{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HEKUDQN65QXLT3T6GN4Y3DAYDI","short_pith_number":"pith:HEKUDQN6","schema_version":"1.0","canonical_sha256":"391541c1beec2eb9ee7e33798d8c181a1bef8af8db475ef4ee7a45eeddf18ace","source":{"kind":"arxiv","id":"2604.19355","version":2},"attestation_state":"computed","paper":{"title":"LASER: Learning Active Sensing for Continuum Field Reconstruction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"A reinforcement learning policy trained inside a latent model of physical dynamics can adapt sensor movements to reconstruct continuum fields from sparse measurements more accurately than fixed layouts.","cross_cats":["cs.AI","cs.CE"],"primary_cat":"cs.LG","authors_text":"Huayu Deng, Jinghui Zhong, Xiangming Zhu, Xiaokang Yang, Yunbo Wang","submitted_at":"2026-04-21T11:36:09Z","abstract_excerpt":"High-fidelity measurements of continuum physical fields are essential for scientific discovery and engineering design but remain challenging under sparse and constrained sensing. Conventional reconstruction methods typically rely on fixed sensor layouts, which cannot adapt to evolving physical states. We propose LASER, a unified, closed-loop framework that formulates active sensing as a Partially Observable Markov Decision Process (POMDP). At its core, LASER employs a continuum field latent world model that captures the underlying physical dynamics and provides intrinsic reward feedback. This "},"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":"2604.19355","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-21T11:36:09Z","cross_cats_sorted":["cs.AI","cs.CE"],"title_canon_sha256":"d20ff0090faee95bb16e7e471fc53dfac09a240875ab4cda62fe93587f3a8ec2","abstract_canon_sha256":"1a50d8551c48219505a11e8df58d2532ea27968ddc6957fdb0ed60fa94b27e21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:40.554955Z","signature_b64":"yBlNBplKgCVIpYuoX5CKCfsJe4AZ19OZGPeHDAFSczRs5bhRrLr/Rh6wBu4datcFEIsk4ib2xxceduYS141UCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"391541c1beec2eb9ee7e33798d8c181a1bef8af8db475ef4ee7a45eeddf18ace","last_reissued_at":"2026-05-28T01:04:40.554379Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:40.554379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LASER: Learning Active Sensing for Continuum Field Reconstruction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"A reinforcement learning policy trained inside a latent model of physical dynamics can adapt sensor movements to reconstruct continuum fields from sparse measurements more accurately than fixed layouts.","cross_cats":["cs.AI","cs.CE"],"primary_cat":"cs.LG","authors_text":"Huayu Deng, Jinghui Zhong, Xiangming Zhu, Xiaokang Yang, Yunbo Wang","submitted_at":"2026-04-21T11:36:09Z","abstract_excerpt":"High-fidelity measurements of continuum physical fields are essential for scientific discovery and engineering design but remain challenging under sparse and constrained sensing. Conventional reconstruction methods typically rely on fixed sensor layouts, which cannot adapt to evolving physical states. We propose LASER, a unified, closed-loop framework that formulates active sensing as a Partially Observable Markov Decision Process (POMDP). At its core, LASER employs a continuum field latent world model that captures the underlying physical dynamics and provides intrinsic reward feedback. This "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"LASER consistently outperforms static and offline-optimized strategies, achieving high-fidelity reconstruction under sparsity across diverse continuum fields.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the learned continuum field latent world model provides sufficiently accurate intrinsic reward feedback and 'what-if' predictions to train a policy that transfers to real sensing scenarios.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LASER trains a reinforcement learning policy inside a latent dynamics model to choose sensor placements that improve reconstruction of continuum fields under sparsity.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A reinforcement learning policy trained inside a latent model of physical dynamics can adapt sensor movements to reconstruct continuum fields from sparse measurements more accurately than fixed layouts.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3c23881a8266099ea20131910361cb489b2ee0b20f52462d5179ef0f7f4186e0"},"source":{"id":"2604.19355","kind":"arxiv","version":2},"verdict":{"id":"f34a40f7-73ec-4990-8b2d-8413418e5005","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T03:32:38.091215Z","strongest_claim":"LASER consistently outperforms static and offline-optimized strategies, achieving high-fidelity reconstruction under sparsity across diverse continuum fields.","one_line_summary":"LASER trains a reinforcement learning policy inside a latent dynamics model to choose sensor placements that improve reconstruction of continuum fields under sparsity.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the learned continuum field latent world model provides sufficiently accurate intrinsic reward feedback and 'what-if' predictions to train a policy that transfers to real sensing scenarios.","pith_extraction_headline":"A reinforcement learning policy trained inside a latent model of physical dynamics can adapt sensor movements to reconstruct continuum fields from sparse measurements more accurately than fixed layouts."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.19355/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-20T03:04:23.450561Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"8737f6cbfbec8f2bd03d38e3b9ec63c20a61173c30fc7b321dc5640334004609"},"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":"2604.19355","created_at":"2026-05-28T01:04:40.554434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.19355v2","created_at":"2026-05-28T01:04:40.554434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.19355","created_at":"2026-05-28T01:04:40.554434+00:00"},{"alias_kind":"pith_short_12","alias_value":"HEKUDQN65QXL","created_at":"2026-05-28T01:04:40.554434+00:00"},{"alias_kind":"pith_short_16","alias_value":"HEKUDQN65QXLT3T6","created_at":"2026-05-28T01:04:40.554434+00:00"},{"alias_kind":"pith_short_8","alias_value":"HEKUDQN6","created_at":"2026-05-28T01:04:40.554434+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/HEKUDQN65QXLT3T6GN4Y3DAYDI","json":"https://pith.science/pith/HEKUDQN65QXLT3T6GN4Y3DAYDI.json","graph_json":"https://pith.science/api/pith-number/HEKUDQN65QXLT3T6GN4Y3DAYDI/graph.json","events_json":"https://pith.science/api/pith-number/HEKUDQN65QXLT3T6GN4Y3DAYDI/events.json","paper":"https://pith.science/paper/HEKUDQN6"},"agent_actions":{"view_html":"https://pith.science/pith/HEKUDQN65QXLT3T6GN4Y3DAYDI","download_json":"https://pith.science/pith/HEKUDQN65QXLT3T6GN4Y3DAYDI.json","view_paper":"https://pith.science/paper/HEKUDQN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.19355&json=true","fetch_graph":"https://pith.science/api/pith-number/HEKUDQN65QXLT3T6GN4Y3DAYDI/graph.json","fetch_events":"https://pith.science/api/pith-number/HEKUDQN65QXLT3T6GN4Y3DAYDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HEKUDQN65QXLT3T6GN4Y3DAYDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HEKUDQN65QXLT3T6GN4Y3DAYDI/action/storage_attestation","attest_author":"https://pith.science/pith/HEKUDQN65QXLT3T6GN4Y3DAYDI/action/author_attestation","sign_citation":"https://pith.science/pith/HEKUDQN65QXLT3T6GN4Y3DAYDI/action/citation_signature","submit_replication":"https://pith.science/pith/HEKUDQN65QXLT3T6GN4Y3DAYDI/action/replication_record"}},"created_at":"2026-05-28T01:04:40.554434+00:00","updated_at":"2026-05-28T01:04:40.554434+00:00"}