{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FTN76RF6UUB2HPMKDVM6US76DF","short_pith_number":"pith:FTN76RF6","canonical_record":{"source":{"id":"2503.19881","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T17:46:50Z","cross_cats_sorted":[],"title_canon_sha256":"81998303a90a18602222de32b065a0b65b659cc9aa87f45944be3a6763cde8f2","abstract_canon_sha256":"97942aae2713572fb1f3747f616cd54ee52442b81ab3c77d46dc7a3d8397ef26"},"schema_version":"1.0"},"canonical_sha256":"2cdbff44bea503a3bd8a1d59ea4bfe1959eec6c279275e36fab9fd07f72993d2","source":{"kind":"arxiv","id":"2503.19881","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19881","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19881v1","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19881","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"pith_short_12","alias_value":"FTN76RF6UUB2","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"pith_short_16","alias_value":"FTN76RF6UUB2HPMK","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"pith_short_8","alias_value":"FTN76RF6","created_at":"2026-07-05T10:39:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FTN76RF6UUB2HPMKDVM6US76DF","target":"record","payload":{"canonical_record":{"source":{"id":"2503.19881","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T17:46:50Z","cross_cats_sorted":[],"title_canon_sha256":"81998303a90a18602222de32b065a0b65b659cc9aa87f45944be3a6763cde8f2","abstract_canon_sha256":"97942aae2713572fb1f3747f616cd54ee52442b81ab3c77d46dc7a3d8397ef26"},"schema_version":"1.0"},"canonical_sha256":"2cdbff44bea503a3bd8a1d59ea4bfe1959eec6c279275e36fab9fd07f72993d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:03.055557Z","signature_b64":"tQnt1QsvM89tIw4URzAzK7k2TwW08tViheB/6SWX362CJhLQmywuTeiI/LWVbOgGGvtWRMaNMGFXkGaE860WBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cdbff44bea503a3bd8a1d59ea4bfe1959eec6c279275e36fab9fd07f72993d2","last_reissued_at":"2026-07-05T10:39:03.055036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:03.055036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.19881","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":"2026-07-05T10:39:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tPQ0KU4z0gZDfF6pP3/zXmsXYhLBtZ8zkSrH/zhonfDB7IGoxnS553fpu/TWuBQZSnnXax1O0aZj+FXLgTFYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:48:35.660808Z"},"content_sha256":"a83fb74d81a1edd6612760c69b586f055c39008fd20a9f62a0aa6b07ee3ee7b4","schema_version":"1.0","event_id":"sha256:a83fb74d81a1edd6612760c69b586f055c39008fd20a9f62a0aa6b07ee3ee7b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FTN76RF6UUB2HPMKDVM6US76DF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mask$^2$DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongtao Xie, Jianlong Yuan, Jiawei Liu, Qian He, Shancheng Fang, Siyu Zhou, Tianhao Qi, Wanquan Feng, Yongdong Zhang","submitted_at":"2025-03-25T17:46:50Z","abstract_excerpt":"Sora has unveiled the immense potential of the Diffusion Transformer (DiT) architecture in single-scene video generation. However, the more challenging task of multi-scene video generation, which offers broader applications, remains relatively underexplored. To bridge this gap, we propose Mask$^2$DiT, a novel approach that establishes fine-grained, one-to-one alignment between video segments and their corresponding text annotations. Specifically, we introduce a symmetric binary mask at each attention layer within the DiT architecture, ensuring that each text annotation applies exclusively to i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19881","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/2503.19881/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":"2026-07-05T10:39:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aZ1Qo7nPQIyApfP05Z62i3EqF6vyy4GyCVcjVeqFTgkDJZSS1t5mMLOtee21GznDgqbBj4ri4iy+mtIrgRPjBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:48:35.661456Z"},"content_sha256":"190ebb9ac771aab2d15fae79b00d366c715427eec95e7a572350146e3b69f776","schema_version":"1.0","event_id":"sha256:190ebb9ac771aab2d15fae79b00d366c715427eec95e7a572350146e3b69f776"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FTN76RF6UUB2HPMKDVM6US76DF/bundle.json","state_url":"https://pith.science/pith/FTN76RF6UUB2HPMKDVM6US76DF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FTN76RF6UUB2HPMKDVM6US76DF/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":"2026-07-07T06:48:35Z","links":{"resolver":"https://pith.science/pith/FTN76RF6UUB2HPMKDVM6US76DF","bundle":"https://pith.science/pith/FTN76RF6UUB2HPMKDVM6US76DF/bundle.json","state":"https://pith.science/pith/FTN76RF6UUB2HPMKDVM6US76DF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FTN76RF6UUB2HPMKDVM6US76DF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FTN76RF6UUB2HPMKDVM6US76DF","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":"97942aae2713572fb1f3747f616cd54ee52442b81ab3c77d46dc7a3d8397ef26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T17:46:50Z","title_canon_sha256":"81998303a90a18602222de32b065a0b65b659cc9aa87f45944be3a6763cde8f2"},"schema_version":"1.0","source":{"id":"2503.19881","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19881","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19881v1","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19881","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"pith_short_12","alias_value":"FTN76RF6UUB2","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"pith_short_16","alias_value":"FTN76RF6UUB2HPMK","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"pith_short_8","alias_value":"FTN76RF6","created_at":"2026-07-05T10:39:03Z"}],"graph_snapshots":[{"event_id":"sha256:190ebb9ac771aab2d15fae79b00d366c715427eec95e7a572350146e3b69f776","target":"graph","created_at":"2026-07-05T10:39:03Z","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/2503.19881/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sora has unveiled the immense potential of the Diffusion Transformer (DiT) architecture in single-scene video generation. However, the more challenging task of multi-scene video generation, which offers broader applications, remains relatively underexplored. To bridge this gap, we propose Mask$^2$DiT, a novel approach that establishes fine-grained, one-to-one alignment between video segments and their corresponding text annotations. Specifically, we introduce a symmetric binary mask at each attention layer within the DiT architecture, ensuring that each text annotation applies exclusively to i","authors_text":"Hongtao Xie, Jianlong Yuan, Jiawei Liu, Qian He, Shancheng Fang, Siyu Zhou, Tianhao Qi, Wanquan Feng, Yongdong Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T17:46:50Z","title":"Mask$^2$DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19881","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:a83fb74d81a1edd6612760c69b586f055c39008fd20a9f62a0aa6b07ee3ee7b4","target":"record","created_at":"2026-07-05T10:39:03Z","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":"97942aae2713572fb1f3747f616cd54ee52442b81ab3c77d46dc7a3d8397ef26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T17:46:50Z","title_canon_sha256":"81998303a90a18602222de32b065a0b65b659cc9aa87f45944be3a6763cde8f2"},"schema_version":"1.0","source":{"id":"2503.19881","kind":"arxiv","version":1}},"canonical_sha256":"2cdbff44bea503a3bd8a1d59ea4bfe1959eec6c279275e36fab9fd07f72993d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cdbff44bea503a3bd8a1d59ea4bfe1959eec6c279275e36fab9fd07f72993d2","first_computed_at":"2026-07-05T10:39:03.055036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:03.055036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tQnt1QsvM89tIw4URzAzK7k2TwW08tViheB/6SWX362CJhLQmywuTeiI/LWVbOgGGvtWRMaNMGFXkGaE860WBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:03.055557Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.19881","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a83fb74d81a1edd6612760c69b586f055c39008fd20a9f62a0aa6b07ee3ee7b4","sha256:190ebb9ac771aab2d15fae79b00d366c715427eec95e7a572350146e3b69f776"],"state_sha256":"efcd2165b82d6bc04bf5b0f8eed397c176a6fe479b50c5bc50f3030540d43d9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7BrmjgG+7iJ5hzOLv8XEllugtasifqN3ZA2aprAXCpJSa/OcMqy83jM/j2eloTwacErgdivDICaUBPEms5rtCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:48:35.664653Z","bundle_sha256":"b3ae4b93293122780f510828f14e770605809b8bba66925bbea0c41ff7d470ce"}}