{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S7EJSVBF7JKYHL6WGN76LQ35BJ","short_pith_number":"pith:S7EJSVBF","schema_version":"1.0","canonical_sha256":"97c8995425fa5583afd6337fe5c37d0a68797ca84c358a31e0bea10c40f6cf2a","source":{"kind":"arxiv","id":"2507.13834","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.13834","created_at":"2026-07-05T11:39:24.071581+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13834v1","created_at":"2026-07-05T11:39:24.071581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13834","created_at":"2026-07-05T11:39:24.071581+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7EJSVBF7JKY","created_at":"2026-07-05T11:39:24.071581+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7EJSVBF7JKYHL6W","created_at":"2026-07-05T11:39:24.071581+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7EJSVBF","created_at":"2026-07-05T11:39:24.071581+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S7EJSVBF7JKYHL6WGN76LQ35BJ","json":"https://pith.science/pith/S7EJSVBF7JKYHL6WGN76LQ35BJ.json","graph_json":"https://pith.science/api/pith-number/S7EJSVBF7JKYHL6WGN76LQ35BJ/graph.json","events_json":"https://pith.science/api/pith-number/S7EJSVBF7JKYHL6WGN76LQ35BJ/events.json","paper":"https://pith.science/paper/S7EJSVBF"},"agent_actions":{"view_html":"https://pith.science/pith/S7EJSVBF7JKYHL6WGN76LQ35BJ","download_json":"https://pith.science/pith/S7EJSVBF7JKYHL6WGN76LQ35BJ.json","view_paper":"https://pith.science/paper/S7EJSVBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13834&json=true","fetch_graph":"https://pith.science/api/pith-number/S7EJSVBF7JKYHL6WGN76LQ35BJ/graph.json","fetch_events":"https://pith.science/api/pith-number/S7EJSVBF7JKYHL6WGN76LQ35BJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7EJSVBF7JKYHL6WGN76LQ35BJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7EJSVBF7JKYHL6WGN76LQ35BJ/action/storage_attestation","attest_author":"https://pith.science/pith/S7EJSVBF7JKYHL6WGN76LQ35BJ/action/author_attestation","sign_citation":"https://pith.science/pith/S7EJSVBF7JKYHL6WGN76LQ35BJ/action/citation_signature","submit_replication":"https://pith.science/pith/S7EJSVBF7JKYHL6WGN76LQ35BJ/action/replication_record"}},"created_at":"2026-07-05T11:39:24.071581+00:00","updated_at":"2026-07-05T11:39:24.071581+00:00"}