{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6YVRTKVSRF45OYKFEHMFCSLRDU","short_pith_number":"pith:6YVRTKVS","canonical_record":{"source":{"id":"2506.02577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T07:55:57Z","cross_cats_sorted":[],"title_canon_sha256":"b4eb0d16810b0f896918d866430e243c96e60f76c3b1d3fc0724dccfb2b2a2c3","abstract_canon_sha256":"553afa889bb7d8d1a60f0500f05a01f36b60dbb7c7a240cebddb5473aadb24e3"},"schema_version":"1.0"},"canonical_sha256":"f62b19aab28979d7614521d85149711d308da5ee4d78287db7aff1dbd0d971de","source":{"kind":"arxiv","id":"2506.02577","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02577","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02577v1","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02577","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"6YVRTKVSRF45","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_16","alias_value":"6YVRTKVSRF45OYKF","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_8","alias_value":"6YVRTKVS","created_at":"2026-07-05T11:15:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6YVRTKVSRF45OYKFEHMFCSLRDU","target":"record","payload":{"canonical_record":{"source":{"id":"2506.02577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T07:55:57Z","cross_cats_sorted":[],"title_canon_sha256":"b4eb0d16810b0f896918d866430e243c96e60f76c3b1d3fc0724dccfb2b2a2c3","abstract_canon_sha256":"553afa889bb7d8d1a60f0500f05a01f36b60dbb7c7a240cebddb5473aadb24e3"},"schema_version":"1.0"},"canonical_sha256":"f62b19aab28979d7614521d85149711d308da5ee4d78287db7aff1dbd0d971de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:04.589393Z","signature_b64":"b8jv2kZzQQo+Yjlf/WhvBHPnScAJ8agiEORY3F05/wyAm5+YfHJayYXQyj6xrwYfSefxSepS7OoX2qVRnxXFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f62b19aab28979d7614521d85149711d308da5ee4d78287db7aff1dbd0d971de","last_reissued_at":"2026-07-05T11:15:04.588909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:04.588909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.02577","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":"2026-07-05T11:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7xJogKLarY/hAprj8Jprf9kIC03afijLLkfI8v8XJPIfGxYW/FJzPMk1dVti4nAbYexPXdWEgumC9HnvXtt8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:47:32.897545Z"},"content_sha256":"a44db28627df7da23b18279df3c246c4154a49d3fc31e180801002b31bd14b3c","schema_version":"1.0","event_id":"sha256:a44db28627df7da23b18279df3c246c4154a49d3fc31e180801002b31bd14b3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6YVRTKVSRF45OYKFEHMFCSLRDU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reachability Weighted Offline Goal-conditioned Resampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Joni Pajarinen, Wenyan Yang","submitted_at":"2025-06-03T07:55:57Z","abstract_excerpt":"Offline goal-conditioned reinforcement learning (RL) relies on fixed datasets where many potential goals share the same state and action spaces. However, these potential goals are not explicitly represented in the collected trajectories. To learn a generalizable goal-conditioned policy, it is common to sample goals and state-action pairs uniformly using dynamic programming methods such as Q-learning. Uniform sampling, however, requires an intractably large dataset to cover all possible combinations and creates many unreachable state-goal-action pairs that degrade policy performance. Our key in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02577","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/2506.02577/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":"2026-07-05T11:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LvkAGo5y/7qAos5iS/28F4Taft9ebjSTIYg+5rCGc1nkiln+pHlN7gzJk5t6WPSkhCxqA3LJ5YlZxbUx+svLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:47:32.898043Z"},"content_sha256":"a915a58c9fd64ec990f1b99a1b5936326724c2d183ac04efe32103a42c6f42e2","schema_version":"1.0","event_id":"sha256:a915a58c9fd64ec990f1b99a1b5936326724c2d183ac04efe32103a42c6f42e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6YVRTKVSRF45OYKFEHMFCSLRDU/bundle.json","state_url":"https://pith.science/pith/6YVRTKVSRF45OYKFEHMFCSLRDU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6YVRTKVSRF45OYKFEHMFCSLRDU/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":"2026-08-07T23:47:32Z","links":{"resolver":"https://pith.science/pith/6YVRTKVSRF45OYKFEHMFCSLRDU","bundle":"https://pith.science/pith/6YVRTKVSRF45OYKFEHMFCSLRDU/bundle.json","state":"https://pith.science/pith/6YVRTKVSRF45OYKFEHMFCSLRDU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6YVRTKVSRF45OYKFEHMFCSLRDU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6YVRTKVSRF45OYKFEHMFCSLRDU","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":"553afa889bb7d8d1a60f0500f05a01f36b60dbb7c7a240cebddb5473aadb24e3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T07:55:57Z","title_canon_sha256":"b4eb0d16810b0f896918d866430e243c96e60f76c3b1d3fc0724dccfb2b2a2c3"},"schema_version":"1.0","source":{"id":"2506.02577","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02577","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02577v1","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02577","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"6YVRTKVSRF45","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_16","alias_value":"6YVRTKVSRF45OYKF","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_8","alias_value":"6YVRTKVS","created_at":"2026-07-05T11:15:04Z"}],"graph_snapshots":[{"event_id":"sha256:a915a58c9fd64ec990f1b99a1b5936326724c2d183ac04efe32103a42c6f42e2","target":"graph","created_at":"2026-07-05T11:15:04Z","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/2506.02577/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline goal-conditioned reinforcement learning (RL) relies on fixed datasets where many potential goals share the same state and action spaces. However, these potential goals are not explicitly represented in the collected trajectories. To learn a generalizable goal-conditioned policy, it is common to sample goals and state-action pairs uniformly using dynamic programming methods such as Q-learning. Uniform sampling, however, requires an intractably large dataset to cover all possible combinations and creates many unreachable state-goal-action pairs that degrade policy performance. Our key in","authors_text":"Joni Pajarinen, Wenyan Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T07:55:57Z","title":"Reachability Weighted Offline Goal-conditioned Resampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02577","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:a44db28627df7da23b18279df3c246c4154a49d3fc31e180801002b31bd14b3c","target":"record","created_at":"2026-07-05T11:15:04Z","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":"553afa889bb7d8d1a60f0500f05a01f36b60dbb7c7a240cebddb5473aadb24e3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T07:55:57Z","title_canon_sha256":"b4eb0d16810b0f896918d866430e243c96e60f76c3b1d3fc0724dccfb2b2a2c3"},"schema_version":"1.0","source":{"id":"2506.02577","kind":"arxiv","version":1}},"canonical_sha256":"f62b19aab28979d7614521d85149711d308da5ee4d78287db7aff1dbd0d971de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f62b19aab28979d7614521d85149711d308da5ee4d78287db7aff1dbd0d971de","first_computed_at":"2026-07-05T11:15:04.588909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:04.588909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b8jv2kZzQQo+Yjlf/WhvBHPnScAJ8agiEORY3F05/wyAm5+YfHJayYXQyj6xrwYfSefxSepS7OoX2qVRnxXFCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:04.589393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02577","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a44db28627df7da23b18279df3c246c4154a49d3fc31e180801002b31bd14b3c","sha256:a915a58c9fd64ec990f1b99a1b5936326724c2d183ac04efe32103a42c6f42e2"],"state_sha256":"e474d9caa75c57148991957605c74250673579182637a782bde65fa95158bb2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YQOmo0y3sq6Lgjys/BFDEVqS/0rmsY0PZi+QuxxLEz6VGIaXjB1C0tHv7SM/4EIbhkAgh6jimOO2a3RfqjgMAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:47:32.902903Z","bundle_sha256":"36bd7075c33fb7f662d909ccbc1bff8caf45427621d0519c63fa8ca7249a15af"}}