{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6EQULQPSREPGRMBSQR2EEDJPLN","short_pith_number":"pith:6EQULQPS","canonical_record":{"source":{"id":"2607.09042","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-10T02:17:41Z","cross_cats_sorted":[],"title_canon_sha256":"6eb32790b5dc73f111f29a2cbb646af083098fcc3883126558b3b27f9782088e","abstract_canon_sha256":"a63335393536bf6670bc3acf1046c5f000f0921f07f2f7acfe2cffa1994b03da"},"schema_version":"1.0"},"canonical_sha256":"f12145c1f2891e68b0328474420d2f5b421bbde7d9847e8181cfb93a1b1b1014","source":{"kind":"arxiv","id":"2607.09042","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6EQULQPSREPGRMBSQR2EEDJPLN","target":"record","payload":{"canonical_record":{"source":{"id":"2607.09042","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-10T02:17:41Z","cross_cats_sorted":[],"title_canon_sha256":"6eb32790b5dc73f111f29a2cbb646af083098fcc3883126558b3b27f9782088e","abstract_canon_sha256":"a63335393536bf6670bc3acf1046c5f000f0921f07f2f7acfe2cffa1994b03da"},"schema_version":"1.0"},"canonical_sha256":"f12145c1f2891e68b0328474420d2f5b421bbde7d9847e8181cfb93a1b1b1014","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T00:17:37.144632Z","signature_b64":"yNtTMU/W0RpZ3pLxzA2/pqfzeSUJ3Ihb1C9rS4fXsCiZDXdi2dcTaD3SAusb8Ff9LmO9wONp31IvDPBRtSRXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f12145c1f2891e68b0328474420d2f5b421bbde7d9847e8181cfb93a1b1b1014","last_reissued_at":"2026-07-13T00:17:37.143391Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T00:17:37.143391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.09042","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":"2026-07-13T00:17:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L9UDoJnt0YWjjkIGSLdoXR+am8lfSpPvrBddNmRbkvS8akPMYHSss09sn9uzYsmbqN+giXkBd0SkRTTb6MxtAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:02:36.212630Z"},"content_sha256":"5b4c8844fa468da18ca68a08e7a9c935d60f6c395a2284a0f47247be9a066755","schema_version":"1.0","event_id":"sha256:5b4c8844fa468da18ca68a08e7a9c935d60f6c395a2284a0f47247be9a066755"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6EQULQPSREPGRMBSQR2EEDJPLN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning More from Less: Reinforcement Learning from Hindsight","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","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","submitted_at":"2026-07-10T02:17:41Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09042","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/2607.09042/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":"2026-07-13T00:17:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kEMJtuf58KjGyr8C71P/AQ29RvGbM4E56zydAdGLs3Cl39WTb0Au+zUjnzbZyUJf1sHt05OBc50hmcD4mroJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:02:36.213252Z"},"content_sha256":"3e106dddd14ece736175ec8cdb4aa6a759904f7e8b673fbe39228a0ebefaae20","schema_version":"1.0","event_id":"sha256:3e106dddd14ece736175ec8cdb4aa6a759904f7e8b673fbe39228a0ebefaae20"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6EQULQPSREPGRMBSQR2EEDJPLN/bundle.json","state_url":"https://pith.science/pith/6EQULQPSREPGRMBSQR2EEDJPLN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6EQULQPSREPGRMBSQR2EEDJPLN/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":"2026-08-06T21:02:36Z","links":{"resolver":"https://pith.science/pith/6EQULQPSREPGRMBSQR2EEDJPLN","bundle":"https://pith.science/pith/6EQULQPSREPGRMBSQR2EEDJPLN/bundle.json","state":"https://pith.science/pith/6EQULQPSREPGRMBSQR2EEDJPLN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6EQULQPSREPGRMBSQR2EEDJPLN/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sy9pJHlsdwy/E5knkaWR0uXQ+AD3dePcvdavWdwpuvcNlaB7cyg8qzwqiFJ5PWbnjIWtztdy8E4cl9kYyg55DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:02:36.218040Z","bundle_sha256":"a3e703166e8f4f9a49435194fc9f445e38696ea729424e150c2f596a61072847"}}