{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:S7EJSVBF7JKYHL6WGN76LQ35BJ","short_pith_number":"pith:S7EJSVBF","canonical_record":{"source":{"id":"2507.13834","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-18T11:42:07Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"cc497b08f260622b1950e319ba1edbfb14dfe6c529e2a8ecbcfa20b105f43917","abstract_canon_sha256":"88628d423ff8b18ad229e22049ea7dacec3542e271674cfe4a8bc803633e4455"},"schema_version":"1.0"},"canonical_sha256":"97c8995425fa5583afd6337fe5c37d0a68797ca84c358a31e0bea10c40f6cf2a","source":{"kind":"arxiv","id":"2507.13834","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13834","created_at":"2026-07-05T11:39:24Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13834v1","created_at":"2026-07-05T11:39:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13834","created_at":"2026-07-05T11:39:24Z"},{"alias_kind":"pith_short_12","alias_value":"S7EJSVBF7JKY","created_at":"2026-07-05T11:39:24Z"},{"alias_kind":"pith_short_16","alias_value":"S7EJSVBF7JKYHL6W","created_at":"2026-07-05T11:39:24Z"},{"alias_kind":"pith_short_8","alias_value":"S7EJSVBF","created_at":"2026-07-05T11:39:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:S7EJSVBF7JKYHL6WGN76LQ35BJ","target":"record","payload":{"canonical_record":{"source":{"id":"2507.13834","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-18T11:42:07Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"cc497b08f260622b1950e319ba1edbfb14dfe6c529e2a8ecbcfa20b105f43917","abstract_canon_sha256":"88628d423ff8b18ad229e22049ea7dacec3542e271674cfe4a8bc803633e4455"},"schema_version":"1.0"},"canonical_sha256":"97c8995425fa5583afd6337fe5c37d0a68797ca84c358a31e0bea10c40f6cf2a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:24.072142Z","signature_b64":"usjdPj3Ib4deJK8BMbfcDUlz0FzSobwPvqloXKRT8ZrKnNtcPfgkHFy3yU+ISD2wM9njttrTzTPvpmTlYWIXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97c8995425fa5583afd6337fe5c37d0a68797ca84c358a31e0bea10c40f6cf2a","last_reissued_at":"2026-07-05T11:39:24.071502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:24.071502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.13834","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":"2026-07-05T11:39:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WgVrOQLzQ4K3jNO5Df1sPvHBRQQu2jVlY2vtXp9rIPBSvSwLyE3RxdYU4Kf9txPLYkRnLnT2PTnYLOKthSKfAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T21:28:50.291996Z"},"content_sha256":"b487f8927846a9415549afe6e9ab2d470cc8c43153775f8cb9f56081e9618e25","schema_version":"1.0","event_id":"sha256:b487f8927846a9415549afe6e9ab2d470cc8c43153775f8cb9f56081e9618e25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:S7EJSVBF7JKYHL6WGN76LQ35BJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable Submodular Policy Optimization via Pruned Submodularity Graph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Aditi Anand, Dildar Ali, Suman Banerjee","submitted_at":"2025-07-18T11:42:07Z","abstract_excerpt":"In Reinforcement Learning (abbreviated as RL), an agent interacts with the environment via a set of possible actions, and a reward is generated from some unknown distribution. The task here is to find an optimal set of actions such that the reward after a certain time step gets maximized. In a traditional setup, the reward function in an RL Problem is considered additive. However, in reality, there exist many problems, including path planning, coverage control, etc., the reward function follows the diminishing return, which can be modeled as a submodular function. In this paper, we study a var"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13834","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/2507.13834/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":"2026-07-05T11:39:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gi7BVQH3RRaVY+lKqmL1QQguKNzApIz9DVyLrCNVUagYuVRBVB76BYL9FCrJYxgfc5z7R6bohkFFvzYZ3boEDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T21:28:50.292558Z"},"content_sha256":"e525b3a61b2ef1ecbb0eb92b20a4ff3d357c05112562808be144eb7eb2d366a8","schema_version":"1.0","event_id":"sha256:e525b3a61b2ef1ecbb0eb92b20a4ff3d357c05112562808be144eb7eb2d366a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S7EJSVBF7JKYHL6WGN76LQ35BJ/bundle.json","state_url":"https://pith.science/pith/S7EJSVBF7JKYHL6WGN76LQ35BJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S7EJSVBF7JKYHL6WGN76LQ35BJ/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":"2026-08-16T21:28:50Z","links":{"resolver":"https://pith.science/pith/S7EJSVBF7JKYHL6WGN76LQ35BJ","bundle":"https://pith.science/pith/S7EJSVBF7JKYHL6WGN76LQ35BJ/bundle.json","state":"https://pith.science/pith/S7EJSVBF7JKYHL6WGN76LQ35BJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S7EJSVBF7JKYHL6WGN76LQ35BJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:S7EJSVBF7JKYHL6WGN76LQ35BJ","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":"88628d423ff8b18ad229e22049ea7dacec3542e271674cfe4a8bc803633e4455","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-18T11:42:07Z","title_canon_sha256":"cc497b08f260622b1950e319ba1edbfb14dfe6c529e2a8ecbcfa20b105f43917"},"schema_version":"1.0","source":{"id":"2507.13834","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13834","created_at":"2026-07-05T11:39:24Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13834v1","created_at":"2026-07-05T11:39:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13834","created_at":"2026-07-05T11:39:24Z"},{"alias_kind":"pith_short_12","alias_value":"S7EJSVBF7JKY","created_at":"2026-07-05T11:39:24Z"},{"alias_kind":"pith_short_16","alias_value":"S7EJSVBF7JKYHL6W","created_at":"2026-07-05T11:39:24Z"},{"alias_kind":"pith_short_8","alias_value":"S7EJSVBF","created_at":"2026-07-05T11:39:24Z"}],"graph_snapshots":[{"event_id":"sha256:e525b3a61b2ef1ecbb0eb92b20a4ff3d357c05112562808be144eb7eb2d366a8","target":"graph","created_at":"2026-07-05T11:39:24Z","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/2507.13834/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Reinforcement Learning (abbreviated as RL), an agent interacts with the environment via a set of possible actions, and a reward is generated from some unknown distribution. The task here is to find an optimal set of actions such that the reward after a certain time step gets maximized. In a traditional setup, the reward function in an RL Problem is considered additive. However, in reality, there exist many problems, including path planning, coverage control, etc., the reward function follows the diminishing return, which can be modeled as a submodular function. In this paper, we study a var","authors_text":"Aditi Anand, Dildar Ali, Suman Banerjee","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-18T11:42:07Z","title":"Scalable Submodular Policy Optimization via Pruned Submodularity Graph"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13834","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:b487f8927846a9415549afe6e9ab2d470cc8c43153775f8cb9f56081e9618e25","target":"record","created_at":"2026-07-05T11:39:24Z","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":"88628d423ff8b18ad229e22049ea7dacec3542e271674cfe4a8bc803633e4455","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-18T11:42:07Z","title_canon_sha256":"cc497b08f260622b1950e319ba1edbfb14dfe6c529e2a8ecbcfa20b105f43917"},"schema_version":"1.0","source":{"id":"2507.13834","kind":"arxiv","version":1}},"canonical_sha256":"97c8995425fa5583afd6337fe5c37d0a68797ca84c358a31e0bea10c40f6cf2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97c8995425fa5583afd6337fe5c37d0a68797ca84c358a31e0bea10c40f6cf2a","first_computed_at":"2026-07-05T11:39:24.071502Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:24.071502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"usjdPj3Ib4deJK8BMbfcDUlz0FzSobwPvqloXKRT8ZrKnNtcPfgkHFy3yU+ISD2wM9njttrTzTPvpmTlYWIXAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:24.072142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.13834","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b487f8927846a9415549afe6e9ab2d470cc8c43153775f8cb9f56081e9618e25","sha256:e525b3a61b2ef1ecbb0eb92b20a4ff3d357c05112562808be144eb7eb2d366a8"],"state_sha256":"2ac5d3912e57bf704cbc0a9583508d38ed581041c051253d258e19f76e5525ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ah3PRljQStGrYAQx7FuII1lAKGvL/uGwxn3ZzssXhBP4EZXXl1qKAT4/ibky65OgpI2jfsF6VViHrmIyMVL2AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T21:28:50.297198Z","bundle_sha256":"6b81d109acb899da4e4542eea5517a08a9b4b9c7b50982f3bebe298d1787266f"}}