{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q6MSA36KAJC25SAPNQHD4Q4VEO","short_pith_number":"pith:Q6MSA36K","schema_version":"1.0","canonical_sha256":"8799206fca0245aec80f6c0e3e4395239b47dd0ac708485bc590760e85911e16","source":{"kind":"arxiv","id":"2405.06672","version":2},"attestation_state":"computed","paper":{"title":"Liouville Flow Importance Sampler","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","math.PR","physics.data-an","stat.CO"],"primary_cat":"stat.ML","authors_text":"Nishant Panda, Yen Ting Lin, Yifeng Tian","submitted_at":"2024-05-03T16:44:31Z","abstract_excerpt":"We present the Liouville Flow Importance Sampler (LFIS), an innovative flow-based model for generating samples from unnormalized density functions. LFIS learns a time-dependent velocity field that deterministically transports samples from a simple initial distribution to a complex target distribution, guided by a prescribed path of annealed distributions. The training of LFIS utilizes a unique method that enforces the structure of a derived partial differential equation to neural networks modeling velocity fields. By considering the neural velocity field as an importance sampler, sample weight"},"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":"2405.06672","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-03T16:44:31Z","cross_cats_sorted":["cs.LG","math.PR","physics.data-an","stat.CO"],"title_canon_sha256":"5be9425eaaadaeddf99d4d210c4210a37a8dc69c498bccc4c08d4a721bae32a8","abstract_canon_sha256":"a26bf6e1031d82387269f5da8a44cc51ac5fbb681afd45f905a38ce5501244eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:25.998992Z","signature_b64":"9RHpyxRuAW2GFmZlCpEwAl+KW3r72gXuZF4NjeihU8sKu6JpgpZWtlsjjr5NkJBoTHSuevlA+IkZz/uy3AR4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8799206fca0245aec80f6c0e3e4395239b47dd0ac708485bc590760e85911e16","last_reissued_at":"2026-07-05T08:29:25.998407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:25.998407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Liouville Flow Importance Sampler","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","math.PR","physics.data-an","stat.CO"],"primary_cat":"stat.ML","authors_text":"Nishant Panda, Yen Ting Lin, Yifeng Tian","submitted_at":"2024-05-03T16:44:31Z","abstract_excerpt":"We present the Liouville Flow Importance Sampler (LFIS), an innovative flow-based model for generating samples from unnormalized density functions. LFIS learns a time-dependent velocity field that deterministically transports samples from a simple initial distribution to a complex target distribution, guided by a prescribed path of annealed distributions. The training of LFIS utilizes a unique method that enforces the structure of a derived partial differential equation to neural networks modeling velocity fields. By considering the neural velocity field as an importance sampler, sample weight"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.06672","kind":"arxiv","version":2},"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/2405.06672/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":"2405.06672","created_at":"2026-07-05T08:29:25.998547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.06672v2","created_at":"2026-07-05T08:29:25.998547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.06672","created_at":"2026-07-05T08:29:25.998547+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q6MSA36KAJC2","created_at":"2026-07-05T08:29:25.998547+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q6MSA36KAJC25SAP","created_at":"2026-07-05T08:29:25.998547+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q6MSA36K","created_at":"2026-07-05T08:29:25.998547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24959","citing_title":"CoreFlow: Low-Rank Matrix Generative Models","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q6MSA36KAJC25SAPNQHD4Q4VEO","json":"https://pith.science/pith/Q6MSA36KAJC25SAPNQHD4Q4VEO.json","graph_json":"https://pith.science/api/pith-number/Q6MSA36KAJC25SAPNQHD4Q4VEO/graph.json","events_json":"https://pith.science/api/pith-number/Q6MSA36KAJC25SAPNQHD4Q4VEO/events.json","paper":"https://pith.science/paper/Q6MSA36K"},"agent_actions":{"view_html":"https://pith.science/pith/Q6MSA36KAJC25SAPNQHD4Q4VEO","download_json":"https://pith.science/pith/Q6MSA36KAJC25SAPNQHD4Q4VEO.json","view_paper":"https://pith.science/paper/Q6MSA36K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.06672&json=true","fetch_graph":"https://pith.science/api/pith-number/Q6MSA36KAJC25SAPNQHD4Q4VEO/graph.json","fetch_events":"https://pith.science/api/pith-number/Q6MSA36KAJC25SAPNQHD4Q4VEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q6MSA36KAJC25SAPNQHD4Q4VEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q6MSA36KAJC25SAPNQHD4Q4VEO/action/storage_attestation","attest_author":"https://pith.science/pith/Q6MSA36KAJC25SAPNQHD4Q4VEO/action/author_attestation","sign_citation":"https://pith.science/pith/Q6MSA36KAJC25SAPNQHD4Q4VEO/action/citation_signature","submit_replication":"https://pith.science/pith/Q6MSA36KAJC25SAPNQHD4Q4VEO/action/replication_record"}},"created_at":"2026-07-05T08:29:25.998547+00:00","updated_at":"2026-07-05T08:29:25.998547+00:00"}