{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6KIRYUBFG24Y34LNGFWN3FV6JA","short_pith_number":"pith:6KIRYUBF","canonical_record":{"source":{"id":"2406.13961","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T03:02:49Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"a4fa7ff32105d14de7653fc96ab4a97b5f4620592e3c1d8f3d9b4b59f3294e17","abstract_canon_sha256":"53b4b3d624fa232dda6ff1d88ab99761e911d411b08d16844ebe88013df47c1f"},"schema_version":"1.0"},"canonical_sha256":"f2911c502536b98df16d316cdd96be483a8b11cb6cc719fb2af81ea66a62827b","source":{"kind":"arxiv","id":"2406.13961","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13961","created_at":"2026-07-05T08:34:37Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13961v1","created_at":"2026-07-05T08:34:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13961","created_at":"2026-07-05T08:34:37Z"},{"alias_kind":"pith_short_12","alias_value":"6KIRYUBFG24Y","created_at":"2026-07-05T08:34:37Z"},{"alias_kind":"pith_short_16","alias_value":"6KIRYUBFG24Y34LN","created_at":"2026-07-05T08:34:37Z"},{"alias_kind":"pith_short_8","alias_value":"6KIRYUBF","created_at":"2026-07-05T08:34:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6KIRYUBFG24Y34LNGFWN3FV6JA","target":"record","payload":{"canonical_record":{"source":{"id":"2406.13961","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T03:02:49Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"a4fa7ff32105d14de7653fc96ab4a97b5f4620592e3c1d8f3d9b4b59f3294e17","abstract_canon_sha256":"53b4b3d624fa232dda6ff1d88ab99761e911d411b08d16844ebe88013df47c1f"},"schema_version":"1.0"},"canonical_sha256":"f2911c502536b98df16d316cdd96be483a8b11cb6cc719fb2af81ea66a62827b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:37.234297Z","signature_b64":"ij5dlw73Y0Xfi2MXFdwGseD+LnupayHtsqD/9fBVEvrg0QyEhjb9sY+9oryJjHjazpjI7LclkJ1SKaklpqSjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2911c502536b98df16d316cdd96be483a8b11cb6cc719fb2af81ea66a62827b","last_reissued_at":"2026-07-05T08:34:37.233843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:37.233843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.13961","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":"2026-07-05T08:34:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"be0KhqhRsz/WsWWciCjW6IB1r5F33gptYpMbDnJ3XxmjSNTgu0PMRev5kTsAxUA5JMV0dBs0etaOLmP/oho+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:44:38.182551Z"},"content_sha256":"e044071dc01de9feb77db527df3a2aa29c458b93f6b5b5126cc9c7e0b9d2d8ab","schema_version":"1.0","event_id":"sha256:e044071dc01de9feb77db527df3a2aa29c458b93f6b5b5126cc9c7e0b9d2d8ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6KIRYUBFG24Y34LNGFWN3FV6JA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Equivariant Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Arsh Tangri, David Klee, Dian Wang, Ondrej Biza, Owen Howell, Robert Platt","submitted_at":"2024-06-20T03:02:49Z","abstract_excerpt":"Sample efficiency is critical when applying learning-based methods to robotic manipulation due to the high cost of collecting expert demonstrations and the challenges of on-robot policy learning through online Reinforcement Learning (RL). Offline RL addresses this issue by enabling policy learning from an offline dataset collected using any behavioral policy, regardless of its quality. However, recent advancements in offline RL have predominantly focused on learning from large datasets. Given that many robotic manipulation tasks can be formulated as rotation-symmetric problems, we investigate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13961","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/2406.13961/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":"2026-07-05T08:34:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7AEkierGrti0ZEvlemB1M07asNWUW0WkFRN8QdWqQGR3ImCboaF+LsEmR7Zx/hUo0YI1HGVKPy3yLa2IccK3DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:44:38.182923Z"},"content_sha256":"96026cbf712b54544d09187ead81a762c3f0af9a4c7530dde0b958a81ace5fd0","schema_version":"1.0","event_id":"sha256:96026cbf712b54544d09187ead81a762c3f0af9a4c7530dde0b958a81ace5fd0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6KIRYUBFG24Y34LNGFWN3FV6JA/bundle.json","state_url":"https://pith.science/pith/6KIRYUBFG24Y34LNGFWN3FV6JA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6KIRYUBFG24Y34LNGFWN3FV6JA/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":"2026-07-07T12:44:38Z","links":{"resolver":"https://pith.science/pith/6KIRYUBFG24Y34LNGFWN3FV6JA","bundle":"https://pith.science/pith/6KIRYUBFG24Y34LNGFWN3FV6JA/bundle.json","state":"https://pith.science/pith/6KIRYUBFG24Y34LNGFWN3FV6JA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6KIRYUBFG24Y34LNGFWN3FV6JA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6KIRYUBFG24Y34LNGFWN3FV6JA","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":"53b4b3d624fa232dda6ff1d88ab99761e911d411b08d16844ebe88013df47c1f","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T03:02:49Z","title_canon_sha256":"a4fa7ff32105d14de7653fc96ab4a97b5f4620592e3c1d8f3d9b4b59f3294e17"},"schema_version":"1.0","source":{"id":"2406.13961","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13961","created_at":"2026-07-05T08:34:37Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13961v1","created_at":"2026-07-05T08:34:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13961","created_at":"2026-07-05T08:34:37Z"},{"alias_kind":"pith_short_12","alias_value":"6KIRYUBFG24Y","created_at":"2026-07-05T08:34:37Z"},{"alias_kind":"pith_short_16","alias_value":"6KIRYUBFG24Y34LN","created_at":"2026-07-05T08:34:37Z"},{"alias_kind":"pith_short_8","alias_value":"6KIRYUBF","created_at":"2026-07-05T08:34:37Z"}],"graph_snapshots":[{"event_id":"sha256:96026cbf712b54544d09187ead81a762c3f0af9a4c7530dde0b958a81ace5fd0","target":"graph","created_at":"2026-07-05T08:34:37Z","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/2406.13961/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sample efficiency is critical when applying learning-based methods to robotic manipulation due to the high cost of collecting expert demonstrations and the challenges of on-robot policy learning through online Reinforcement Learning (RL). Offline RL addresses this issue by enabling policy learning from an offline dataset collected using any behavioral policy, regardless of its quality. However, recent advancements in offline RL have predominantly focused on learning from large datasets. Given that many robotic manipulation tasks can be formulated as rotation-symmetric problems, we investigate ","authors_text":"Arsh Tangri, David Klee, Dian Wang, Ondrej Biza, Owen Howell, Robert Platt","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T03:02:49Z","title":"Equivariant Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13961","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:e044071dc01de9feb77db527df3a2aa29c458b93f6b5b5126cc9c7e0b9d2d8ab","target":"record","created_at":"2026-07-05T08:34:37Z","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":"53b4b3d624fa232dda6ff1d88ab99761e911d411b08d16844ebe88013df47c1f","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T03:02:49Z","title_canon_sha256":"a4fa7ff32105d14de7653fc96ab4a97b5f4620592e3c1d8f3d9b4b59f3294e17"},"schema_version":"1.0","source":{"id":"2406.13961","kind":"arxiv","version":1}},"canonical_sha256":"f2911c502536b98df16d316cdd96be483a8b11cb6cc719fb2af81ea66a62827b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2911c502536b98df16d316cdd96be483a8b11cb6cc719fb2af81ea66a62827b","first_computed_at":"2026-07-05T08:34:37.233843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:37.233843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ij5dlw73Y0Xfi2MXFdwGseD+LnupayHtsqD/9fBVEvrg0QyEhjb9sY+9oryJjHjazpjI7LclkJ1SKaklpqSjCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:37.234297Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.13961","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e044071dc01de9feb77db527df3a2aa29c458b93f6b5b5126cc9c7e0b9d2d8ab","sha256:96026cbf712b54544d09187ead81a762c3f0af9a4c7530dde0b958a81ace5fd0"],"state_sha256":"aba478a6d498931aa945ee429b285649c3ad230670beafaf121034d04220c589"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v3Y5RLivwyJpFuiXhRTRp+AOKatnXiDSewzxtqle3Khr+Xa2RAqjItFb04DdtqhHRFeZOa8aXjapAemdJAnOBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:44:38.184866Z","bundle_sha256":"90803a426e9542c9efec5b842b317f3b6763587bc8b1de66de546e7d74ce1548"}}