{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:5P7AECTHH6MB4EYAMMTAYAIHBN","short_pith_number":"pith:5P7AECTH","canonical_record":{"source":{"id":"2206.03023","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T05:40:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cc9d842e17703c424133159532ccf981c0fbf65b819f51fc30157f968aa971a0","abstract_canon_sha256":"03c66f35e53e61f433db0c252f114da9c5b6194972148e208ca893a901f2bef1"},"schema_version":"1.0"},"canonical_sha256":"ebfe020a673f981e130063260c01070b6f6091a1828d6f897990b1f69aceae1e","source":{"kind":"arxiv","id":"2206.03023","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.03023","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"arxiv_version","alias_value":"2206.03023v2","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03023","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"pith_short_12","alias_value":"5P7AECTHH6MB","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"pith_short_16","alias_value":"5P7AECTHH6MB4EYA","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"pith_short_8","alias_value":"5P7AECTH","created_at":"2026-07-05T05:14:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:5P7AECTHH6MB4EYAMMTAYAIHBN","target":"record","payload":{"canonical_record":{"source":{"id":"2206.03023","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T05:40:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cc9d842e17703c424133159532ccf981c0fbf65b819f51fc30157f968aa971a0","abstract_canon_sha256":"03c66f35e53e61f433db0c252f114da9c5b6194972148e208ca893a901f2bef1"},"schema_version":"1.0"},"canonical_sha256":"ebfe020a673f981e130063260c01070b6f6091a1828d6f897990b1f69aceae1e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:14:57.748642Z","signature_b64":"7BYn/Vfw/zIWcZmzwegqlJG1ZvEiX0oOxyy23l7d4kHKUbt8pm58ATV23QcJh+qJHiX7dQKK/ms+VtCiw1z1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebfe020a673f981e130063260c01070b6f6091a1828d6f897990b1f69aceae1e","last_reissued_at":"2026-07-05T05:14:57.748172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:14:57.748172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.03023","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":"2026-07-05T05:14:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ujQnQUVU46rbSqW2+gD3ee7pxrBHvUzXK1TDSE3NMKcLa0lGMemsoXMufZd3h3QdceU7lrkKwK7eeJUGv2OpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T00:11:05.935720Z"},"content_sha256":"47fbdd150f3c53bb42d2b668b1548c281a7f381243d5145ff4c8d1af94f0f62f","schema_version":"1.0","event_id":"sha256:47fbdd150f3c53bb42d2b668b1548c281a7f381243d5145ff4c8d1af94f0f62f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:5P7AECTHH6MB4EYAMMTAYAIHBN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dinesh Jayaraman, Jason Yan, Osbert Bastani, Yecheng Jason Ma","submitted_at":"2022-06-07T05:40:16Z","abstract_excerpt":"Offline goal-conditioned reinforcement learning (GCRL) promises general-purpose skill learning in the form of reaching diverse goals from purely offline datasets. We propose $\\textbf{Go}$al-conditioned $f$-$\\textbf{A}$dvantage $\\textbf{R}$egression (GoFAR), a novel regression-based offline GCRL algorithm derived from a state-occupancy matching perspective; the key intuition is that the goal-reaching task can be formulated as a state-occupancy matching problem between a dynamics-abiding imitator agent and an expert agent that directly teleports to the goal. In contrast to prior approaches, GoFA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03023","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/2206.03023/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":"2026-07-05T05:14:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p3u5x/pMublE/MX8CDM1Z+DL7Tcc0gxY6VqjTfAGXHqXwI4Z4duQ6vnCXLY9ZEi/DR5AvJuaB9ak9g8x5p3nAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T00:11:05.936125Z"},"content_sha256":"3ad74d627706876b8bd2531786df144d807948285f8f259f2e2c736610256503","schema_version":"1.0","event_id":"sha256:3ad74d627706876b8bd2531786df144d807948285f8f259f2e2c736610256503"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5P7AECTHH6MB4EYAMMTAYAIHBN/bundle.json","state_url":"https://pith.science/pith/5P7AECTHH6MB4EYAMMTAYAIHBN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5P7AECTHH6MB4EYAMMTAYAIHBN/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":"2026-07-13T00:11:05Z","links":{"resolver":"https://pith.science/pith/5P7AECTHH6MB4EYAMMTAYAIHBN","bundle":"https://pith.science/pith/5P7AECTHH6MB4EYAMMTAYAIHBN/bundle.json","state":"https://pith.science/pith/5P7AECTHH6MB4EYAMMTAYAIHBN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5P7AECTHH6MB4EYAMMTAYAIHBN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5P7AECTHH6MB4EYAMMTAYAIHBN","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":"03c66f35e53e61f433db0c252f114da9c5b6194972148e208ca893a901f2bef1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T05:40:16Z","title_canon_sha256":"cc9d842e17703c424133159532ccf981c0fbf65b819f51fc30157f968aa971a0"},"schema_version":"1.0","source":{"id":"2206.03023","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.03023","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"arxiv_version","alias_value":"2206.03023v2","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03023","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"pith_short_12","alias_value":"5P7AECTHH6MB","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"pith_short_16","alias_value":"5P7AECTHH6MB4EYA","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"pith_short_8","alias_value":"5P7AECTH","created_at":"2026-07-05T05:14:57Z"}],"graph_snapshots":[{"event_id":"sha256:3ad74d627706876b8bd2531786df144d807948285f8f259f2e2c736610256503","target":"graph","created_at":"2026-07-05T05:14:57Z","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/2206.03023/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline goal-conditioned reinforcement learning (GCRL) promises general-purpose skill learning in the form of reaching diverse goals from purely offline datasets. We propose $\\textbf{Go}$al-conditioned $f$-$\\textbf{A}$dvantage $\\textbf{R}$egression (GoFAR), a novel regression-based offline GCRL algorithm derived from a state-occupancy matching perspective; the key intuition is that the goal-reaching task can be formulated as a state-occupancy matching problem between a dynamics-abiding imitator agent and an expert agent that directly teleports to the goal. In contrast to prior approaches, GoFA","authors_text":"Dinesh Jayaraman, Jason Yan, Osbert Bastani, Yecheng Jason Ma","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T05:40:16Z","title":"How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03023","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":"sha256:47fbdd150f3c53bb42d2b668b1548c281a7f381243d5145ff4c8d1af94f0f62f","target":"record","created_at":"2026-07-05T05:14:57Z","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":"03c66f35e53e61f433db0c252f114da9c5b6194972148e208ca893a901f2bef1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T05:40:16Z","title_canon_sha256":"cc9d842e17703c424133159532ccf981c0fbf65b819f51fc30157f968aa971a0"},"schema_version":"1.0","source":{"id":"2206.03023","kind":"arxiv","version":2}},"canonical_sha256":"ebfe020a673f981e130063260c01070b6f6091a1828d6f897990b1f69aceae1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebfe020a673f981e130063260c01070b6f6091a1828d6f897990b1f69aceae1e","first_computed_at":"2026-07-05T05:14:57.748172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:14:57.748172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7BYn/Vfw/zIWcZmzwegqlJG1ZvEiX0oOxyy23l7d4kHKUbt8pm58ATV23QcJh+qJHiX7dQKK/ms+VtCiw1z1DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:14:57.748642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.03023","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47fbdd150f3c53bb42d2b668b1548c281a7f381243d5145ff4c8d1af94f0f62f","sha256:3ad74d627706876b8bd2531786df144d807948285f8f259f2e2c736610256503"],"state_sha256":"3ac7f1d42939aee0d7d499be4e98b0a1b1fae516e0bb7c4068b3fb8fa30fd663"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gp7+DnIqzi9V4e9M0YLR8mbzQsWGr307o1L+x5qnH6Em8bEjUF/wnjvV2Jw79V+rCjNWTLs75sEKTHxnDL7XCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T00:11:05.940612Z","bundle_sha256":"0e5ba45f38f866dccbd2f0256b6d9a5cfe6d7b76c699b71a42ea45990cf433af"}}