{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NNRWHVJ5VRTB5HETIEXMOTTV6G","short_pith_number":"pith:NNRWHVJ5","schema_version":"1.0","canonical_sha256":"6b6363d53dac661e9c93412ec74e75f1aedb6907f784f7dd7a67e20d074de3e0","source":{"kind":"arxiv","id":"2502.02150","version":3},"attestation_state":"computed","paper":{"title":"On the Guidance of Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenglei Yu, Peiyan Hu, Ruiqi Feng, Tailin Wu, Wenhao Deng","submitted_at":"2025-02-04T09:27:57Z","abstract_excerpt":"Flow matching has shown state-of-the-art performance in various generative tasks, ranging from image generation to decision-making, where generation under energy guidance (abbreviated as guidance in the following) is pivotal. However, the guidance of flow matching is more general than and thus substantially different from that of its predecessor, diffusion models. Therefore, the challenge in guidance for general flow matching remains largely underexplored. In this paper, we propose the first framework of general guidance for flow matching. From this framework, we derive a family of guidance te"},"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":"2502.02150","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T09:27:57Z","cross_cats_sorted":[],"title_canon_sha256":"8be25a4488b87402f7c21c850f3335f0a361a40be6b6757ecbe43879cb0b4f98","abstract_canon_sha256":"d27811f6d02ac4d508b447e239356d7ea11c73de624d6be3974710e61aa7ad69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:44.892559Z","signature_b64":"ecYc6L2g0GH8gnJv6GvRpqlLJ7NP6FG9HL0zjuzgQiyeVIY4l5YoMSs9sk3H+FIKPgC7KS5fj2LrFe+emeZ5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b6363d53dac661e9c93412ec74e75f1aedb6907f784f7dd7a67e20d074de3e0","last_reissued_at":"2026-07-05T11:09:44.892036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:44.892036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Guidance of Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenglei Yu, Peiyan Hu, Ruiqi Feng, Tailin Wu, Wenhao Deng","submitted_at":"2025-02-04T09:27:57Z","abstract_excerpt":"Flow matching has shown state-of-the-art performance in various generative tasks, ranging from image generation to decision-making, where generation under energy guidance (abbreviated as guidance in the following) is pivotal. However, the guidance of flow matching is more general than and thus substantially different from that of its predecessor, diffusion models. Therefore, the challenge in guidance for general flow matching remains largely underexplored. In this paper, we propose the first framework of general guidance for flow matching. From this framework, we derive a family of guidance te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02150","kind":"arxiv","version":3},"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/2502.02150/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":"2502.02150","created_at":"2026-07-05T11:09:44.892097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02150v3","created_at":"2026-07-05T11:09:44.892097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02150","created_at":"2026-07-05T11:09:44.892097+00:00"},{"alias_kind":"pith_short_12","alias_value":"NNRWHVJ5VRTB","created_at":"2026-07-05T11:09:44.892097+00:00"},{"alias_kind":"pith_short_16","alias_value":"NNRWHVJ5VRTB5HET","created_at":"2026-07-05T11:09:44.892097+00:00"},{"alias_kind":"pith_short_8","alias_value":"NNRWHVJ5","created_at":"2026-07-05T11:09:44.892097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23147","citing_title":"Assistron: Bayesian Shared Autonomy with Off-the-shelf Vision-Language-Action Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22958","citing_title":"PG-MAP: Joint MAP Optimization for Inference-Time Alignment of Diffusion and Flow-Matching Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13240","citing_title":"Towards More General Control of Diffusion Models Using Jeffrey Guidance","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28867","citing_title":"PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2512.22597","citing_title":"Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2512.16768","citing_title":"On The Hidden Biases of Flow Matching Samplers","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20239","citing_title":"TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NNRWHVJ5VRTB5HETIEXMOTTV6G","json":"https://pith.science/pith/NNRWHVJ5VRTB5HETIEXMOTTV6G.json","graph_json":"https://pith.science/api/pith-number/NNRWHVJ5VRTB5HETIEXMOTTV6G/graph.json","events_json":"https://pith.science/api/pith-number/NNRWHVJ5VRTB5HETIEXMOTTV6G/events.json","paper":"https://pith.science/paper/NNRWHVJ5"},"agent_actions":{"view_html":"https://pith.science/pith/NNRWHVJ5VRTB5HETIEXMOTTV6G","download_json":"https://pith.science/pith/NNRWHVJ5VRTB5HETIEXMOTTV6G.json","view_paper":"https://pith.science/paper/NNRWHVJ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02150&json=true","fetch_graph":"https://pith.science/api/pith-number/NNRWHVJ5VRTB5HETIEXMOTTV6G/graph.json","fetch_events":"https://pith.science/api/pith-number/NNRWHVJ5VRTB5HETIEXMOTTV6G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NNRWHVJ5VRTB5HETIEXMOTTV6G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NNRWHVJ5VRTB5HETIEXMOTTV6G/action/storage_attestation","attest_author":"https://pith.science/pith/NNRWHVJ5VRTB5HETIEXMOTTV6G/action/author_attestation","sign_citation":"https://pith.science/pith/NNRWHVJ5VRTB5HETIEXMOTTV6G/action/citation_signature","submit_replication":"https://pith.science/pith/NNRWHVJ5VRTB5HETIEXMOTTV6G/action/replication_record"}},"created_at":"2026-07-05T11:09:44.892097+00:00","updated_at":"2026-07-05T11:09:44.892097+00:00"}