{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6OAZJRETLC6UF4K7R7RRKRNQPW","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":"95236a3280522cde2aca4f80c46f032615a6737605ae1460e9b267f42eae72c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-09T01:46:23Z","title_canon_sha256":"7006ec12c8b7e79be9e34c97e85ada602c92645d0914deeaac460b5d14bedaa1"},"schema_version":"1.0","source":{"id":"2606.10305","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10305","created_at":"2026-06-10T01:10:10Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10305v1","created_at":"2026-06-10T01:10:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10305","created_at":"2026-06-10T01:10:10Z"},{"alias_kind":"pith_short_12","alias_value":"6OAZJRETLC6U","created_at":"2026-06-10T01:10:10Z"},{"alias_kind":"pith_short_16","alias_value":"6OAZJRETLC6UF4K7","created_at":"2026-06-10T01:10:10Z"},{"alias_kind":"pith_short_8","alias_value":"6OAZJRET","created_at":"2026-06-10T01:10:10Z"}],"graph_snapshots":[{"event_id":"sha256:0fc5ecf2c994f1431cd2b287507a84af0c7a415687f60e3c7db30147c386a69a","target":"graph","created_at":"2026-06-10T01:10:10Z","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/2606.10305/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning vision-language-action (VLA) policies for long-horizon manipulation still relies heavily on behavior cloning, which requires costly high-quality demonstrations and keeps policies near the demonstration distribution. Reward models can reduce this dependence by reweighting demonstrations and providing dense supervision for on-robot reinforcement learning (RL), but they must be dense, accurate, and general. Existing methods fall short: task-specific stage-aware models are accurate but require per-task annotations, while general vision-language-model (VLM) reward models are broadly app","authors_text":"Chuan Wen, Hau Zheng, Jiankai Sun, Justin Yu, Ken Goldberg, Mac Schwager, Philipp Wu, Pieter Abbeel, Qianzhong Chen, Suning Huang, Yide Shentu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-09T01:46:23Z","title":"SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10305","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:f22a75a782a6ffe019633ac06cfe210f6804121dfc78de4ec879d10c2927ac34","target":"record","created_at":"2026-06-10T01:10:10Z","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":"95236a3280522cde2aca4f80c46f032615a6737605ae1460e9b267f42eae72c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-09T01:46:23Z","title_canon_sha256":"7006ec12c8b7e79be9e34c97e85ada602c92645d0914deeaac460b5d14bedaa1"},"schema_version":"1.0","source":{"id":"2606.10305","kind":"arxiv","version":1}},"canonical_sha256":"f38194c49358bd42f15f8fe31545b07d848893f416046fc463029a7679cc3dc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f38194c49358bd42f15f8fe31545b07d848893f416046fc463029a7679cc3dc4","first_computed_at":"2026-06-10T01:10:10.858573Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:10.858573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"49jXmYF65oSTLZeblRXjfBGPCxzvsM/qRrfhO4cVWcZjhGJAH+ofzWT7Kmsxlu/GtE9hTG+lLWjps/3cmIJdBg==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:10.859567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10305","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f22a75a782a6ffe019633ac06cfe210f6804121dfc78de4ec879d10c2927ac34","sha256:0fc5ecf2c994f1431cd2b287507a84af0c7a415687f60e3c7db30147c386a69a"],"state_sha256":"5e1a8bfba930868b510b6e53bf253a2db05fcda6be6b6d6f67bd92e1b017aeca"}