{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2HFPKYXVONFVQ6LKYQVE73TFOD","short_pith_number":"pith:2HFPKYXV","canonical_record":{"source":{"id":"2307.13372","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-25T09:46:02Z","cross_cats_sorted":[],"title_canon_sha256":"9b59ebd8cdc9c7161872399ddaf7c0934d6392d92f0ad7b8b48b35c64b0e626e","abstract_canon_sha256":"a40468a4970ad2fa966535670f4959d16e0a75546c647fb304a0dc0d47c5e983"},"schema_version":"1.0"},"canonical_sha256":"d1caf562f5734b58796ac42a4fee6570d87cf1492efce3c5bfe54ca101c5a987","source":{"kind":"arxiv","id":"2307.13372","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.13372","created_at":"2026-07-05T08:22:32Z"},{"alias_kind":"arxiv_version","alias_value":"2307.13372v2","created_at":"2026-07-05T08:22:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13372","created_at":"2026-07-05T08:22:32Z"},{"alias_kind":"pith_short_12","alias_value":"2HFPKYXVONFV","created_at":"2026-07-05T08:22:32Z"},{"alias_kind":"pith_short_16","alias_value":"2HFPKYXVONFVQ6LK","created_at":"2026-07-05T08:22:32Z"},{"alias_kind":"pith_short_8","alias_value":"2HFPKYXV","created_at":"2026-07-05T08:22:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2HFPKYXVONFVQ6LKYQVE73TFOD","target":"record","payload":{"canonical_record":{"source":{"id":"2307.13372","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-25T09:46:02Z","cross_cats_sorted":[],"title_canon_sha256":"9b59ebd8cdc9c7161872399ddaf7c0934d6392d92f0ad7b8b48b35c64b0e626e","abstract_canon_sha256":"a40468a4970ad2fa966535670f4959d16e0a75546c647fb304a0dc0d47c5e983"},"schema_version":"1.0"},"canonical_sha256":"d1caf562f5734b58796ac42a4fee6570d87cf1492efce3c5bfe54ca101c5a987","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:32.579934Z","signature_b64":"4+zpSd20DPY6smtocLutGMNQrY7DW7EtrksGGdCM7lGqB1rpCP2t8peuNBbj4veGJdAFww600/is3WQLKr92AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1caf562f5734b58796ac42a4fee6570d87cf1492efce3c5bfe54ca101c5a987","last_reissued_at":"2026-07-05T08:22:32.579350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:32.579350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.13372","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":"2026-07-05T08:22:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wpUPsvRNF01104G8q51lGggyz/du6W2iXVXb4TyZ8tJHusoVGMFF3KjnhxDye7fvl4Ag0MtfWr3auiBb6bdNCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:41:54.626862Z"},"content_sha256":"6e5ccfffbee070a12ffe34b0ea5b80ee387c4b94992a153a5c6ffbb3761892e2","schema_version":"1.0","event_id":"sha256:6e5ccfffbee070a12ffe34b0ea5b80ee387c4b94992a153a5c6ffbb3761892e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2HFPKYXVONFVQ6LKYQVE73TFOD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Submodular Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Manish Prajapat, Melanie N. Zeilinger, Mojm\\'ir Mutn\\'y","submitted_at":"2023-07-25T09:46:02Z","abstract_excerpt":"In reinforcement learning (RL), rewards of states are typically considered additive, and following the Markov assumption, they are $\\textit{independent}$ of states visited previously. In many important applications, such as coverage control, experiment design and informative path planning, rewards naturally have diminishing returns, i.e., their value decreases in light of similar states visited previously. To tackle this, we propose $\\textit{submodular RL}$ (SubRL), a paradigm which seeks to optimize more general, non-additive (and history-dependent) rewards modelled via submodular set functio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13372","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/2307.13372/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":"2026-07-05T08:22:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"odr2CoMwfXwHFwjXk5gSfhESLdEU9oWH8LLqCvqLxVTwOFjXbjaaZyGxhTFQu3M34+Zr3MD9U/sVlfE1mO8JBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:41:54.627405Z"},"content_sha256":"873161eb0192f0c3a6cebc9e181204aa14231d7628895693de953e2eb6a5e89d","schema_version":"1.0","event_id":"sha256:873161eb0192f0c3a6cebc9e181204aa14231d7628895693de953e2eb6a5e89d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2HFPKYXVONFVQ6LKYQVE73TFOD/bundle.json","state_url":"https://pith.science/pith/2HFPKYXVONFVQ6LKYQVE73TFOD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2HFPKYXVONFVQ6LKYQVE73TFOD/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":"2026-08-17T21:41:54Z","links":{"resolver":"https://pith.science/pith/2HFPKYXVONFVQ6LKYQVE73TFOD","bundle":"https://pith.science/pith/2HFPKYXVONFVQ6LKYQVE73TFOD/bundle.json","state":"https://pith.science/pith/2HFPKYXVONFVQ6LKYQVE73TFOD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2HFPKYXVONFVQ6LKYQVE73TFOD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2HFPKYXVONFVQ6LKYQVE73TFOD","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":"a40468a4970ad2fa966535670f4959d16e0a75546c647fb304a0dc0d47c5e983","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-25T09:46:02Z","title_canon_sha256":"9b59ebd8cdc9c7161872399ddaf7c0934d6392d92f0ad7b8b48b35c64b0e626e"},"schema_version":"1.0","source":{"id":"2307.13372","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.13372","created_at":"2026-07-05T08:22:32Z"},{"alias_kind":"arxiv_version","alias_value":"2307.13372v2","created_at":"2026-07-05T08:22:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13372","created_at":"2026-07-05T08:22:32Z"},{"alias_kind":"pith_short_12","alias_value":"2HFPKYXVONFV","created_at":"2026-07-05T08:22:32Z"},{"alias_kind":"pith_short_16","alias_value":"2HFPKYXVONFVQ6LK","created_at":"2026-07-05T08:22:32Z"},{"alias_kind":"pith_short_8","alias_value":"2HFPKYXV","created_at":"2026-07-05T08:22:32Z"}],"graph_snapshots":[{"event_id":"sha256:873161eb0192f0c3a6cebc9e181204aa14231d7628895693de953e2eb6a5e89d","target":"graph","created_at":"2026-07-05T08:22:32Z","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/2307.13372/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning (RL), rewards of states are typically considered additive, and following the Markov assumption, they are $\\textit{independent}$ of states visited previously. In many important applications, such as coverage control, experiment design and informative path planning, rewards naturally have diminishing returns, i.e., their value decreases in light of similar states visited previously. To tackle this, we propose $\\textit{submodular RL}$ (SubRL), a paradigm which seeks to optimize more general, non-additive (and history-dependent) rewards modelled via submodular set functio","authors_text":"Andreas Krause, Manish Prajapat, Melanie N. Zeilinger, Mojm\\'ir Mutn\\'y","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-25T09:46:02Z","title":"Submodular Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13372","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":"sha256:6e5ccfffbee070a12ffe34b0ea5b80ee387c4b94992a153a5c6ffbb3761892e2","target":"record","created_at":"2026-07-05T08:22:32Z","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":"a40468a4970ad2fa966535670f4959d16e0a75546c647fb304a0dc0d47c5e983","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-25T09:46:02Z","title_canon_sha256":"9b59ebd8cdc9c7161872399ddaf7c0934d6392d92f0ad7b8b48b35c64b0e626e"},"schema_version":"1.0","source":{"id":"2307.13372","kind":"arxiv","version":2}},"canonical_sha256":"d1caf562f5734b58796ac42a4fee6570d87cf1492efce3c5bfe54ca101c5a987","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1caf562f5734b58796ac42a4fee6570d87cf1492efce3c5bfe54ca101c5a987","first_computed_at":"2026-07-05T08:22:32.579350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:32.579350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4+zpSd20DPY6smtocLutGMNQrY7DW7EtrksGGdCM7lGqB1rpCP2t8peuNBbj4veGJdAFww600/is3WQLKr92AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:32.579934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.13372","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e5ccfffbee070a12ffe34b0ea5b80ee387c4b94992a153a5c6ffbb3761892e2","sha256:873161eb0192f0c3a6cebc9e181204aa14231d7628895693de953e2eb6a5e89d"],"state_sha256":"fda89123f215e93e507f5cff8b4c5b15719326cfb53d175b788e7549e2b0f94f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NxjRsBBcmFjkPf/1mEaVEA4+X5jhOIXltji0Wzd5Kje5aWVzkterSs23RqqlNALx2MDiHzvIwqIJS4rH3VPgAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T21:41:54.631965Z","bundle_sha256":"9f6af5dba6862f8ad8b831469cac08b12132c93e383feda22796f63f0321b335"}}