{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Y3RQ5AOK6YETPMWVGSBBUEVQ7F","short_pith_number":"pith:Y3RQ5AOK","canonical_record":{"source":{"id":"2505.19196","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T15:43:54Z","cross_cats_sorted":[],"title_canon_sha256":"7f958bd0ec4c97199ca320686c7eee8732686e63990534b06a81734213eb53a4","abstract_canon_sha256":"9672432cc60cea11c32325c56932a3f40bd47fc8364fc10c653035dc85cbbfb4"},"schema_version":"1.0"},"canonical_sha256":"c6e30e81caf60937b2d534821a12b0f95cad06d96d1da029a1d8d27679f6d268","source":{"kind":"arxiv","id":"2505.19196","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19196","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19196v1","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19196","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"pith_short_12","alias_value":"Y3RQ5AOK6YET","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"pith_short_16","alias_value":"Y3RQ5AOK6YETPMWV","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"pith_short_8","alias_value":"Y3RQ5AOK","created_at":"2026-07-05T11:09:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Y3RQ5AOK6YETPMWVGSBBUEVQ7F","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19196","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T15:43:54Z","cross_cats_sorted":[],"title_canon_sha256":"7f958bd0ec4c97199ca320686c7eee8732686e63990534b06a81734213eb53a4","abstract_canon_sha256":"9672432cc60cea11c32325c56932a3f40bd47fc8364fc10c653035dc85cbbfb4"},"schema_version":"1.0"},"canonical_sha256":"c6e30e81caf60937b2d534821a12b0f95cad06d96d1da029a1d8d27679f6d268","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:26.319588Z","signature_b64":"mKqM481fSwxc7X1v0cJmKRbVWoZyM6+KOk9Reb0lmBtWNhj3LebD1xiQnJiw2F1624xtvt5pYjCmWjN3ZUCyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6e30e81caf60937b2d534821a12b0f95cad06d96d1da029a1d8d27679f6d268","last_reissued_at":"2026-07-05T11:09:26.318951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:26.318951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19196","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IO83kfHpn1BjB1ynpz4taAqEEMm10LJSK0Lwd70DAjgIZ98aYHD/uXE/cUnuwUes7h3XCBDEywLJLMBzQlgcAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:08:06.258563Z"},"content_sha256":"e3f737c18f99a261a4725ee85f201f3ebde41a0b2496081e8d937aaff7e182c0","schema_version":"1.0","event_id":"sha256:e3f737c18f99a261a4725ee85f201f3ebde41a0b2496081e8d937aaff7e182c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Y3RQ5AOK6YETPMWVGSBBUEVQ7F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Step-level Reward for Free in RL-based T2I Diffusion Model Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wei Wei, Xiaoye Qu, Xinyao Liao, Yu Cheng","submitted_at":"2025-05-25T15:43:54Z","abstract_excerpt":"Recent advances in text-to-image (T2I) diffusion model fine-tuning leverage reinforcement learning (RL) to align generated images with learnable reward functions. The existing approaches reformulate denoising as a Markov decision process for RL-driven optimization. However, they suffer from reward sparsity, receiving only a single delayed reward per generated trajectory. This flaw hinders precise step-level attribution of denoising actions, undermines training efficiency. To address this, we propose a simple yet effective credit assignment framework that dynamically distributes dense rewards a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19196","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/2505.19196/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hJU+2AIvNR4ES7aA00a7dJcfDYwnIQep1OnN1gZ74x79EA7tviz/GBK9Vtsqw8ILfM0xGwTZJYqttjrbBZcCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:08:06.259075Z"},"content_sha256":"be0984ab662d005b5bd8cf497ee8d0e889695e584e370f74df462ff825d3af17","schema_version":"1.0","event_id":"sha256:be0984ab662d005b5bd8cf497ee8d0e889695e584e370f74df462ff825d3af17"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y3RQ5AOK6YETPMWVGSBBUEVQ7F/bundle.json","state_url":"https://pith.science/pith/Y3RQ5AOK6YETPMWVGSBBUEVQ7F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y3RQ5AOK6YETPMWVGSBBUEVQ7F/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T09:08:06Z","links":{"resolver":"https://pith.science/pith/Y3RQ5AOK6YETPMWVGSBBUEVQ7F","bundle":"https://pith.science/pith/Y3RQ5AOK6YETPMWVGSBBUEVQ7F/bundle.json","state":"https://pith.science/pith/Y3RQ5AOK6YETPMWVGSBBUEVQ7F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y3RQ5AOK6YETPMWVGSBBUEVQ7F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y3RQ5AOK6YETPMWVGSBBUEVQ7F","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9672432cc60cea11c32325c56932a3f40bd47fc8364fc10c653035dc85cbbfb4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T15:43:54Z","title_canon_sha256":"7f958bd0ec4c97199ca320686c7eee8732686e63990534b06a81734213eb53a4"},"schema_version":"1.0","source":{"id":"2505.19196","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19196","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19196v1","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19196","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"pith_short_12","alias_value":"Y3RQ5AOK6YET","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"pith_short_16","alias_value":"Y3RQ5AOK6YETPMWV","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"pith_short_8","alias_value":"Y3RQ5AOK","created_at":"2026-07-05T11:09:26Z"}],"graph_snapshots":[{"event_id":"sha256:be0984ab662d005b5bd8cf497ee8d0e889695e584e370f74df462ff825d3af17","target":"graph","created_at":"2026-07-05T11:09:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.19196/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in text-to-image (T2I) diffusion model fine-tuning leverage reinforcement learning (RL) to align generated images with learnable reward functions. The existing approaches reformulate denoising as a Markov decision process for RL-driven optimization. However, they suffer from reward sparsity, receiving only a single delayed reward per generated trajectory. This flaw hinders precise step-level attribution of denoising actions, undermines training efficiency. To address this, we propose a simple yet effective credit assignment framework that dynamically distributes dense rewards a","authors_text":"Wei Wei, Xiaoye Qu, Xinyao Liao, Yu Cheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T15:43:54Z","title":"Step-level Reward for Free in RL-based T2I Diffusion Model Fine-tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19196","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e3f737c18f99a261a4725ee85f201f3ebde41a0b2496081e8d937aaff7e182c0","target":"record","created_at":"2026-07-05T11:09:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9672432cc60cea11c32325c56932a3f40bd47fc8364fc10c653035dc85cbbfb4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T15:43:54Z","title_canon_sha256":"7f958bd0ec4c97199ca320686c7eee8732686e63990534b06a81734213eb53a4"},"schema_version":"1.0","source":{"id":"2505.19196","kind":"arxiv","version":1}},"canonical_sha256":"c6e30e81caf60937b2d534821a12b0f95cad06d96d1da029a1d8d27679f6d268","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6e30e81caf60937b2d534821a12b0f95cad06d96d1da029a1d8d27679f6d268","first_computed_at":"2026-07-05T11:09:26.318951Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:26.318951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mKqM481fSwxc7X1v0cJmKRbVWoZyM6+KOk9Reb0lmBtWNhj3LebD1xiQnJiw2F1624xtvt5pYjCmWjN3ZUCyBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:26.319588Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19196","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3f737c18f99a261a4725ee85f201f3ebde41a0b2496081e8d937aaff7e182c0","sha256:be0984ab662d005b5bd8cf497ee8d0e889695e584e370f74df462ff825d3af17"],"state_sha256":"f28bedbe71d2027e9b4d15146d5285f3c3237233084fb1077a4042158e5aad83"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZnJIHY748ZLmfOtyxNAln/KJnQ/ePSAKMDU2kWYFrRlNQMCq0acw39Ohz5nhcvUQSoUuhXIpOrP3Ta3lmRRJBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:08:06.263127Z","bundle_sha256":"152db5ad73d7d18f2e48a1747e5cb05ae826dbddaca2db122999c0a0c7c45965"}}