{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IDVMLM6ZJWUHIHMXULEPBSSCB3","short_pith_number":"pith:IDVMLM6Z","schema_version":"1.0","canonical_sha256":"40eac5b3d94da8741d97a2c8f0ca420ee505207e98c2d78529c3f6c003c7630e","source":{"kind":"arxiv","id":"2010.11863","version":1},"attestation_state":"computed","paper":{"title":"Planning with Submodular Objective Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Denis Garagi\\'c, Devendra Singh Chaplot, Hanrui Zhang, Ruosong Wang, Ruslan Salakhutdinov","submitted_at":"2020-10-22T16:55:12Z","abstract_excerpt":"We study planning with submodular objective functions, where instead of maximizing the cumulative reward, the goal is to maximize the objective value induced by a submodular function. Our framework subsumes standard planning and submodular maximization with cardinality constraints as special cases, and thus many practical applications can be naturally formulated within our framework. Based on the notion of multilinear extension, we propose a novel and theoretically principled algorithmic framework for planning with submodular objective functions, which recovers classical algorithms when applie"},"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":"2010.11863","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-10-22T16:55:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"00d228328b3d008720030b987daf85dfb1ac7005795eecd102c68c114f482002","abstract_canon_sha256":"5ccbe78523721f6547f924c727b49e9e59244625493e8900ede95ed501764276"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:21.639432Z","signature_b64":"9bBtvX1mhy35qiWYaZXO5rV4WgB7OMe8zeXAr8eZHR3jHUrRojQ8d+LhAGAmdkhdjqSlczGHFhSodRomsXK0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40eac5b3d94da8741d97a2c8f0ca420ee505207e98c2d78529c3f6c003c7630e","last_reissued_at":"2026-07-05T01:45:21.638971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:21.638971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Planning with Submodular Objective Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Denis Garagi\\'c, Devendra Singh Chaplot, Hanrui Zhang, Ruosong Wang, Ruslan Salakhutdinov","submitted_at":"2020-10-22T16:55:12Z","abstract_excerpt":"We study planning with submodular objective functions, where instead of maximizing the cumulative reward, the goal is to maximize the objective value induced by a submodular function. Our framework subsumes standard planning and submodular maximization with cardinality constraints as special cases, and thus many practical applications can be naturally formulated within our framework. Based on the notion of multilinear extension, we propose a novel and theoretically principled algorithmic framework for planning with submodular objective functions, which recovers classical algorithms when applie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11863","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/2010.11863/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":"2010.11863","created_at":"2026-07-05T01:45:21.639031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.11863v1","created_at":"2026-07-05T01:45:21.639031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11863","created_at":"2026-07-05T01:45:21.639031+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDVMLM6ZJWUH","created_at":"2026-07-05T01:45:21.639031+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDVMLM6ZJWUHIHMX","created_at":"2026-07-05T01:45:21.639031+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDVMLM6Z","created_at":"2026-07-05T01:45:21.639031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18531","citing_title":"When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IDVMLM6ZJWUHIHMXULEPBSSCB3","json":"https://pith.science/pith/IDVMLM6ZJWUHIHMXULEPBSSCB3.json","graph_json":"https://pith.science/api/pith-number/IDVMLM6ZJWUHIHMXULEPBSSCB3/graph.json","events_json":"https://pith.science/api/pith-number/IDVMLM6ZJWUHIHMXULEPBSSCB3/events.json","paper":"https://pith.science/paper/IDVMLM6Z"},"agent_actions":{"view_html":"https://pith.science/pith/IDVMLM6ZJWUHIHMXULEPBSSCB3","download_json":"https://pith.science/pith/IDVMLM6ZJWUHIHMXULEPBSSCB3.json","view_paper":"https://pith.science/paper/IDVMLM6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.11863&json=true","fetch_graph":"https://pith.science/api/pith-number/IDVMLM6ZJWUHIHMXULEPBSSCB3/graph.json","fetch_events":"https://pith.science/api/pith-number/IDVMLM6ZJWUHIHMXULEPBSSCB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDVMLM6ZJWUHIHMXULEPBSSCB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDVMLM6ZJWUHIHMXULEPBSSCB3/action/storage_attestation","attest_author":"https://pith.science/pith/IDVMLM6ZJWUHIHMXULEPBSSCB3/action/author_attestation","sign_citation":"https://pith.science/pith/IDVMLM6ZJWUHIHMXULEPBSSCB3/action/citation_signature","submit_replication":"https://pith.science/pith/IDVMLM6ZJWUHIHMXULEPBSSCB3/action/replication_record"}},"created_at":"2026-07-05T01:45:21.639031+00:00","updated_at":"2026-07-05T01:45:21.639031+00:00"}