{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SQQ23FVNIB2V7WCU2XCAVBUKFX","short_pith_number":"pith:SQQ23FVN","canonical_record":{"source":{"id":"2509.09547","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-11T15:39:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"884ab06151b3aa4160a9181c2993909debc3d899976619601c38e53b0809337c","abstract_canon_sha256":"1a7eb0de32322998b205843ea74b337913606d8aa573ca21811bf2a323e71a10"},"schema_version":"1.0"},"canonical_sha256":"9421ad96ad40755fd854d5c40a868a2dc4827c3c0c803ee1a503e24898161107","source":{"kind":"arxiv","id":"2509.09547","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09547","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09547v1","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09547","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"pith_short_12","alias_value":"SQQ23FVNIB2V","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"pith_short_16","alias_value":"SQQ23FVNIB2V7WCU","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"pith_short_8","alias_value":"SQQ23FVN","created_at":"2026-07-05T12:09:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SQQ23FVNIB2V7WCU2XCAVBUKFX","target":"record","payload":{"canonical_record":{"source":{"id":"2509.09547","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-11T15:39:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"884ab06151b3aa4160a9181c2993909debc3d899976619601c38e53b0809337c","abstract_canon_sha256":"1a7eb0de32322998b205843ea74b337913606d8aa573ca21811bf2a323e71a10"},"schema_version":"1.0"},"canonical_sha256":"9421ad96ad40755fd854d5c40a868a2dc4827c3c0c803ee1a503e24898161107","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:37.928781Z","signature_b64":"KqxUu42wJbnQewo/M+Gg8cHGwUFfv9FmMEsvhy2FEZrwMv0vUHs5vnJSiX4ipsGtr0SuV6WXBQkMuwL+gtsxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9421ad96ad40755fd854d5c40a868a2dc4827c3c0c803ee1a503e24898161107","last_reissued_at":"2026-07-05T12:09:37.928229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:37.928229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.09547","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":"2026-07-05T12:09:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GNcb6XYr2YqP8h7tmWH0GXpf8L8bhOPdzaTqMraNxJqOl5nAwh3rGK38866kXj3WqP4P0Gm1DT/br22FOzmVDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:32:48.060310Z"},"content_sha256":"37bd1d00f920af21256988b5ed1a85e63c6c55dd9da556b05561429a33932ab4","schema_version":"1.0","event_id":"sha256:37bd1d00f920af21256988b5ed1a85e63c6c55dd9da556b05561429a33932ab4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SQQ23FVNIB2V7WCU2XCAVBUKFX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Video Diffusion Transformer Training by Multi-Feature Fusion and Alignment from Self-Supervised Vision Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dohun Lee, Duygu Ceylan, Hyeonho Jeong, Jiwook Kim, Jong Chul Ye","submitted_at":"2025-09-11T15:39:27Z","abstract_excerpt":"Video diffusion models have advanced rapidly in the recent years as a result of series of architectural innovations (e.g., diffusion transformers) and use of novel training objectives (e.g., flow matching). In contrast, less attention has been paid to improving the feature representation power of such models. In this work, we show that training video diffusion models can benefit from aligning the intermediate features of the video generator with feature representations of pre-trained vision encoders. We propose a new metric and conduct an in-depth analysis of various vision encoders to evaluat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09547","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/2509.09547/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":"2026-07-05T12:09:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PrDSFrhQ5WHMn0ELNqYbYH2BD9H0Sv2LE5T4UOu6P4ZNmcoYgtaROsSeBCBv/jQ7HdvxG52RG6ETbVoNIH/PCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:32:48.060892Z"},"content_sha256":"52b89fc698135d8d134e447665ac6e6fa29ad57edcbc50dc3f31e534da7c8f6c","schema_version":"1.0","event_id":"sha256:52b89fc698135d8d134e447665ac6e6fa29ad57edcbc50dc3f31e534da7c8f6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SQQ23FVNIB2V7WCU2XCAVBUKFX/bundle.json","state_url":"https://pith.science/pith/SQQ23FVNIB2V7WCU2XCAVBUKFX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SQQ23FVNIB2V7WCU2XCAVBUKFX/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":"2026-08-05T09:32:48Z","links":{"resolver":"https://pith.science/pith/SQQ23FVNIB2V7WCU2XCAVBUKFX","bundle":"https://pith.science/pith/SQQ23FVNIB2V7WCU2XCAVBUKFX/bundle.json","state":"https://pith.science/pith/SQQ23FVNIB2V7WCU2XCAVBUKFX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SQQ23FVNIB2V7WCU2XCAVBUKFX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SQQ23FVNIB2V7WCU2XCAVBUKFX","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":"1a7eb0de32322998b205843ea74b337913606d8aa573ca21811bf2a323e71a10","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-11T15:39:27Z","title_canon_sha256":"884ab06151b3aa4160a9181c2993909debc3d899976619601c38e53b0809337c"},"schema_version":"1.0","source":{"id":"2509.09547","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09547","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09547v1","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09547","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"pith_short_12","alias_value":"SQQ23FVNIB2V","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"pith_short_16","alias_value":"SQQ23FVNIB2V7WCU","created_at":"2026-07-05T12:09:37Z"},{"alias_kind":"pith_short_8","alias_value":"SQQ23FVN","created_at":"2026-07-05T12:09:37Z"}],"graph_snapshots":[{"event_id":"sha256:52b89fc698135d8d134e447665ac6e6fa29ad57edcbc50dc3f31e534da7c8f6c","target":"graph","created_at":"2026-07-05T12:09:37Z","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/2509.09547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video diffusion models have advanced rapidly in the recent years as a result of series of architectural innovations (e.g., diffusion transformers) and use of novel training objectives (e.g., flow matching). In contrast, less attention has been paid to improving the feature representation power of such models. In this work, we show that training video diffusion models can benefit from aligning the intermediate features of the video generator with feature representations of pre-trained vision encoders. We propose a new metric and conduct an in-depth analysis of various vision encoders to evaluat","authors_text":"Dohun Lee, Duygu Ceylan, Hyeonho Jeong, Jiwook Kim, Jong Chul Ye","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-11T15:39:27Z","title":"Improving Video Diffusion Transformer Training by Multi-Feature Fusion and Alignment from Self-Supervised Vision Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09547","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":"sha256:37bd1d00f920af21256988b5ed1a85e63c6c55dd9da556b05561429a33932ab4","target":"record","created_at":"2026-07-05T12:09:37Z","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":"1a7eb0de32322998b205843ea74b337913606d8aa573ca21811bf2a323e71a10","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-11T15:39:27Z","title_canon_sha256":"884ab06151b3aa4160a9181c2993909debc3d899976619601c38e53b0809337c"},"schema_version":"1.0","source":{"id":"2509.09547","kind":"arxiv","version":1}},"canonical_sha256":"9421ad96ad40755fd854d5c40a868a2dc4827c3c0c803ee1a503e24898161107","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9421ad96ad40755fd854d5c40a868a2dc4827c3c0c803ee1a503e24898161107","first_computed_at":"2026-07-05T12:09:37.928229Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:37.928229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KqxUu42wJbnQewo/M+Gg8cHGwUFfv9FmMEsvhy2FEZrwMv0vUHs5vnJSiX4ipsGtr0SuV6WXBQkMuwL+gtsxDA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:37.928781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.09547","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37bd1d00f920af21256988b5ed1a85e63c6c55dd9da556b05561429a33932ab4","sha256:52b89fc698135d8d134e447665ac6e6fa29ad57edcbc50dc3f31e534da7c8f6c"],"state_sha256":"be510872f978331dcf136f5a5856fe4bfda5609cb8afe8059ae7b135315ac573"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"izHV5/V/OkvIGbpPvfPaylKCdooAu0MtW1JkuGdB1xbepTODQLU8m/g+w8+SjM63SOVgvqTf1xyHaPYQKxipCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:32:48.069701Z","bundle_sha256":"5e3b00eaa34612f01db1a886d966abe2613e5ec8d78ef1636c3cfb19671494fe"}}