{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4TG5XPAN2L6MIKTLZTESF7T4OK","short_pith_number":"pith:4TG5XPAN","canonical_record":{"source":{"id":"2405.01434","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-02T16:25:16Z","cross_cats_sorted":[],"title_canon_sha256":"fa0d41d4a8a4c793398e006d252c19f5f8fa8b379f397d33dfd694377efbcf1b","abstract_canon_sha256":"deb682963629c170197b1e2ad34a170d3cfd2d108707e1aae9890b6ecd6aef38"},"schema_version":"1.0"},"canonical_sha256":"e4cddbbc0dd2fcc42a6bccc922fe7c72a52c586f9f09a19c1b18e3638fd40801","source":{"kind":"arxiv","id":"2405.01434","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.01434","created_at":"2026-07-05T08:14:45Z"},{"alias_kind":"arxiv_version","alias_value":"2405.01434v1","created_at":"2026-07-05T08:14:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01434","created_at":"2026-07-05T08:14:45Z"},{"alias_kind":"pith_short_12","alias_value":"4TG5XPAN2L6M","created_at":"2026-07-05T08:14:45Z"},{"alias_kind":"pith_short_16","alias_value":"4TG5XPAN2L6MIKTL","created_at":"2026-07-05T08:14:45Z"},{"alias_kind":"pith_short_8","alias_value":"4TG5XPAN","created_at":"2026-07-05T08:14:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4TG5XPAN2L6MIKTLZTESF7T4OK","target":"record","payload":{"canonical_record":{"source":{"id":"2405.01434","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-02T16:25:16Z","cross_cats_sorted":[],"title_canon_sha256":"fa0d41d4a8a4c793398e006d252c19f5f8fa8b379f397d33dfd694377efbcf1b","abstract_canon_sha256":"deb682963629c170197b1e2ad34a170d3cfd2d108707e1aae9890b6ecd6aef38"},"schema_version":"1.0"},"canonical_sha256":"e4cddbbc0dd2fcc42a6bccc922fe7c72a52c586f9f09a19c1b18e3638fd40801","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:45.147786Z","signature_b64":"erRMacsaBT1Gd6mTjGiaWb726vqzzryaFAD75jlvo6XRkNncyxHeAAHwfiyHQ/Gb/uPsJO5ui8O4oabXw9m2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4cddbbc0dd2fcc42a6bccc922fe7c72a52c586f9f09a19c1b18e3638fd40801","last_reissued_at":"2026-07-05T08:14:45.147278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:45.147278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.01434","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":"2026-07-05T08:14:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0ZZRe5JYa21DyXdNVe25XcbcvCov99jzf1RrkXg6GLW3Uw2ZlhJlAOwU2Umh/2DJ32uJI9Wws7n2NRMo8VcxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:38:05.631753Z"},"content_sha256":"8fdbf83714b8bfb6f0c14d5cc60fd9ea9a17be069f7703a7c5f6010e674587d3","schema_version":"1.0","event_id":"sha256:8fdbf83714b8bfb6f0c14d5cc60fd9ea9a17be069f7703a7c5f6010e674587d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4TG5XPAN2L6MIKTLZTESF7T4OK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daquan Zhou, Jiashi Feng, Ming-Ming Cheng, Qibin Hou, Yupeng Zhou","submitted_at":"2024-05-02T16:25:16Z","abstract_excerpt":"For recent diffusion-based generative models, maintaining consistent content across a series of generated images, especially those containing subjects and complex details, presents a significant challenge. In this paper, we propose a new way of self-attention calculation, termed Consistent Self-Attention, that significantly boosts the consistency between the generated images and augments prevalent pretrained diffusion-based text-to-image models in a zero-shot manner. To extend our method to long-range video generation, we further introduce a novel semantic space temporal motion prediction modu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01434","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/2405.01434/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":"2026-07-05T08:14:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KA7iquMGRwsIlTEJ3GjJeEJjX1EKd2dajjO0+8oxr4Z1uvaQQCMy9cjJ+hGdA+l5673+yuPQQnKtgIpC5MYiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:38:05.632117Z"},"content_sha256":"4c402a4f5d279356c45fbc31de0d63eec046b3fd187b7d66c3dfc4d56d6e92d3","schema_version":"1.0","event_id":"sha256:4c402a4f5d279356c45fbc31de0d63eec046b3fd187b7d66c3dfc4d56d6e92d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4TG5XPAN2L6MIKTLZTESF7T4OK/bundle.json","state_url":"https://pith.science/pith/4TG5XPAN2L6MIKTLZTESF7T4OK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4TG5XPAN2L6MIKTLZTESF7T4OK/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":"2026-07-06T19:38:05Z","links":{"resolver":"https://pith.science/pith/4TG5XPAN2L6MIKTLZTESF7T4OK","bundle":"https://pith.science/pith/4TG5XPAN2L6MIKTLZTESF7T4OK/bundle.json","state":"https://pith.science/pith/4TG5XPAN2L6MIKTLZTESF7T4OK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4TG5XPAN2L6MIKTLZTESF7T4OK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4TG5XPAN2L6MIKTLZTESF7T4OK","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":"deb682963629c170197b1e2ad34a170d3cfd2d108707e1aae9890b6ecd6aef38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-02T16:25:16Z","title_canon_sha256":"fa0d41d4a8a4c793398e006d252c19f5f8fa8b379f397d33dfd694377efbcf1b"},"schema_version":"1.0","source":{"id":"2405.01434","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.01434","created_at":"2026-07-05T08:14:45Z"},{"alias_kind":"arxiv_version","alias_value":"2405.01434v1","created_at":"2026-07-05T08:14:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01434","created_at":"2026-07-05T08:14:45Z"},{"alias_kind":"pith_short_12","alias_value":"4TG5XPAN2L6M","created_at":"2026-07-05T08:14:45Z"},{"alias_kind":"pith_short_16","alias_value":"4TG5XPAN2L6MIKTL","created_at":"2026-07-05T08:14:45Z"},{"alias_kind":"pith_short_8","alias_value":"4TG5XPAN","created_at":"2026-07-05T08:14:45Z"}],"graph_snapshots":[{"event_id":"sha256:4c402a4f5d279356c45fbc31de0d63eec046b3fd187b7d66c3dfc4d56d6e92d3","target":"graph","created_at":"2026-07-05T08:14:45Z","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/2405.01434/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For recent diffusion-based generative models, maintaining consistent content across a series of generated images, especially those containing subjects and complex details, presents a significant challenge. In this paper, we propose a new way of self-attention calculation, termed Consistent Self-Attention, that significantly boosts the consistency between the generated images and augments prevalent pretrained diffusion-based text-to-image models in a zero-shot manner. To extend our method to long-range video generation, we further introduce a novel semantic space temporal motion prediction modu","authors_text":"Daquan Zhou, Jiashi Feng, Ming-Ming Cheng, Qibin Hou, Yupeng Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-02T16:25:16Z","title":"StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01434","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":"sha256:8fdbf83714b8bfb6f0c14d5cc60fd9ea9a17be069f7703a7c5f6010e674587d3","target":"record","created_at":"2026-07-05T08:14:45Z","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":"deb682963629c170197b1e2ad34a170d3cfd2d108707e1aae9890b6ecd6aef38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-02T16:25:16Z","title_canon_sha256":"fa0d41d4a8a4c793398e006d252c19f5f8fa8b379f397d33dfd694377efbcf1b"},"schema_version":"1.0","source":{"id":"2405.01434","kind":"arxiv","version":1}},"canonical_sha256":"e4cddbbc0dd2fcc42a6bccc922fe7c72a52c586f9f09a19c1b18e3638fd40801","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4cddbbc0dd2fcc42a6bccc922fe7c72a52c586f9f09a19c1b18e3638fd40801","first_computed_at":"2026-07-05T08:14:45.147278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:14:45.147278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"erRMacsaBT1Gd6mTjGiaWb726vqzzryaFAD75jlvo6XRkNncyxHeAAHwfiyHQ/Gb/uPsJO5ui8O4oabXw9m2Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:14:45.147786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.01434","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fdbf83714b8bfb6f0c14d5cc60fd9ea9a17be069f7703a7c5f6010e674587d3","sha256:4c402a4f5d279356c45fbc31de0d63eec046b3fd187b7d66c3dfc4d56d6e92d3"],"state_sha256":"39322d21fa57411d5a415fdb0c6da0b2a85febc88b665ad7679917f72a03263a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v6eK1u1t42RDd8HtDf+OHu+P5chx0MoOXFChAC+G5cU1l63/IQOjVnpFZsTdsqHvC2luu9lBRhc56O7BmGuECA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:38:05.634139Z","bundle_sha256":"684c2f4672713b5790144093946e3c5d5eb365ccba8ae527a350faee7e35fa68"}}