{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KW5NAKUZX5SXELGUCYQCU7PXUO","short_pith_number":"pith:KW5NAKUZ","schema_version":"1.0","canonical_sha256":"55bad02a99bf65722cd416202a7df7a3b103ccf6ce6b4108522154d8521e761b","source":{"kind":"arxiv","id":"2606.21604","version":1},"attestation_state":"computed","paper":{"title":"Learning to Place Guards by Reinforcement: A Geo-Free Neural Policy for the Vertex-Guard Art Gallery Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CG"],"primary_cat":"cs.LG","authors_text":"Domagoj Matijevi\\'c, Domagoj \\v{S}everdija, Jurica Maltar, Nathan Chappel","submitted_at":"2026-06-19T17:06:58Z","abstract_excerpt":"Neural combinatorial optimization (NCO) has shown that policies trained by reinforcement can construct strong solutions to NP-hard problems directly from raw instances. What such a policy actually learns, as opposed to what its decoder expresses, remains much less clear. We study this distinction on the vertex-guard Art Gallery Problem, the NP-hard task of choosing polygon vertices from which to observe an entire region. A pointer-network policy is trained from a coverage-aware reward over its own rollouts under the constraint we call geo-free inference: at test time it sees only vertex coordi"},"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":"2606.21604","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T17:06:58Z","cross_cats_sorted":["cs.CG"],"title_canon_sha256":"099161a1c72db4223b87021cc1cf67cfdbeb4f1395e339992262095ad9e19650","abstract_canon_sha256":"79591765f3eaa79a9245493c7fe93f48c088b52d91268f21af220feae3147b2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:16.014955Z","signature_b64":"3aOJEGDfhn9lwTSRfndLSrYDmvLvdcn/mTbOsGqru41+mnMf7wmhn2StDYrBUbkUTxDBKLBSyzTIqIRtfKmaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55bad02a99bf65722cd416202a7df7a3b103ccf6ce6b4108522154d8521e761b","last_reissued_at":"2026-06-23T01:13:16.014475Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:16.014475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Place Guards by Reinforcement: A Geo-Free Neural Policy for the Vertex-Guard Art Gallery Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CG"],"primary_cat":"cs.LG","authors_text":"Domagoj Matijevi\\'c, Domagoj \\v{S}everdija, Jurica Maltar, Nathan Chappel","submitted_at":"2026-06-19T17:06:58Z","abstract_excerpt":"Neural combinatorial optimization (NCO) has shown that policies trained by reinforcement can construct strong solutions to NP-hard problems directly from raw instances. What such a policy actually learns, as opposed to what its decoder expresses, remains much less clear. We study this distinction on the vertex-guard Art Gallery Problem, the NP-hard task of choosing polygon vertices from which to observe an entire region. A pointer-network policy is trained from a coverage-aware reward over its own rollouts under the constraint we call geo-free inference: at test time it sees only vertex coordi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21604","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/2606.21604/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":"2606.21604","created_at":"2026-06-23T01:13:16.014549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21604v1","created_at":"2026-06-23T01:13:16.014549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21604","created_at":"2026-06-23T01:13:16.014549+00:00"},{"alias_kind":"pith_short_12","alias_value":"KW5NAKUZX5SX","created_at":"2026-06-23T01:13:16.014549+00:00"},{"alias_kind":"pith_short_16","alias_value":"KW5NAKUZX5SXELGU","created_at":"2026-06-23T01:13:16.014549+00:00"},{"alias_kind":"pith_short_8","alias_value":"KW5NAKUZ","created_at":"2026-06-23T01:13:16.014549+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/KW5NAKUZX5SXELGUCYQCU7PXUO","json":"https://pith.science/pith/KW5NAKUZX5SXELGUCYQCU7PXUO.json","graph_json":"https://pith.science/api/pith-number/KW5NAKUZX5SXELGUCYQCU7PXUO/graph.json","events_json":"https://pith.science/api/pith-number/KW5NAKUZX5SXELGUCYQCU7PXUO/events.json","paper":"https://pith.science/paper/KW5NAKUZ"},"agent_actions":{"view_html":"https://pith.science/pith/KW5NAKUZX5SXELGUCYQCU7PXUO","download_json":"https://pith.science/pith/KW5NAKUZX5SXELGUCYQCU7PXUO.json","view_paper":"https://pith.science/paper/KW5NAKUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21604&json=true","fetch_graph":"https://pith.science/api/pith-number/KW5NAKUZX5SXELGUCYQCU7PXUO/graph.json","fetch_events":"https://pith.science/api/pith-number/KW5NAKUZX5SXELGUCYQCU7PXUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KW5NAKUZX5SXELGUCYQCU7PXUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KW5NAKUZX5SXELGUCYQCU7PXUO/action/storage_attestation","attest_author":"https://pith.science/pith/KW5NAKUZX5SXELGUCYQCU7PXUO/action/author_attestation","sign_citation":"https://pith.science/pith/KW5NAKUZX5SXELGUCYQCU7PXUO/action/citation_signature","submit_replication":"https://pith.science/pith/KW5NAKUZX5SXELGUCYQCU7PXUO/action/replication_record"}},"created_at":"2026-06-23T01:13:16.014549+00:00","updated_at":"2026-06-23T01:13:16.014549+00:00"}