{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NEEZNZHEUPGVW5VGNC4OBYJRNH","short_pith_number":"pith:NEEZNZHE","canonical_record":{"source":{"id":"2505.05732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-09T02:10:46Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a589c3c0fd90e14687a78f9b28703381d3357f538219c2439c92d7c40b69be58","abstract_canon_sha256":"ab1010fd363ebf8dbd29109f30def1b038c64b41b07cb1dddd7fe863024d76ff"},"schema_version":"1.0"},"canonical_sha256":"690996e4e4a3cd5b76a668b8e0e13169c1fc8850b135a72970689e0c38947c32","source":{"kind":"arxiv","id":"2505.05732","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05732","created_at":"2026-07-05T11:00:46Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05732v1","created_at":"2026-07-05T11:00:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05732","created_at":"2026-07-05T11:00:46Z"},{"alias_kind":"pith_short_12","alias_value":"NEEZNZHEUPGV","created_at":"2026-07-05T11:00:46Z"},{"alias_kind":"pith_short_16","alias_value":"NEEZNZHEUPGVW5VG","created_at":"2026-07-05T11:00:46Z"},{"alias_kind":"pith_short_8","alias_value":"NEEZNZHE","created_at":"2026-07-05T11:00:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NEEZNZHEUPGVW5VGNC4OBYJRNH","target":"record","payload":{"canonical_record":{"source":{"id":"2505.05732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-09T02:10:46Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a589c3c0fd90e14687a78f9b28703381d3357f538219c2439c92d7c40b69be58","abstract_canon_sha256":"ab1010fd363ebf8dbd29109f30def1b038c64b41b07cb1dddd7fe863024d76ff"},"schema_version":"1.0"},"canonical_sha256":"690996e4e4a3cd5b76a668b8e0e13169c1fc8850b135a72970689e0c38947c32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:46.727082Z","signature_b64":"ohx9JDJu3LKv/Qe5muzHcJlRh2QzX9CGqEzd4Q8uFlEDZU0Ht5ajm1AwXHmrnaXodlFpZDjbJyMX7n/2i2CtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"690996e4e4a3cd5b76a668b8e0e13169c1fc8850b135a72970689e0c38947c32","last_reissued_at":"2026-07-05T11:00:46.726593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:46.726593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.05732","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":"2026-07-05T11:00:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jXNN+xqJy00avb85XSC7rjrEL1Niqktu0kJirWqD487rZs9w/eKHcpsupMgsRt+WTdNSyrXSWZq5VD9gLm19Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:34:49.203659Z"},"content_sha256":"f35205aed7260b8c7ade18ff91c9e77912c898d9df4f13ed21c70129510064b0","schema_version":"1.0","event_id":"sha256:f35205aed7260b8c7ade18ff91c9e77912c898d9df4f13ed21c70129510064b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NEEZNZHEUPGVW5VGNC4OBYJRNH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automated Learning of Semantic Embedding Representations for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Limai Jiang, Yunpeng Cai","submitted_at":"2025-05-09T02:10:46Z","abstract_excerpt":"Generative models capture the true distribution of data, yielding semantically rich representations. Denoising diffusion models (DDMs) exhibit superior generative capabilities, though efficient representation learning for them are lacking. In this work, we employ a multi-level denoising autoencoder framework to expand the representation capacity of DDMs, which introduces sequentially consistent Diffusion Transformers and an additional timestep-dependent encoder to acquire embedding representations on the denoising Markov chain through self-conditional diffusion learning. Intuitively, the encod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05732","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/2505.05732/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":"2026-07-05T11:00:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6dLd+q69gL6tIX8g8IF0DfxyL32RF7MzqPH26GTEOWGMU00Lx6rApW8ye6qiKX/p2XWwGTx9CMZ91yKRKZ2eDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:34:49.204251Z"},"content_sha256":"dadb11a0049f73cdb80f513925d1e1dd3c19d7744ab5db282484699b46a9ae4c","schema_version":"1.0","event_id":"sha256:dadb11a0049f73cdb80f513925d1e1dd3c19d7744ab5db282484699b46a9ae4c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NEEZNZHEUPGVW5VGNC4OBYJRNH/bundle.json","state_url":"https://pith.science/pith/NEEZNZHEUPGVW5VGNC4OBYJRNH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NEEZNZHEUPGVW5VGNC4OBYJRNH/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":"2026-08-17T18:34:49Z","links":{"resolver":"https://pith.science/pith/NEEZNZHEUPGVW5VGNC4OBYJRNH","bundle":"https://pith.science/pith/NEEZNZHEUPGVW5VGNC4OBYJRNH/bundle.json","state":"https://pith.science/pith/NEEZNZHEUPGVW5VGNC4OBYJRNH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NEEZNZHEUPGVW5VGNC4OBYJRNH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NEEZNZHEUPGVW5VGNC4OBYJRNH","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":"ab1010fd363ebf8dbd29109f30def1b038c64b41b07cb1dddd7fe863024d76ff","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-09T02:10:46Z","title_canon_sha256":"a589c3c0fd90e14687a78f9b28703381d3357f538219c2439c92d7c40b69be58"},"schema_version":"1.0","source":{"id":"2505.05732","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05732","created_at":"2026-07-05T11:00:46Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05732v1","created_at":"2026-07-05T11:00:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05732","created_at":"2026-07-05T11:00:46Z"},{"alias_kind":"pith_short_12","alias_value":"NEEZNZHEUPGV","created_at":"2026-07-05T11:00:46Z"},{"alias_kind":"pith_short_16","alias_value":"NEEZNZHEUPGVW5VG","created_at":"2026-07-05T11:00:46Z"},{"alias_kind":"pith_short_8","alias_value":"NEEZNZHE","created_at":"2026-07-05T11:00:46Z"}],"graph_snapshots":[{"event_id":"sha256:dadb11a0049f73cdb80f513925d1e1dd3c19d7744ab5db282484699b46a9ae4c","target":"graph","created_at":"2026-07-05T11:00:46Z","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/2505.05732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative models capture the true distribution of data, yielding semantically rich representations. Denoising diffusion models (DDMs) exhibit superior generative capabilities, though efficient representation learning for them are lacking. In this work, we employ a multi-level denoising autoencoder framework to expand the representation capacity of DDMs, which introduces sequentially consistent Diffusion Transformers and an additional timestep-dependent encoder to acquire embedding representations on the denoising Markov chain through self-conditional diffusion learning. Intuitively, the encod","authors_text":"Limai Jiang, Yunpeng Cai","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-09T02:10:46Z","title":"Automated Learning of Semantic Embedding Representations for Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05732","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:f35205aed7260b8c7ade18ff91c9e77912c898d9df4f13ed21c70129510064b0","target":"record","created_at":"2026-07-05T11:00:46Z","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":"ab1010fd363ebf8dbd29109f30def1b038c64b41b07cb1dddd7fe863024d76ff","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-09T02:10:46Z","title_canon_sha256":"a589c3c0fd90e14687a78f9b28703381d3357f538219c2439c92d7c40b69be58"},"schema_version":"1.0","source":{"id":"2505.05732","kind":"arxiv","version":1}},"canonical_sha256":"690996e4e4a3cd5b76a668b8e0e13169c1fc8850b135a72970689e0c38947c32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"690996e4e4a3cd5b76a668b8e0e13169c1fc8850b135a72970689e0c38947c32","first_computed_at":"2026-07-05T11:00:46.726593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:46.726593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ohx9JDJu3LKv/Qe5muzHcJlRh2QzX9CGqEzd4Q8uFlEDZU0Ht5ajm1AwXHmrnaXodlFpZDjbJyMX7n/2i2CtAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:46.727082Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05732","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f35205aed7260b8c7ade18ff91c9e77912c898d9df4f13ed21c70129510064b0","sha256:dadb11a0049f73cdb80f513925d1e1dd3c19d7744ab5db282484699b46a9ae4c"],"state_sha256":"b3cad93bcfac3df6e1891e880294a9f6dabab14dca9934072f5f9b0429e4ad6a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gTVq3Wlsf2zHR3WdMMhWteHiKBYWXokn/4i3UtluOpY9jKuVzoFCijZRvFlFxvTMg6zZEQLxfK67Xd9TQsjRDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T18:34:49.209789Z","bundle_sha256":"f4947b6b45ea6b8c20965c7bef20db450010352a452e261293cf6779e9a6b2df"}}