{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JH4LCTHA55TA74QAOUEDMFDDLC","short_pith_number":"pith:JH4LCTHA","canonical_record":{"source":{"id":"2508.21016","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-28T17:18:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"50be57eab67f91b4b4666a5c8a8434642be005ee9edd34acb6581365acf0c276","abstract_canon_sha256":"b51216b5c0adca2829309cf5de308cc914fd9e1d7927e2c35ea7b917842c795d"},"schema_version":"1.0"},"canonical_sha256":"49f8b14ce0ef660ff200750836146358adad32f4c78c9ef945feb9ebcee63cea","source":{"kind":"arxiv","id":"2508.21016","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21016","created_at":"2026-07-05T12:01:15Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21016v1","created_at":"2026-07-05T12:01:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21016","created_at":"2026-07-05T12:01:15Z"},{"alias_kind":"pith_short_12","alias_value":"JH4LCTHA55TA","created_at":"2026-07-05T12:01:15Z"},{"alias_kind":"pith_short_16","alias_value":"JH4LCTHA55TA74QA","created_at":"2026-07-05T12:01:15Z"},{"alias_kind":"pith_short_8","alias_value":"JH4LCTHA","created_at":"2026-07-05T12:01:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JH4LCTHA55TA74QAOUEDMFDDLC","target":"record","payload":{"canonical_record":{"source":{"id":"2508.21016","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-28T17:18:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"50be57eab67f91b4b4666a5c8a8434642be005ee9edd34acb6581365acf0c276","abstract_canon_sha256":"b51216b5c0adca2829309cf5de308cc914fd9e1d7927e2c35ea7b917842c795d"},"schema_version":"1.0"},"canonical_sha256":"49f8b14ce0ef660ff200750836146358adad32f4c78c9ef945feb9ebcee63cea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:15.296541Z","signature_b64":"Aw3WJ5A/rpi0j2Ttta+JxGY57ATXFghw5B15uNxIfthx1MvMZlGkYHZpGCPqKILI46y39NHUEpV5rwPRt+3nAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49f8b14ce0ef660ff200750836146358adad32f4c78c9ef945feb9ebcee63cea","last_reissued_at":"2026-07-05T12:01:15.295993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:15.295993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.21016","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":"2026-07-05T12:01:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4NSy47uJEQavJbIqVBiAe6mABhLqtZ96jt8QUEyPsbPd7nB6oAvd10JGEB9peckw+OhX/4d+MVK5fp84/aF2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:33:03.928513Z"},"content_sha256":"5ddbcf57279aa269546bc9a7f55a4ad50378a16513950092dc974f91589991c1","schema_version":"1.0","event_id":"sha256:5ddbcf57279aa269546bc9a7f55a4ad50378a16513950092dc974f91589991c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JH4LCTHA55TA74QAOUEDMFDDLC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alex Lamb, Jie Liu, Lifeng Qiao, Luozhijie Jin, Ning Ding, Xipeng Qiu, Zijie Diao, Zijie Qiu","submitted_at":"2025-08-28T17:18:31Z","abstract_excerpt":"Denoising-based generative models, particularly diffusion and flow matching algorithms, have achieved remarkable success. However, aligning their output distributions with complex downstream objectives, such as human preferences, compositional accuracy, or data compressibility, remains challenging. While reinforcement learning (RL) fine-tuning methods, inspired by advances in RL from human feedback (RLHF) for large language models, have been adapted to these generative frameworks, current RL approaches are suboptimal for diffusion models and offer limited flexibility in controlling alignment s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21016","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/2508.21016/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":"2026-07-05T12:01:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Dhz9TZbLU9B/b69F2FnKH3XNn0eGjJhinlra9RAQIablzrGiA8pLhpLrcKAXTkKvWeGzF//hzkbfwtZmxM4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:33:03.929054Z"},"content_sha256":"3c891092360ab12fc3b551441ddb2674cc1dd5a03073086debc542acb67974cc","schema_version":"1.0","event_id":"sha256:3c891092360ab12fc3b551441ddb2674cc1dd5a03073086debc542acb67974cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JH4LCTHA55TA74QAOUEDMFDDLC/bundle.json","state_url":"https://pith.science/pith/JH4LCTHA55TA74QAOUEDMFDDLC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JH4LCTHA55TA74QAOUEDMFDDLC/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":"2026-08-06T09:33:03Z","links":{"resolver":"https://pith.science/pith/JH4LCTHA55TA74QAOUEDMFDDLC","bundle":"https://pith.science/pith/JH4LCTHA55TA74QAOUEDMFDDLC/bundle.json","state":"https://pith.science/pith/JH4LCTHA55TA74QAOUEDMFDDLC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JH4LCTHA55TA74QAOUEDMFDDLC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JH4LCTHA55TA74QAOUEDMFDDLC","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":"b51216b5c0adca2829309cf5de308cc914fd9e1d7927e2c35ea7b917842c795d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-28T17:18:31Z","title_canon_sha256":"50be57eab67f91b4b4666a5c8a8434642be005ee9edd34acb6581365acf0c276"},"schema_version":"1.0","source":{"id":"2508.21016","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21016","created_at":"2026-07-05T12:01:15Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21016v1","created_at":"2026-07-05T12:01:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21016","created_at":"2026-07-05T12:01:15Z"},{"alias_kind":"pith_short_12","alias_value":"JH4LCTHA55TA","created_at":"2026-07-05T12:01:15Z"},{"alias_kind":"pith_short_16","alias_value":"JH4LCTHA55TA74QA","created_at":"2026-07-05T12:01:15Z"},{"alias_kind":"pith_short_8","alias_value":"JH4LCTHA","created_at":"2026-07-05T12:01:15Z"}],"graph_snapshots":[{"event_id":"sha256:3c891092360ab12fc3b551441ddb2674cc1dd5a03073086debc542acb67974cc","target":"graph","created_at":"2026-07-05T12:01:15Z","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/2508.21016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Denoising-based generative models, particularly diffusion and flow matching algorithms, have achieved remarkable success. However, aligning their output distributions with complex downstream objectives, such as human preferences, compositional accuracy, or data compressibility, remains challenging. While reinforcement learning (RL) fine-tuning methods, inspired by advances in RL from human feedback (RLHF) for large language models, have been adapted to these generative frameworks, current RL approaches are suboptimal for diffusion models and offer limited flexibility in controlling alignment s","authors_text":"Alex Lamb, Jie Liu, Lifeng Qiao, Luozhijie Jin, Ning Ding, Xipeng Qiu, Zijie Diao, Zijie Qiu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-28T17:18:31Z","title":"Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21016","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":"sha256:5ddbcf57279aa269546bc9a7f55a4ad50378a16513950092dc974f91589991c1","target":"record","created_at":"2026-07-05T12:01:15Z","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":"b51216b5c0adca2829309cf5de308cc914fd9e1d7927e2c35ea7b917842c795d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-28T17:18:31Z","title_canon_sha256":"50be57eab67f91b4b4666a5c8a8434642be005ee9edd34acb6581365acf0c276"},"schema_version":"1.0","source":{"id":"2508.21016","kind":"arxiv","version":1}},"canonical_sha256":"49f8b14ce0ef660ff200750836146358adad32f4c78c9ef945feb9ebcee63cea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"49f8b14ce0ef660ff200750836146358adad32f4c78c9ef945feb9ebcee63cea","first_computed_at":"2026-07-05T12:01:15.295993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:15.295993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Aw3WJ5A/rpi0j2Ttta+JxGY57ATXFghw5B15uNxIfthx1MvMZlGkYHZpGCPqKILI46y39NHUEpV5rwPRt+3nAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:15.296541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21016","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ddbcf57279aa269546bc9a7f55a4ad50378a16513950092dc974f91589991c1","sha256:3c891092360ab12fc3b551441ddb2674cc1dd5a03073086debc542acb67974cc"],"state_sha256":"41ed8f1ce7514dde8eabac05a6762abc2fae5ba7fb44f2301b8c4d960f2f6dfb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7/3oGgFCgMgV9q5CL9GGNvfjnYeDiYhY5+W4RpXpYTdhULDT2m8sfjZdeOc5dvSERXW3uFO6diKKxhQkOKXtDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:33:03.933174Z","bundle_sha256":"fcaceb528d512a70ad0467ed3ca7683f49e6dbdd105ea0d72e86704f8b1a2ec4"}}