDKKJ6PYEAWCPYKLCXQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T3O5A7XNDKKJ6PYEAWCPYKLCXQ/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":"2026-06-28T20:45:03Z","links":{"resolver":"https://pith.science/pith/T3O5A7XNDKKJ6PYEAWCPYKLCXQ","bundle":"https://pith.science/pith/T3O5A7XNDKKJ6PYEAWCPYKLCXQ/bundle.json","state":"https://pith.science/pith/T3O5A7XNDKKJ6PYEAWCPYKLCXQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T3O5A7XNDKKJ6PYEAWCPYKLCXQ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NN0CjiclQBX22p3ED7sEwO5Reo1Mpvu3jAlKvmeFy92pTjU4qaOe+1sXrXGPV1xjQ4VgVps6bhadgX53+y2xCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T20:45:03.744996Z","bundle_sha256":"7299b95f2fd41222e90549390f0b2bed7ac2867dd05b16014edb0da3893d3d78"}}