{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6GAEJJJXSLF7AZ5J47T6FAECBU","short_pith_number":"pith:6GAEJJJX","canonical_record":{"source":{"id":"2607.17972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T14:10:53Z","cross_cats_sorted":[],"title_canon_sha256":"8af23c6078f4e14eb401a0842fffd91a455380610ed61f114f1f83a17f129923","abstract_canon_sha256":"1785abf1e0300fbd0888b87497dc0117aad620b1b2914bd1aeb79abe09f14a0a"},"schema_version":"1.0"},"canonical_sha256":"f18044a53792cbf067a9e7e7e280820d37208fc4afd8a5aabcb32130b2875d96","source":{"kind":"arxiv","id":"2607.17972","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17972","created_at":"2026-07-21T02:22:09Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17972v1","created_at":"2026-07-21T02:22:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17972","created_at":"2026-07-21T02:22:09Z"},{"alias_kind":"pith_short_12","alias_value":"6GAEJJJXSLF7","created_at":"2026-07-21T02:22:09Z"},{"alias_kind":"pith_short_16","alias_value":"6GAEJJJXSLF7AZ5J","created_at":"2026-07-21T02:22:09Z"},{"alias_kind":"pith_short_8","alias_value":"6GAEJJJX","created_at":"2026-07-21T02:22:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6GAEJJJXSLF7AZ5J47T6FAECBU","target":"record","payload":{"canonical_record":{"source":{"id":"2607.17972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T14:10:53Z","cross_cats_sorted":[],"title_canon_sha256":"8af23c6078f4e14eb401a0842fffd91a455380610ed61f114f1f83a17f129923","abstract_canon_sha256":"1785abf1e0300fbd0888b87497dc0117aad620b1b2914bd1aeb79abe09f14a0a"},"schema_version":"1.0"},"canonical_sha256":"f18044a53792cbf067a9e7e7e280820d37208fc4afd8a5aabcb32130b2875d96","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T02:22:09.571404Z","signature_b64":"CRKlUEK3ws5mZ44n5h0Zckqam65Be+KgvBIVj5CTYFpeb1BMUpvbuYNb7ClTz0SwcIGZw1j9WRht840RXQTdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f18044a53792cbf067a9e7e7e280820d37208fc4afd8a5aabcb32130b2875d96","last_reissued_at":"2026-07-21T02:22:09.570553Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T02:22:09.570553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.17972","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":"2026-07-21T02:22:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2a468HIfWl82yEx+K8DfLQPmi4bZDM0Mt/+nYAk7PYCZHFWLbEQ0dabAAVCkDtiRZUKld65RTk3JFpDp3hGFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:46:36.644886Z"},"content_sha256":"c9dbf45f113f4b497929e54d167d64e36db3dd183ef541bb2b4ab0b4d374ef44","schema_version":"1.0","event_id":"sha256:c9dbf45f113f4b497929e54d167d64e36db3dd183ef541bb2b4ab0b4d374ef44"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6GAEJJJXSLF7AZ5J47T6FAECBU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiFA: Inference-Time Forward-Process Alignment for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Delu Zeng, Shigui Li","submitted_at":"2026-07-20T14:10:53Z","abstract_excerpt":"The prevailing inference framework for diffusion models formulates generation fundamentally as a problem of numerical integration. This perspective casts the model as an exact estimator, neglecting the inherent statistical uncertainty of the denoising process. In this work, we propose Forward-Process Aligned Diffusion prediction (\\textbf{DiFA}), a training-free framework that reframes inference-time data prediction refinement as a sequential state estimation problem. Rather than reusing past outputs solely for numerical integration, DiFA treats iterative data predictions along the reverse traj"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17972","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/2607.17972/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":"2026-07-21T02:22:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ajac2sYthFx3clRPnEoieTTI3ImbC9J+Papv8gFf6jXOWkY3m4nncSuz4wCWQ3ozYMtOke/f2iWwFGPnMXkTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:46:36.645928Z"},"content_sha256":"2f5b51422e29a276ff4d0e0d9d8a7d8d74bc07af4a22038115c455f96a8010d7","schema_version":"1.0","event_id":"sha256:2f5b51422e29a276ff4d0e0d9d8a7d8d74bc07af4a22038115c455f96a8010d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6GAEJJJXSLF7AZ5J47T6FAECBU/bundle.json","state_url":"https://pith.science/pith/6GAEJJJXSLF7AZ5J47T6FAECBU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6GAEJJJXSLF7AZ5J47T6FAECBU/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":"2026-08-08T20:46:36Z","links":{"resolver":"https://pith.science/pith/6GAEJJJXSLF7AZ5J47T6FAECBU","bundle":"https://pith.science/pith/6GAEJJJXSLF7AZ5J47T6FAECBU/bundle.json","state":"https://pith.science/pith/6GAEJJJXSLF7AZ5J47T6FAECBU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6GAEJJJXSLF7AZ5J47T6FAECBU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6GAEJJJXSLF7AZ5J47T6FAECBU","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":"1785abf1e0300fbd0888b87497dc0117aad620b1b2914bd1aeb79abe09f14a0a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T14:10:53Z","title_canon_sha256":"8af23c6078f4e14eb401a0842fffd91a455380610ed61f114f1f83a17f129923"},"schema_version":"1.0","source":{"id":"2607.17972","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17972","created_at":"2026-07-21T02:22:09Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17972v1","created_at":"2026-07-21T02:22:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17972","created_at":"2026-07-21T02:22:09Z"},{"alias_kind":"pith_short_12","alias_value":"6GAEJJJXSLF7","created_at":"2026-07-21T02:22:09Z"},{"alias_kind":"pith_short_16","alias_value":"6GAEJJJXSLF7AZ5J","created_at":"2026-07-21T02:22:09Z"},{"alias_kind":"pith_short_8","alias_value":"6GAEJJJX","created_at":"2026-07-21T02:22:09Z"}],"graph_snapshots":[{"event_id":"sha256:2f5b51422e29a276ff4d0e0d9d8a7d8d74bc07af4a22038115c455f96a8010d7","target":"graph","created_at":"2026-07-21T02:22:09Z","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/2607.17972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The prevailing inference framework for diffusion models formulates generation fundamentally as a problem of numerical integration. This perspective casts the model as an exact estimator, neglecting the inherent statistical uncertainty of the denoising process. In this work, we propose Forward-Process Aligned Diffusion prediction (\\textbf{DiFA}), a training-free framework that reframes inference-time data prediction refinement as a sequential state estimation problem. Rather than reusing past outputs solely for numerical integration, DiFA treats iterative data predictions along the reverse traj","authors_text":"Delu Zeng, Shigui Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T14:10:53Z","title":"DiFA: Inference-Time Forward-Process Alignment for Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17972","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:c9dbf45f113f4b497929e54d167d64e36db3dd183ef541bb2b4ab0b4d374ef44","target":"record","created_at":"2026-07-21T02:22:09Z","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":"1785abf1e0300fbd0888b87497dc0117aad620b1b2914bd1aeb79abe09f14a0a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T14:10:53Z","title_canon_sha256":"8af23c6078f4e14eb401a0842fffd91a455380610ed61f114f1f83a17f129923"},"schema_version":"1.0","source":{"id":"2607.17972","kind":"arxiv","version":1}},"canonical_sha256":"f18044a53792cbf067a9e7e7e280820d37208fc4afd8a5aabcb32130b2875d96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f18044a53792cbf067a9e7e7e280820d37208fc4afd8a5aabcb32130b2875d96","first_computed_at":"2026-07-21T02:22:09.570553Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T02:22:09.570553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CRKlUEK3ws5mZ44n5h0Zckqam65Be+KgvBIVj5CTYFpeb1BMUpvbuYNb7ClTz0SwcIGZw1j9WRht840RXQTdBA==","signature_status":"signed_v1","signed_at":"2026-07-21T02:22:09.571404Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.17972","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9dbf45f113f4b497929e54d167d64e36db3dd183ef541bb2b4ab0b4d374ef44","sha256:2f5b51422e29a276ff4d0e0d9d8a7d8d74bc07af4a22038115c455f96a8010d7"],"state_sha256":"ff0f3bb74eb0b5b8c3ad9a8219bd096ce41fb17bd8a516b9d5209696f3429e30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VKPEg/h4GHy91JZXjQg2/n4RkOLpqyRpRSxLy9dPD+oPEYtYVrytuP1m7phcFyCsbHlez2eOEUCosP00cwdjBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:46:36.653014Z","bundle_sha256":"37448aaa69c0fdff869fd8f60ee900d9142bacd7f8a69ea159c6be30d9275628"}}