{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6EQULQPSREPGRMBSQR2EEDJPLN","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":"a63335393536bf6670bc3acf1046c5f000f0921f07f2f7acfe2cffa1994b03da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-10T02:17:41Z","title_canon_sha256":"6eb32790b5dc73f111f29a2cbb646af083098fcc3883126558b3b27f9782088e"},"schema_version":"1.0","source":{"id":"2607.09042","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09042","created_at":"2026-07-13T00:17:37Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09042v1","created_at":"2026-07-13T00:17:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09042","created_at":"2026-07-13T00:17:37Z"},{"alias_kind":"pith_short_12","alias_value":"6EQULQPSREPG","created_at":"2026-07-13T00:17:37Z"},{"alias_kind":"pith_short_16","alias_value":"6EQULQPSREPGRMBS","created_at":"2026-07-13T00:17:37Z"},{"alias_kind":"pith_short_8","alias_value":"6EQULQPS","created_at":"2026-07-13T00:17:37Z"}],"graph_snapshots":[{"event_id":"sha256:3e106dddd14ece736175ec8cdb4aa6a759904f7e8b673fbe39228a0ebefaae20","target":"graph","created_at":"2026-07-13T00:17:37Z","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/2607.09042/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is increasingly used to post-train vision-language-action (VLA) models, but every update consumes robot rollouts that are slow and costly to collect, making sample efficiency a central concern. Manipulation tasks typically provide only sparse rewards, so a weak policy fails almost every rollout early in training and has little to learn from, even when those failures execute coherent behavior. Such a failure, however, is a success at a different task. We present Learning from Hindsight (LfH), which brings hindsight relabeling to RL post-training of VLAs by scoring fa","authors_text":"Alex Pentland, Iris Xu, John Marangola, Nitish Dashora, Pulkit Agrawal, Richard Li, Sunshine Jiang, Thomas Liu, Yuheng Zhi, Zexue He, Zhang-Wei Hong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-10T02:17:41Z","title":"Learning More from Less: Reinforcement Learning from Hindsight"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09042","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":"sha256:5b4c8844fa468da18ca68a08e7a9c935d60f6c395a2284a0f47247be9a066755","target":"record","created_at":"2026-07-13T00:17:37Z","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":"a63335393536bf6670bc3acf1046c5f000f0921f07f2f7acfe2cffa1994b03da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-10T02:17:41Z","title_canon_sha256":"6eb32790b5dc73f111f29a2cbb646af083098fcc3883126558b3b27f9782088e"},"schema_version":"1.0","source":{"id":"2607.09042","kind":"arxiv","version":1}},"canonical_sha256":"f12145c1f2891e68b0328474420d2f5b421bbde7d9847e8181cfb93a1b1b1014","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f12145c1f2891e68b0328474420d2f5b421bbde7d9847e8181cfb93a1b1b1014","first_computed_at":"2026-07-13T00:17:37.143391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T00:17:37.143391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yNtTMU/W0RpZ3pLxzA2/pqfzeSUJ3Ihb1C9rS4fXsCiZDXdi2dcTaD3SAusb8Ff9LmO9wONp31IvDPBRtSRXAw==","signature_status":"signed_v1","signed_at":"2026-07-13T00:17:37.144632Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.09042","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b4c8844fa468da18ca68a08e7a9c935d60f6c395a2284a0f47247be9a066755","sha256:3e106dddd14ece736175ec8cdb4aa6a759904f7e8b673fbe39228a0ebefaae20"],"state_sha256":"8cf4c80daaa3eb28ad0e4b8fbfc259dfb27b4b7aa089566e5f538c79f10aaede"}