{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:R7PITDNY7EZ5G2M33UYZQ3Q5QR","short_pith_number":"pith:R7PITDNY","canonical_record":{"source":{"id":"2412.20519","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-29T16:42:30Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c678849402e0cff1504508d3695d3d834bcb70b07e0a50443aedca6dbc14f9cd","abstract_canon_sha256":"d7ed0d2f7e8fce5f950e7c8adf0131f5551d6a7e9c1d7464bde33c4ac008807e"},"schema_version":"1.0"},"canonical_sha256":"8fde898db8f933d3699bdd31986e1d844419df81adc2baa38df6ec4eeac8eeeb","source":{"kind":"arxiv","id":"2412.20519","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20519","created_at":"2026-07-05T12:03:23Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20519v2","created_at":"2026-07-05T12:03:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20519","created_at":"2026-07-05T12:03:23Z"},{"alias_kind":"pith_short_12","alias_value":"R7PITDNY7EZ5","created_at":"2026-07-05T12:03:23Z"},{"alias_kind":"pith_short_16","alias_value":"R7PITDNY7EZ5G2M3","created_at":"2026-07-05T12:03:23Z"},{"alias_kind":"pith_short_8","alias_value":"R7PITDNY","created_at":"2026-07-05T12:03:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:R7PITDNY7EZ5G2M33UYZQ3Q5QR","target":"record","payload":{"canonical_record":{"source":{"id":"2412.20519","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-29T16:42:30Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c678849402e0cff1504508d3695d3d834bcb70b07e0a50443aedca6dbc14f9cd","abstract_canon_sha256":"d7ed0d2f7e8fce5f950e7c8adf0131f5551d6a7e9c1d7464bde33c4ac008807e"},"schema_version":"1.0"},"canonical_sha256":"8fde898db8f933d3699bdd31986e1d844419df81adc2baa38df6ec4eeac8eeeb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:23.892411Z","signature_b64":"GdBtigUQvQuD9d5Gr5lAfQbm5ZB41FQdRwPfbs4ypIW/iUeFDFO3++BG+h2EuTJc1/zeuTuOfcKpW7XHl0KMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fde898db8f933d3699bdd31986e1d844419df81adc2baa38df6ec4eeac8eeeb","last_reissued_at":"2026-07-05T12:03:23.891792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:23.891792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.20519","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:03:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oGxsn8j5VNBYtvLRMvaNPSi3f+hU5ii9nFPnalpkFiS0Ka7rwZwEFAhWVqM/8Z8/bLXtcEwQuTzVXQg4mQViBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:21:53.680975Z"},"content_sha256":"6b6361565fd5a34bf395cfb644744407d917d3cb55f351341e24ef63213a9e9c","schema_version":"1.0","event_id":"sha256:6b6361565fd5a34bf395cfb644744407d917d3cb55f351341e24ef63213a9e9c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:R7PITDNY7EZ5G2M33UYZQ3Q5QR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Goal-Conditioned Data Augmentation for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Benoit Boulet, Di Wu, Xingshuai Huang","submitted_at":"2024-12-29T16:42:30Z","abstract_excerpt":"Offline reinforcement learning (RL) enables policy learning from pre-collected offline datasets, relaxing the need to interact directly with the environment. However, limited by the quality of offline datasets, it generally fails to learn well-qualified policies in suboptimal datasets. To address datasets with insufficient optimal demonstrations, we introduce Goal-cOnditioned Data Augmentation (GODA), a novel goal-conditioned diffusion-based method for augmenting samples with higher quality. Leveraging recent advancements in generative modelling, GODA incorporates a novel return-oriented goal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20519","kind":"arxiv","version":2},"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/2412.20519/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":"2026-07-05T12:03:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AH2xqh1bQLTBvZajxw76rSHiorwHLjnAkUUjTcbcRVVAaFvfgIzycIoyAh/LY9ns7kOhSpwHwC8oiBeLkf/JCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:21:53.681557Z"},"content_sha256":"fc130de341aa788b6da1ed2c96cad8609bfdcf385d7a68bb61dc9e00c2b07de2","schema_version":"1.0","event_id":"sha256:fc130de341aa788b6da1ed2c96cad8609bfdcf385d7a68bb61dc9e00c2b07de2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R7PITDNY7EZ5G2M33UYZQ3Q5QR/bundle.json","state_url":"https://pith.science/pith/R7PITDNY7EZ5G2M33UYZQ3Q5QR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R7PITDNY7EZ5G2M33UYZQ3Q5QR/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":"2026-08-18T22:21:53Z","links":{"resolver":"https://pith.science/pith/R7PITDNY7EZ5G2M33UYZQ3Q5QR","bundle":"https://pith.science/pith/R7PITDNY7EZ5G2M33UYZQ3Q5QR/bundle.json","state":"https://pith.science/pith/R7PITDNY7EZ5G2M33UYZQ3Q5QR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R7PITDNY7EZ5G2M33UYZQ3Q5QR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R7PITDNY7EZ5G2M33UYZQ3Q5QR","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":"d7ed0d2f7e8fce5f950e7c8adf0131f5551d6a7e9c1d7464bde33c4ac008807e","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-29T16:42:30Z","title_canon_sha256":"c678849402e0cff1504508d3695d3d834bcb70b07e0a50443aedca6dbc14f9cd"},"schema_version":"1.0","source":{"id":"2412.20519","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20519","created_at":"2026-07-05T12:03:23Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20519v2","created_at":"2026-07-05T12:03:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20519","created_at":"2026-07-05T12:03:23Z"},{"alias_kind":"pith_short_12","alias_value":"R7PITDNY7EZ5","created_at":"2026-07-05T12:03:23Z"},{"alias_kind":"pith_short_16","alias_value":"R7PITDNY7EZ5G2M3","created_at":"2026-07-05T12:03:23Z"},{"alias_kind":"pith_short_8","alias_value":"R7PITDNY","created_at":"2026-07-05T12:03:23Z"}],"graph_snapshots":[{"event_id":"sha256:fc130de341aa788b6da1ed2c96cad8609bfdcf385d7a68bb61dc9e00c2b07de2","target":"graph","created_at":"2026-07-05T12:03:23Z","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/2412.20519/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) enables policy learning from pre-collected offline datasets, relaxing the need to interact directly with the environment. However, limited by the quality of offline datasets, it generally fails to learn well-qualified policies in suboptimal datasets. To address datasets with insufficient optimal demonstrations, we introduce Goal-cOnditioned Data Augmentation (GODA), a novel goal-conditioned diffusion-based method for augmenting samples with higher quality. Leveraging recent advancements in generative modelling, GODA incorporates a novel return-oriented goal ","authors_text":"Benoit Boulet, Di Wu, Xingshuai Huang","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-29T16:42:30Z","title":"Goal-Conditioned Data Augmentation for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20519","kind":"arxiv","version":2},"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":"sha256:6b6361565fd5a34bf395cfb644744407d917d3cb55f351341e24ef63213a9e9c","target":"record","created_at":"2026-07-05T12:03:23Z","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":"d7ed0d2f7e8fce5f950e7c8adf0131f5551d6a7e9c1d7464bde33c4ac008807e","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-29T16:42:30Z","title_canon_sha256":"c678849402e0cff1504508d3695d3d834bcb70b07e0a50443aedca6dbc14f9cd"},"schema_version":"1.0","source":{"id":"2412.20519","kind":"arxiv","version":2}},"canonical_sha256":"8fde898db8f933d3699bdd31986e1d844419df81adc2baa38df6ec4eeac8eeeb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fde898db8f933d3699bdd31986e1d844419df81adc2baa38df6ec4eeac8eeeb","first_computed_at":"2026-07-05T12:03:23.891792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:23.891792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GdBtigUQvQuD9d5Gr5lAfQbm5ZB41FQdRwPfbs4ypIW/iUeFDFO3++BG+h2EuTJc1/zeuTuOfcKpW7XHl0KMBw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:23.892411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.20519","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b6361565fd5a34bf395cfb644744407d917d3cb55f351341e24ef63213a9e9c","sha256:fc130de341aa788b6da1ed2c96cad8609bfdcf385d7a68bb61dc9e00c2b07de2"],"state_sha256":"e0528e07a23a6e6ec57987c3f1e4da5d060efc6b46fc99cc1692fd961609460e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"59eKmo5A8jvpt84obPDuQHtNsXOTfd0Put3VxuBnKjkBiAVyQhVrw4cHXQfuW5p08XIjGdLb4sXcToEusAZHCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T22:21:53.686818Z","bundle_sha256":"7e8eb74aa31a5a9ffd4927b3e4e9fdec28948c6fa7b61f999c71eb4e394fe9f3"}}