{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CFHXQC6ATRQ3VLBUM2UPROKD7Q","short_pith_number":"pith:CFHXQC6A","schema_version":"1.0","canonical_sha256":"114f780bc09c61baac3466a8f8b943fc31bba1785c31935b182643055cd2ed1b","source":{"kind":"arxiv","id":"2502.11420","version":3},"attestation_state":"computed","paper":{"title":"Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hui Yuan, Mengdi Wang, Yingqing Guo, Yukang Yang","submitted_at":"2025-02-17T04:20:39Z","abstract_excerpt":"Training-free guidance enables controlled generation in diffusion and flow models, but most methods rely on gradients and assume differentiable objectives. This work focuses on training-free guidance addressing challenges from non-differentiable objectives and discrete data distributions. We propose TreeG: Tree Search-Based Path Steering Guidance, applicable to both continuous and discrete settings in diffusion and flow models. TreeG offers a unified framework for training-free guidance by proposing, evaluating, and selecting candidates at each step, enhanced with tree search over active paths"},"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":"2502.11420","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T04:20:39Z","cross_cats_sorted":[],"title_canon_sha256":"d8efc798283c7fa52ea33bced205ca2ee08b7a287d649435b7a9d61e73e20ca8","abstract_canon_sha256":"63869e599ad8736809b25b4f581db51e308a7636fbc1c71a4dbca8e5b94a1b0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:24.505030Z","signature_b64":"F1sR5DDdU6Ptqmc5CY4VjpS20KtJVGhVRo7OLUOAVosZjFZdyoyw5kEAeeJFwZ/UvIVPHjPgsdts7SBKLUBEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"114f780bc09c61baac3466a8f8b943fc31bba1785c31935b182643055cd2ed1b","last_reissued_at":"2026-07-05T11:19:24.504562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:24.504562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hui Yuan, Mengdi Wang, Yingqing Guo, Yukang Yang","submitted_at":"2025-02-17T04:20:39Z","abstract_excerpt":"Training-free guidance enables controlled generation in diffusion and flow models, but most methods rely on gradients and assume differentiable objectives. This work focuses on training-free guidance addressing challenges from non-differentiable objectives and discrete data distributions. We propose TreeG: Tree Search-Based Path Steering Guidance, applicable to both continuous and discrete settings in diffusion and flow models. TreeG offers a unified framework for training-free guidance by proposing, evaluating, and selecting candidates at each step, enhanced with tree search over active paths"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11420","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/2502.11420/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":"2502.11420","created_at":"2026-07-05T11:19:24.504617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11420v3","created_at":"2026-07-05T11:19:24.504617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11420","created_at":"2026-07-05T11:19:24.504617+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFHXQC6ATRQ3","created_at":"2026-07-05T11:19:24.504617+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFHXQC6ATRQ3VLBU","created_at":"2026-07-05T11:19:24.504617+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFHXQC6A","created_at":"2026-07-05T11:19:24.504617+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06114","citing_title":"x-Prediction Is All You Need:Training-Free Accelerated Generation via Endpoint Decodability","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01144","citing_title":"Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16348","citing_title":"Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19317","citing_title":"Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2511.08425","citing_title":"HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23532","citing_title":"Iterative Inference-time Scaling with Adaptive Frequency Steering for Image Super-Resolution","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07950","citing_title":"Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CFHXQC6ATRQ3VLBUM2UPROKD7Q","json":"https://pith.science/pith/CFHXQC6ATRQ3VLBUM2UPROKD7Q.json","graph_json":"https://pith.science/api/pith-number/CFHXQC6ATRQ3VLBUM2UPROKD7Q/graph.json","events_json":"https://pith.science/api/pith-number/CFHXQC6ATRQ3VLBUM2UPROKD7Q/events.json","paper":"https://pith.science/paper/CFHXQC6A"},"agent_actions":{"view_html":"https://pith.science/pith/CFHXQC6ATRQ3VLBUM2UPROKD7Q","download_json":"https://pith.science/pith/CFHXQC6ATRQ3VLBUM2UPROKD7Q.json","view_paper":"https://pith.science/paper/CFHXQC6A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11420&json=true","fetch_graph":"https://pith.science/api/pith-number/CFHXQC6ATRQ3VLBUM2UPROKD7Q/graph.json","fetch_events":"https://pith.science/api/pith-number/CFHXQC6ATRQ3VLBUM2UPROKD7Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFHXQC6ATRQ3VLBUM2UPROKD7Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFHXQC6ATRQ3VLBUM2UPROKD7Q/action/storage_attestation","attest_author":"https://pith.science/pith/CFHXQC6ATRQ3VLBUM2UPROKD7Q/action/author_attestation","sign_citation":"https://pith.science/pith/CFHXQC6ATRQ3VLBUM2UPROKD7Q/action/citation_signature","submit_replication":"https://pith.science/pith/CFHXQC6ATRQ3VLBUM2UPROKD7Q/action/replication_record"}},"created_at":"2026-07-05T11:19:24.504617+00:00","updated_at":"2026-07-05T11:19:24.504617+00:00"}