{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WDCU245A74SDVILXX2KZ5DFI2F","short_pith_number":"pith:WDCU245A","schema_version":"1.0","canonical_sha256":"b0c54d73a0ff243aa177be959e8ca8d1767e8c6dfdbc662bad59620d63e90a81","source":{"kind":"arxiv","id":"2605.25661","version":1},"attestation_state":"computed","paper":{"title":"DRM: Diffusion-based Reward Model With Step-wise Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binxin Yang, Chen Li, Hubery Yin, Jaxon Zhang, Jing Lyu","submitted_at":"2026-05-25T10:11:32Z","abstract_excerpt":"Current mainstream methods of aligning diffusion models with human preferences typically employ VLM-based reward models. However, these reward models, pre-trained for semantic alignment, struggle to capture the essential perceptual qualities-such as aesthetics, composition, and visual harmony. In this work, we argue that a model capable of high-fidelity generation must possess a profound understanding of these visual attributes. Based on this insight, we introduce the Diffusion-based Reward Model (DRM), a novel paradigm that use the pre-trained diffusion model as a powerful evaluative backbone"},"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":"2605.25661","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T10:11:32Z","cross_cats_sorted":[],"title_canon_sha256":"4b67e30fdac55714c1196acfe8613112687d69f8caea9f58c4b0cddf5c1b20c2","abstract_canon_sha256":"79a5d478d88b3b131b4d6e7ca048d3db80d7d8eeddabf36292ad38419e5af2f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:48.862488Z","signature_b64":"EWIkGhR+ckkF8ZqJ9XLukoovCUpkwt0CeJRfjGc9GBrDcaDUclx0dO6UbphJqJVfxDi6cK4OTCIvB2z0/GnKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0c54d73a0ff243aa177be959e8ca8d1767e8c6dfdbc662bad59620d63e90a81","last_reissued_at":"2026-05-26T02:04:48.861647Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:48.861647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DRM: Diffusion-based Reward Model With Step-wise Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binxin Yang, Chen Li, Hubery Yin, Jaxon Zhang, Jing Lyu","submitted_at":"2026-05-25T10:11:32Z","abstract_excerpt":"Current mainstream methods of aligning diffusion models with human preferences typically employ VLM-based reward models. However, these reward models, pre-trained for semantic alignment, struggle to capture the essential perceptual qualities-such as aesthetics, composition, and visual harmony. In this work, we argue that a model capable of high-fidelity generation must possess a profound understanding of these visual attributes. Based on this insight, we introduce the Diffusion-based Reward Model (DRM), a novel paradigm that use the pre-trained diffusion model as a powerful evaluative backbone"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25661","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/2605.25661/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":"2605.25661","created_at":"2026-05-26T02:04:48.861767+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25661v1","created_at":"2026-05-26T02:04:48.861767+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25661","created_at":"2026-05-26T02:04:48.861767+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDCU245A74SD","created_at":"2026-05-26T02:04:48.861767+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDCU245A74SDVILX","created_at":"2026-05-26T02:04:48.861767+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDCU245A","created_at":"2026-05-26T02:04:48.861767+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/WDCU245A74SDVILXX2KZ5DFI2F","json":"https://pith.science/pith/WDCU245A74SDVILXX2KZ5DFI2F.json","graph_json":"https://pith.science/api/pith-number/WDCU245A74SDVILXX2KZ5DFI2F/graph.json","events_json":"https://pith.science/api/pith-number/WDCU245A74SDVILXX2KZ5DFI2F/events.json","paper":"https://pith.science/paper/WDCU245A"},"agent_actions":{"view_html":"https://pith.science/pith/WDCU245A74SDVILXX2KZ5DFI2F","download_json":"https://pith.science/pith/WDCU245A74SDVILXX2KZ5DFI2F.json","view_paper":"https://pith.science/paper/WDCU245A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25661&json=true","fetch_graph":"https://pith.science/api/pith-number/WDCU245A74SDVILXX2KZ5DFI2F/graph.json","fetch_events":"https://pith.science/api/pith-number/WDCU245A74SDVILXX2KZ5DFI2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDCU245A74SDVILXX2KZ5DFI2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDCU245A74SDVILXX2KZ5DFI2F/action/storage_attestation","attest_author":"https://pith.science/pith/WDCU245A74SDVILXX2KZ5DFI2F/action/author_attestation","sign_citation":"https://pith.science/pith/WDCU245A74SDVILXX2KZ5DFI2F/action/citation_signature","submit_replication":"https://pith.science/pith/WDCU245A74SDVILXX2KZ5DFI2F/action/replication_record"}},"created_at":"2026-05-26T02:04:48.861767+00:00","updated_at":"2026-05-26T02:04:48.861767+00:00"}