{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:FGYU6YTQZAEWK7DTC6I5JHKIQN","short_pith_number":"pith:FGYU6YTQ","canonical_record":{"source":{"id":"2204.12458","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-26T17:24:36Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"3e0f3766c13d87b5ee90c9c8742dc955bdb6753221a899ed1149f6255120faaa","abstract_canon_sha256":"725784d29db6f8faf93c40d2e1a3cc2fe98fcc70a7045196e87ba267d039dee9"},"schema_version":"1.0"},"canonical_sha256":"29b14f6270c809657c731791d49d48836c50fe38a0e7d1a6b7ccd34ed0507936","source":{"kind":"arxiv","id":"2204.12458","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.12458","created_at":"2026-07-05T04:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"2204.12458v1","created_at":"2026-07-05T04:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12458","created_at":"2026-07-05T04:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"FGYU6YTQZAEW","created_at":"2026-07-05T04:17:48Z"},{"alias_kind":"pith_short_16","alias_value":"FGYU6YTQZAEWK7DT","created_at":"2026-07-05T04:17:48Z"},{"alias_kind":"pith_short_8","alias_value":"FGYU6YTQ","created_at":"2026-07-05T04:17:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:FGYU6YTQZAEWK7DTC6I5JHKIQN","target":"record","payload":{"canonical_record":{"source":{"id":"2204.12458","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-26T17:24:36Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"3e0f3766c13d87b5ee90c9c8742dc955bdb6753221a899ed1149f6255120faaa","abstract_canon_sha256":"725784d29db6f8faf93c40d2e1a3cc2fe98fcc70a7045196e87ba267d039dee9"},"schema_version":"1.0"},"canonical_sha256":"29b14f6270c809657c731791d49d48836c50fe38a0e7d1a6b7ccd34ed0507936","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:48.227707Z","signature_b64":"cOKkjuOt7rNYweIwlupe93Gv8xWHUX/u54AznJssVyy3TZDL1B9wMUMRqK72QYaqCuoDrZ6tvAqV2ulHRLH+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29b14f6270c809657c731791d49d48836c50fe38a0e7d1a6b7ccd34ed0507936","last_reissued_at":"2026-07-05T04:17:48.226037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:48.226037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.12458","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":"2026-07-05T04:17:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fv80LUiLwRszBAeISuB9Qh/+x9rtmt6AGCE36kObFXVfti8b3b+I5gnNjdwziKE+hzgQ/p8rRJIm/kPVhxRIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T08:07:56.561220Z"},"content_sha256":"3e89646154c175b3b6759d6f89dce8d7a8c3b59679f4b5cd0033bf6b01786756","schema_version":"1.0","event_id":"sha256:3e89646154c175b3b6759d6f89dce8d7a8c3b59679f4b5cd0033bf6b01786756"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:FGYU6YTQZAEWK7DTC6I5JHKIQN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Value Functions from Undirected State-only Experience","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Arjun Gupta, Matthew Chang, Saurabh Gupta","submitted_at":"2022-04-26T17:24:36Z","abstract_excerpt":"This paper tackles the problem of learning value functions from undirected state-only experience (state transitions without action labels i.e. (s,s',r) tuples). We first theoretically characterize the applicability of Q-learning in this setting. We show that tabular Q-learning in discrete Markov decision processes (MDPs) learns the same value function under any arbitrary refinement of the action space. This theoretical result motivates the design of Latent Action Q-learning or LAQ, an offline RL method that can learn effective value functions from state-only experience. Latent Action Q-learnin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12458","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/2204.12458/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":"2026-07-05T04:17:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UmE9EWZMqzl19Z+ji6ZgIfVWTgBs84GjHRMd23tRrADIcHmPnC84mQm9h12R9mv8YtrY1Mb9S7/ydG2kDyKBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T08:07:56.562055Z"},"content_sha256":"97721f767728fa885ced00de35567d4580d4525837eccf1539609506cf56c580","schema_version":"1.0","event_id":"sha256:97721f767728fa885ced00de35567d4580d4525837eccf1539609506cf56c580"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FGYU6YTQZAEWK7DTC6I5JHKIQN/bundle.json","state_url":"https://pith.science/pith/FGYU6YTQZAEWK7DTC6I5JHKIQN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FGYU6YTQZAEWK7DTC6I5JHKIQN/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":"2026-08-17T08:07:56Z","links":{"resolver":"https://pith.science/pith/FGYU6YTQZAEWK7DTC6I5JHKIQN","bundle":"https://pith.science/pith/FGYU6YTQZAEWK7DTC6I5JHKIQN/bundle.json","state":"https://pith.science/pith/FGYU6YTQZAEWK7DTC6I5JHKIQN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FGYU6YTQZAEWK7DTC6I5JHKIQN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FGYU6YTQZAEWK7DTC6I5JHKIQN","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":"725784d29db6f8faf93c40d2e1a3cc2fe98fcc70a7045196e87ba267d039dee9","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-26T17:24:36Z","title_canon_sha256":"3e0f3766c13d87b5ee90c9c8742dc955bdb6753221a899ed1149f6255120faaa"},"schema_version":"1.0","source":{"id":"2204.12458","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.12458","created_at":"2026-07-05T04:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"2204.12458v1","created_at":"2026-07-05T04:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12458","created_at":"2026-07-05T04:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"FGYU6YTQZAEW","created_at":"2026-07-05T04:17:48Z"},{"alias_kind":"pith_short_16","alias_value":"FGYU6YTQZAEWK7DT","created_at":"2026-07-05T04:17:48Z"},{"alias_kind":"pith_short_8","alias_value":"FGYU6YTQ","created_at":"2026-07-05T04:17:48Z"}],"graph_snapshots":[{"event_id":"sha256:97721f767728fa885ced00de35567d4580d4525837eccf1539609506cf56c580","target":"graph","created_at":"2026-07-05T04:17:48Z","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/2204.12458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper tackles the problem of learning value functions from undirected state-only experience (state transitions without action labels i.e. (s,s',r) tuples). We first theoretically characterize the applicability of Q-learning in this setting. We show that tabular Q-learning in discrete Markov decision processes (MDPs) learns the same value function under any arbitrary refinement of the action space. This theoretical result motivates the design of Latent Action Q-learning or LAQ, an offline RL method that can learn effective value functions from state-only experience. Latent Action Q-learnin","authors_text":"Arjun Gupta, Matthew Chang, Saurabh Gupta","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-26T17:24:36Z","title":"Learning Value Functions from Undirected State-only Experience"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12458","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":"sha256:3e89646154c175b3b6759d6f89dce8d7a8c3b59679f4b5cd0033bf6b01786756","target":"record","created_at":"2026-07-05T04:17:48Z","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":"725784d29db6f8faf93c40d2e1a3cc2fe98fcc70a7045196e87ba267d039dee9","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-26T17:24:36Z","title_canon_sha256":"3e0f3766c13d87b5ee90c9c8742dc955bdb6753221a899ed1149f6255120faaa"},"schema_version":"1.0","source":{"id":"2204.12458","kind":"arxiv","version":1}},"canonical_sha256":"29b14f6270c809657c731791d49d48836c50fe38a0e7d1a6b7ccd34ed0507936","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29b14f6270c809657c731791d49d48836c50fe38a0e7d1a6b7ccd34ed0507936","first_computed_at":"2026-07-05T04:17:48.226037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:48.226037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cOKkjuOt7rNYweIwlupe93Gv8xWHUX/u54AznJssVyy3TZDL1B9wMUMRqK72QYaqCuoDrZ6tvAqV2ulHRLH+CA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:48.227707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.12458","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e89646154c175b3b6759d6f89dce8d7a8c3b59679f4b5cd0033bf6b01786756","sha256:97721f767728fa885ced00de35567d4580d4525837eccf1539609506cf56c580"],"state_sha256":"d174f28589bad9ab1c3cbbd14d112f24e2375f2fad24527693fd03cb67f4bf5d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+N2aory2RvWw25NZvJ63rBfOmHefCVBtSn9F+nsNSgedqmXscPcS+qTnQE8WI4LN0XVX0Ej34oC6IqT+y5MjAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T08:07:56.568244Z","bundle_sha256":"615f21d605c76f10ef495de99ee9557deef34020dc70ead20e09c9e89db196fb"}}