{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IPWR3Y2BVQHGIFKYLNZOJQ24WB","short_pith_number":"pith:IPWR3Y2B","schema_version":"1.0","canonical_sha256":"43ed1de341ac0e6415585b72e4c35cb0636ec36308dc841fe2ab3ed39904642e","source":{"kind":"arxiv","id":"2502.08006","version":3},"attestation_state":"computed","paper":{"title":"Greed is Good: A Unifying Perspective on Guided Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Liu, Zander W. Blasingame","submitted_at":"2025-02-11T23:05:16Z","abstract_excerpt":"Training-free guided generation is a widely used and powerful technique that allows the end user to exert further control over the generative process of flow/diffusion models. Generally speaking, two families of techniques have emerged for solving this problem for gradient-based guidance: namely, posterior guidance (i.e., guidance via projecting the current sample to the target distribution via the target prediction model) and end-to-end guidance (i.e., guidance by performing backpropagation throughout the entire ODE solve). In this work, we show that these two seemingly separate families can "},"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":"2502.08006","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T23:05:16Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"713a95dfef73f54119e2529968d67a0ddd258c1a7b50cc2f6f1e0bf9ef2997ed","abstract_canon_sha256":"efea8868556d1f886330c3689bfb383ae4365c592487942000585652832f14ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:43.432976Z","signature_b64":"QU8L+0rv5wrWLn7zj09acOkXgu74eL3LmKFoFHbMLyEAkoz41bOhYTO3RQMKkXWl4ULVNSm+GipjoYeLJ5i9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43ed1de341ac0e6415585b72e4c35cb0636ec36308dc841fe2ab3ed39904642e","last_reissued_at":"2026-06-03T01:05:43.432519Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:43.432519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Greed is Good: A Unifying Perspective on Guided Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Liu, Zander W. Blasingame","submitted_at":"2025-02-11T23:05:16Z","abstract_excerpt":"Training-free guided generation is a widely used and powerful technique that allows the end user to exert further control over the generative process of flow/diffusion models. Generally speaking, two families of techniques have emerged for solving this problem for gradient-based guidance: namely, posterior guidance (i.e., guidance via projecting the current sample to the target distribution via the target prediction model) and end-to-end guidance (i.e., guidance by performing backpropagation throughout the entire ODE solve). In this work, we show that these two seemingly separate families can "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08006","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/2502.08006/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":"2502.08006","created_at":"2026-06-03T01:05:43.432570+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.08006v3","created_at":"2026-06-03T01:05:43.432570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08006","created_at":"2026-06-03T01:05:43.432570+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPWR3Y2BVQHG","created_at":"2026-06-03T01:05:43.432570+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPWR3Y2BVQHGIFKY","created_at":"2026-06-03T01:05:43.432570+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPWR3Y2B","created_at":"2026-06-03T01:05:43.432570+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/IPWR3Y2BVQHGIFKYLNZOJQ24WB","json":"https://pith.science/pith/IPWR3Y2BVQHGIFKYLNZOJQ24WB.json","graph_json":"https://pith.science/api/pith-number/IPWR3Y2BVQHGIFKYLNZOJQ24WB/graph.json","events_json":"https://pith.science/api/pith-number/IPWR3Y2BVQHGIFKYLNZOJQ24WB/events.json","paper":"https://pith.science/paper/IPWR3Y2B"},"agent_actions":{"view_html":"https://pith.science/pith/IPWR3Y2BVQHGIFKYLNZOJQ24WB","download_json":"https://pith.science/pith/IPWR3Y2BVQHGIFKYLNZOJQ24WB.json","view_paper":"https://pith.science/paper/IPWR3Y2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.08006&json=true","fetch_graph":"https://pith.science/api/pith-number/IPWR3Y2BVQHGIFKYLNZOJQ24WB/graph.json","fetch_events":"https://pith.science/api/pith-number/IPWR3Y2BVQHGIFKYLNZOJQ24WB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPWR3Y2BVQHGIFKYLNZOJQ24WB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPWR3Y2BVQHGIFKYLNZOJQ24WB/action/storage_attestation","attest_author":"https://pith.science/pith/IPWR3Y2BVQHGIFKYLNZOJQ24WB/action/author_attestation","sign_citation":"https://pith.science/pith/IPWR3Y2BVQHGIFKYLNZOJQ24WB/action/citation_signature","submit_replication":"https://pith.science/pith/IPWR3Y2BVQHGIFKYLNZOJQ24WB/action/replication_record"}},"created_at":"2026-06-03T01:05:43.432570+00:00","updated_at":"2026-06-03T01:05:43.432570+00:00"}