{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SDUP3FXVKZOBF5EKLJDVJSEKBF","short_pith_number":"pith:SDUP3FXV","schema_version":"1.0","canonical_sha256":"90e8fd96f5565c12f48a5a4754c88a0945ca6d5093e43741f974a73684b7ff3f","source":{"kind":"arxiv","id":"2606.03119","version":1},"attestation_state":"computed","paper":{"title":"GuidedBridge: Training-freely Improving Bridge Models with Prior Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Binjie Yuan, Jun S. Liu, Jun Zhu, Kaiwen Zheng, Yucheng Yang, Zehua Chen","submitted_at":"2026-06-02T04:04:23Z","abstract_excerpt":"Guidance methods, such as classifier-free guidance (CFG) and auto-guidance (AG), have advanced noise-to-data generation in diffusion models. Recently, bridge models have introduced a data-to-data generative process that can exploit an instructive clean prior. In this work, inspired by previous methods creating quality difference between denoising results as guidance, we propose a training-free bridge guidance method, termed Prior Guidance (PG). Specifically, we introduce a weak prior, which is unseen during bridge pre-training, hindering prior exploitation and thereby degrading denoising resul"},"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":"2606.03119","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T04:04:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"80c40749d4019902a82561c3db13c0517dec21139b3ad3fc3e1dba5a2dbe29b6","abstract_canon_sha256":"05d09b0b03cacd82f21724f641be7999df85af2e7fb1292f2bf51de8f7b458fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:32.236370Z","signature_b64":"ypKWwtRgLS8zXyzsS3dasr6xHti06C9MMsSIwfUeKmEeCqznrdfyrm+5qE3axn7w0OpEeGcHzIXb2mlriBjOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90e8fd96f5565c12f48a5a4754c88a0945ca6d5093e43741f974a73684b7ff3f","last_reissued_at":"2026-06-03T01:05:32.235942Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:32.235942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GuidedBridge: Training-freely Improving Bridge Models with Prior Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Binjie Yuan, Jun S. Liu, Jun Zhu, Kaiwen Zheng, Yucheng Yang, Zehua Chen","submitted_at":"2026-06-02T04:04:23Z","abstract_excerpt":"Guidance methods, such as classifier-free guidance (CFG) and auto-guidance (AG), have advanced noise-to-data generation in diffusion models. Recently, bridge models have introduced a data-to-data generative process that can exploit an instructive clean prior. In this work, inspired by previous methods creating quality difference between denoising results as guidance, we propose a training-free bridge guidance method, termed Prior Guidance (PG). Specifically, we introduce a weak prior, which is unseen during bridge pre-training, hindering prior exploitation and thereby degrading denoising resul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03119","kind":"arxiv","version":1},"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/2606.03119/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":"2606.03119","created_at":"2026-06-03T01:05:32.236000+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03119v1","created_at":"2026-06-03T01:05:32.236000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03119","created_at":"2026-06-03T01:05:32.236000+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDUP3FXVKZOB","created_at":"2026-06-03T01:05:32.236000+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDUP3FXVKZOBF5EK","created_at":"2026-06-03T01:05:32.236000+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDUP3FXV","created_at":"2026-06-03T01:05:32.236000+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/SDUP3FXVKZOBF5EKLJDVJSEKBF","json":"https://pith.science/pith/SDUP3FXVKZOBF5EKLJDVJSEKBF.json","graph_json":"https://pith.science/api/pith-number/SDUP3FXVKZOBF5EKLJDVJSEKBF/graph.json","events_json":"https://pith.science/api/pith-number/SDUP3FXVKZOBF5EKLJDVJSEKBF/events.json","paper":"https://pith.science/paper/SDUP3FXV"},"agent_actions":{"view_html":"https://pith.science/pith/SDUP3FXVKZOBF5EKLJDVJSEKBF","download_json":"https://pith.science/pith/SDUP3FXVKZOBF5EKLJDVJSEKBF.json","view_paper":"https://pith.science/paper/SDUP3FXV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03119&json=true","fetch_graph":"https://pith.science/api/pith-number/SDUP3FXVKZOBF5EKLJDVJSEKBF/graph.json","fetch_events":"https://pith.science/api/pith-number/SDUP3FXVKZOBF5EKLJDVJSEKBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDUP3FXVKZOBF5EKLJDVJSEKBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDUP3FXVKZOBF5EKLJDVJSEKBF/action/storage_attestation","attest_author":"https://pith.science/pith/SDUP3FXVKZOBF5EKLJDVJSEKBF/action/author_attestation","sign_citation":"https://pith.science/pith/SDUP3FXVKZOBF5EKLJDVJSEKBF/action/citation_signature","submit_replication":"https://pith.science/pith/SDUP3FXVKZOBF5EKLJDVJSEKBF/action/replication_record"}},"created_at":"2026-06-03T01:05:32.236000+00:00","updated_at":"2026-06-03T01:05:32.236000+00:00"}