{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XA6FSVW5Y6PBV2MYQ7T7KXFZWX","short_pith_number":"pith:XA6FSVW5","schema_version":"1.0","canonical_sha256":"b83c5956ddc79e1ae99887e7f55cb9b5eb8c0132b85f7b736b3aca9bde2a40fa","source":{"kind":"arxiv","id":"2406.01853","version":1},"attestation_state":"computed","paper":{"title":"Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Ali Kamen, Dorin Comaniciu, Esa Kuusela, Florin C. Ghesu, Martin Kraus, Riqiang Gao, Shahab Basiri, Simon Arberet","submitted_at":"2024-06-03T23:55:20Z","abstract_excerpt":"In contemporary radiotherapy planning (RTP), a key module leaf sequencing is predominantly addressed by optimization-based approaches. In this paper, we propose a novel deep reinforcement learning (DRL) model termed as Reinforced Leaf Sequencer (RLS) in a multi-agent framework for leaf sequencing. The RLS model offers improvements to time-consuming iterative optimization steps via large-scale training and can control movement patterns through the design of reward mechanisms. We have conducted experiments on four datasets with four metrics and compared our model with a leading optimization sequ"},"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":"2406.01853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T23:55:20Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"011c88a578a5eb4318981c47e231054f45afe19c2435ad30bc8ad98480501bc3","abstract_canon_sha256":"10632d88d1e7d1f8a6056d62f0b3c2921569675bf4ebdae62a915bc50a7411ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:49.538750Z","signature_b64":"/wKbBQ2tdIkHD3K74hs4HHHk2ofuSjp11IGprTiMCJBZiqJs8SLzwP1ZfFZ7nLKY98/2WG1BVMenJYhYE1BWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b83c5956ddc79e1ae99887e7f55cb9b5eb8c0132b85f7b736b3aca9bde2a40fa","last_reissued_at":"2026-07-05T08:26:49.538266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:49.538266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Ali Kamen, Dorin Comaniciu, Esa Kuusela, Florin C. Ghesu, Martin Kraus, Riqiang Gao, Shahab Basiri, Simon Arberet","submitted_at":"2024-06-03T23:55:20Z","abstract_excerpt":"In contemporary radiotherapy planning (RTP), a key module leaf sequencing is predominantly addressed by optimization-based approaches. In this paper, we propose a novel deep reinforcement learning (DRL) model termed as Reinforced Leaf Sequencer (RLS) in a multi-agent framework for leaf sequencing. The RLS model offers improvements to time-consuming iterative optimization steps via large-scale training and can control movement patterns through the design of reward mechanisms. We have conducted experiments on four datasets with four metrics and compared our model with a leading optimization sequ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01853","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/2406.01853/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":"2406.01853","created_at":"2026-07-05T08:26:49.538355+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01853v1","created_at":"2026-07-05T08:26:49.538355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01853","created_at":"2026-07-05T08:26:49.538355+00:00"},{"alias_kind":"pith_short_12","alias_value":"XA6FSVW5Y6PB","created_at":"2026-07-05T08:26:49.538355+00:00"},{"alias_kind":"pith_short_16","alias_value":"XA6FSVW5Y6PBV2MY","created_at":"2026-07-05T08:26:49.538355+00:00"},{"alias_kind":"pith_short_8","alias_value":"XA6FSVW5","created_at":"2026-07-05T08:26:49.538355+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09622","citing_title":"Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Study","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XA6FSVW5Y6PBV2MYQ7T7KXFZWX","json":"https://pith.science/pith/XA6FSVW5Y6PBV2MYQ7T7KXFZWX.json","graph_json":"https://pith.science/api/pith-number/XA6FSVW5Y6PBV2MYQ7T7KXFZWX/graph.json","events_json":"https://pith.science/api/pith-number/XA6FSVW5Y6PBV2MYQ7T7KXFZWX/events.json","paper":"https://pith.science/paper/XA6FSVW5"},"agent_actions":{"view_html":"https://pith.science/pith/XA6FSVW5Y6PBV2MYQ7T7KXFZWX","download_json":"https://pith.science/pith/XA6FSVW5Y6PBV2MYQ7T7KXFZWX.json","view_paper":"https://pith.science/paper/XA6FSVW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01853&json=true","fetch_graph":"https://pith.science/api/pith-number/XA6FSVW5Y6PBV2MYQ7T7KXFZWX/graph.json","fetch_events":"https://pith.science/api/pith-number/XA6FSVW5Y6PBV2MYQ7T7KXFZWX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XA6FSVW5Y6PBV2MYQ7T7KXFZWX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XA6FSVW5Y6PBV2MYQ7T7KXFZWX/action/storage_attestation","attest_author":"https://pith.science/pith/XA6FSVW5Y6PBV2MYQ7T7KXFZWX/action/author_attestation","sign_citation":"https://pith.science/pith/XA6FSVW5Y6PBV2MYQ7T7KXFZWX/action/citation_signature","submit_replication":"https://pith.science/pith/XA6FSVW5Y6PBV2MYQ7T7KXFZWX/action/replication_record"}},"created_at":"2026-07-05T08:26:49.538355+00:00","updated_at":"2026-07-05T08:26:49.538355+00:00"}