{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7CA6K55VDOLF2EVEK73G5PBZL7","short_pith_number":"pith:7CA6K55V","canonical_record":{"source":{"id":"2405.07838","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T15:24:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9463b7be81dc4bbb4932edf87d12e7e1ba340ef70ef07a3e05f6a0ca64cd09b0","abstract_canon_sha256":"7d6ed8594b2ca07ffea5095cd9b2b0644d6d8ab25144a056b97ea31b8e6e6d72"},"schema_version":"1.0"},"canonical_sha256":"f881e577b51b965d12a457f66ebc395ff9ae1744e292aedfa1af2857f2c95c26","source":{"kind":"arxiv","id":"2405.07838","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.07838","created_at":"2026-07-05T09:19:57Z"},{"alias_kind":"arxiv_version","alias_value":"2405.07838v2","created_at":"2026-07-05T09:19:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07838","created_at":"2026-07-05T09:19:57Z"},{"alias_kind":"pith_short_12","alias_value":"7CA6K55VDOLF","created_at":"2026-07-05T09:19:57Z"},{"alias_kind":"pith_short_16","alias_value":"7CA6K55VDOLF2EVE","created_at":"2026-07-05T09:19:57Z"},{"alias_kind":"pith_short_8","alias_value":"7CA6K55V","created_at":"2026-07-05T09:19:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7CA6K55VDOLF2EVEK73G5PBZL7","target":"record","payload":{"canonical_record":{"source":{"id":"2405.07838","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T15:24:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9463b7be81dc4bbb4932edf87d12e7e1ba340ef70ef07a3e05f6a0ca64cd09b0","abstract_canon_sha256":"7d6ed8594b2ca07ffea5095cd9b2b0644d6d8ab25144a056b97ea31b8e6e6d72"},"schema_version":"1.0"},"canonical_sha256":"f881e577b51b965d12a457f66ebc395ff9ae1744e292aedfa1af2857f2c95c26","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:57.250052Z","signature_b64":"db/fnSlYUR4ypBuykBzDvtvijQcwCkq57B0iy9Blqzg/4cMdbw63OH9V6gC2jnoPHWD9kupWnlnOyHeEX632Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f881e577b51b965d12a457f66ebc395ff9ae1744e292aedfa1af2857f2c95c26","last_reissued_at":"2026-07-05T09:19:57.249613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:57.249613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.07838","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":"2026-07-05T09:19:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tAQzhXM7aMb6RkrilWqXeSudqLc8HKg3q/4r3XA/xxOTkNQW2FcDeki/hZ6EFfAPM89cwACnHOHLal/N66XlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:52:28.767124Z"},"content_sha256":"89968bcb282288aa18081f53c420676b01b73f850928af5ee43db1b57175b13e","schema_version":"1.0","event_id":"sha256:89968bcb282288aa18081f53c420676b01b73f850928af5ee43db1b57175b13e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7CA6K55VDOLF2EVEK73G5PBZL7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Exploration for Data-Efficient General Value Function Evaluations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arushi Jain, Doina Precup, Josiah P. Hanna","submitted_at":"2024-05-13T15:24:27Z","abstract_excerpt":"General Value Functions (GVFs) (Sutton et al., 2011) represent predictive knowledge in reinforcement learning. Each GVF computes the expected return for a given policy, based on a unique reward. Existing methods relying on fixed behavior policies or pre-collected data often face data efficiency issues when learning multiple GVFs in parallel using off-policy methods. To address this, we introduce GVFExplorer, which adaptively learns a single behavior policy that efficiently collects data for evaluating multiple GVFs in parallel. Our method optimizes the behavior policy by minimizing the total v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07838","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/2405.07838/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":"2026-07-05T09:19:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sw7RlVzR8KTolNm3eBvoMdQj7CeRqvVKmiHRKGMeFahrTHvwpp4HdY0wGw0ijfkVjIkRLhAw4v/OHEGupar3Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:52:28.767510Z"},"content_sha256":"ada6e79dcf5cb569cf3dd1076e7fe445f369223314c148839176a7e9a631f02e","schema_version":"1.0","event_id":"sha256:ada6e79dcf5cb569cf3dd1076e7fe445f369223314c148839176a7e9a631f02e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7CA6K55VDOLF2EVEK73G5PBZL7/bundle.json","state_url":"https://pith.science/pith/7CA6K55VDOLF2EVEK73G5PBZL7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7CA6K55VDOLF2EVEK73G5PBZL7/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":"2026-07-07T06:52:28Z","links":{"resolver":"https://pith.science/pith/7CA6K55VDOLF2EVEK73G5PBZL7","bundle":"https://pith.science/pith/7CA6K55VDOLF2EVEK73G5PBZL7/bundle.json","state":"https://pith.science/pith/7CA6K55VDOLF2EVEK73G5PBZL7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7CA6K55VDOLF2EVEK73G5PBZL7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7CA6K55VDOLF2EVEK73G5PBZL7","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":"7d6ed8594b2ca07ffea5095cd9b2b0644d6d8ab25144a056b97ea31b8e6e6d72","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T15:24:27Z","title_canon_sha256":"9463b7be81dc4bbb4932edf87d12e7e1ba340ef70ef07a3e05f6a0ca64cd09b0"},"schema_version":"1.0","source":{"id":"2405.07838","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.07838","created_at":"2026-07-05T09:19:57Z"},{"alias_kind":"arxiv_version","alias_value":"2405.07838v2","created_at":"2026-07-05T09:19:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07838","created_at":"2026-07-05T09:19:57Z"},{"alias_kind":"pith_short_12","alias_value":"7CA6K55VDOLF","created_at":"2026-07-05T09:19:57Z"},{"alias_kind":"pith_short_16","alias_value":"7CA6K55VDOLF2EVE","created_at":"2026-07-05T09:19:57Z"},{"alias_kind":"pith_short_8","alias_value":"7CA6K55V","created_at":"2026-07-05T09:19:57Z"}],"graph_snapshots":[{"event_id":"sha256:ada6e79dcf5cb569cf3dd1076e7fe445f369223314c148839176a7e9a631f02e","target":"graph","created_at":"2026-07-05T09:19:57Z","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/2405.07838/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"General Value Functions (GVFs) (Sutton et al., 2011) represent predictive knowledge in reinforcement learning. Each GVF computes the expected return for a given policy, based on a unique reward. Existing methods relying on fixed behavior policies or pre-collected data often face data efficiency issues when learning multiple GVFs in parallel using off-policy methods. To address this, we introduce GVFExplorer, which adaptively learns a single behavior policy that efficiently collects data for evaluating multiple GVFs in parallel. Our method optimizes the behavior policy by minimizing the total v","authors_text":"Arushi Jain, Doina Precup, Josiah P. Hanna","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T15:24:27Z","title":"Adaptive Exploration for Data-Efficient General Value Function Evaluations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07838","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":"sha256:89968bcb282288aa18081f53c420676b01b73f850928af5ee43db1b57175b13e","target":"record","created_at":"2026-07-05T09:19:57Z","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":"7d6ed8594b2ca07ffea5095cd9b2b0644d6d8ab25144a056b97ea31b8e6e6d72","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T15:24:27Z","title_canon_sha256":"9463b7be81dc4bbb4932edf87d12e7e1ba340ef70ef07a3e05f6a0ca64cd09b0"},"schema_version":"1.0","source":{"id":"2405.07838","kind":"arxiv","version":2}},"canonical_sha256":"f881e577b51b965d12a457f66ebc395ff9ae1744e292aedfa1af2857f2c95c26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f881e577b51b965d12a457f66ebc395ff9ae1744e292aedfa1af2857f2c95c26","first_computed_at":"2026-07-05T09:19:57.249613Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:57.249613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"db/fnSlYUR4ypBuykBzDvtvijQcwCkq57B0iy9Blqzg/4cMdbw63OH9V6gC2jnoPHWD9kupWnlnOyHeEX632Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:57.250052Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.07838","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89968bcb282288aa18081f53c420676b01b73f850928af5ee43db1b57175b13e","sha256:ada6e79dcf5cb569cf3dd1076e7fe445f369223314c148839176a7e9a631f02e"],"state_sha256":"0d4bc53ce296912d47a29524a1ddce33bbaca8e439b4761398c9987b405a3557"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oRhrzW7YmZ3EEQtA8Rub9X97ingRR6KtLEfuffwibaMqQtfuXgtDWiD98HEbI4Gu4sXPZYxHkzF7mF6c1SL2Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:52:28.769412Z","bundle_sha256":"54599e913a150846f5f12771e4ab38d7969c20ffa0a0e9ea3a50b30a27446e39"}}