{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZDGD7KZ4SK5AE2DVAXGYE6OCDP","short_pith_number":"pith:ZDGD7KZ4","canonical_record":{"source":{"id":"2501.07647","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-13T19:17:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1916c31f8bc2019fe599c2573a6a65f195a4bcf16f7b5c63ad729d394b72cc6f","abstract_canon_sha256":"60dc19a32bb92804661006c31f26bc1eb57fa21bab27a9d78e4e5f58ddb8f781"},"schema_version":"1.0"},"canonical_sha256":"c8cc3fab3c92ba02687505cd8279c21bf1b73389fb88e1153e759db23fbbe33e","source":{"kind":"arxiv","id":"2501.07647","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07647","created_at":"2026-07-05T10:00:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07647v1","created_at":"2026-07-05T10:00:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07647","created_at":"2026-07-05T10:00:48Z"},{"alias_kind":"pith_short_12","alias_value":"ZDGD7KZ4SK5A","created_at":"2026-07-05T10:00:48Z"},{"alias_kind":"pith_short_16","alias_value":"ZDGD7KZ4SK5AE2DV","created_at":"2026-07-05T10:00:48Z"},{"alias_kind":"pith_short_8","alias_value":"ZDGD7KZ4","created_at":"2026-07-05T10:00:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZDGD7KZ4SK5AE2DVAXGYE6OCDP","target":"record","payload":{"canonical_record":{"source":{"id":"2501.07647","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-13T19:17:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1916c31f8bc2019fe599c2573a6a65f195a4bcf16f7b5c63ad729d394b72cc6f","abstract_canon_sha256":"60dc19a32bb92804661006c31f26bc1eb57fa21bab27a9d78e4e5f58ddb8f781"},"schema_version":"1.0"},"canonical_sha256":"c8cc3fab3c92ba02687505cd8279c21bf1b73389fb88e1153e759db23fbbe33e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:48.046986Z","signature_b64":"uGXQNM90Ifo4geFZhMvzPeNNiAETSGP4h0Ui/VoSE0K/oeUHlDJ7fre+3Ns71Jalr/rMZZNe06LP/Rr3ExGDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8cc3fab3c92ba02687505cd8279c21bf1b73389fb88e1153e759db23fbbe33e","last_reissued_at":"2026-07-05T10:00:48.046487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:48.046487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.07647","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":"2026-07-05T10:00:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F6RRE54IrPrWCzJHo5BcIacUYNMOto0kRx0RHMDcVvGw7LRFdqXeuA+Vv062NlWcuk6nXFAk88AHAvUR1WMvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:09:57.328773Z"},"content_sha256":"f2a89f22b36ab716475f807b737722d4c95a7e93e9e1b6eb475f54fe76b88a66","schema_version":"1.0","event_id":"sha256:f2a89f22b36ab716475f807b737722d4c95a7e93e9e1b6eb475f54fe76b88a66"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZDGD7KZ4SK5AE2DVAXGYE6OCDP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Arash Vahdat, Chao Liu, Sifei Liu, Weili Nie, Weixi Feng, William Yang Wang","submitted_at":"2025-01-13T19:17:06Z","abstract_excerpt":"Existing video generation models struggle to follow complex text prompts and synthesize multiple objects, raising the need for additional grounding input for improved controllability. In this work, we propose to decompose videos into visual primitives - blob video representation, a general representation for controllable video generation. Based on blob conditions, we develop a blob-grounded video diffusion model named BlobGEN-Vid that allows users to control object motions and fine-grained object appearance. In particular, we introduce a masked 3D attention module that effectively improves reg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07647","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/2501.07647/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":"2026-07-05T10:00:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zkJs8vE2KBdNusTT2IPq7kWSse1x4KuruyIBLpajBW8RVOK0Bx5/qQANgMr5k7QnS+XS2TtEMfXF9K64Nr+CAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:09:57.329266Z"},"content_sha256":"6482532c3ec262b8729edbe673f1a3a807135f062845873076ca9b32dc282091","schema_version":"1.0","event_id":"sha256:6482532c3ec262b8729edbe673f1a3a807135f062845873076ca9b32dc282091"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZDGD7KZ4SK5AE2DVAXGYE6OCDP/bundle.json","state_url":"https://pith.science/pith/ZDGD7KZ4SK5AE2DVAXGYE6OCDP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZDGD7KZ4SK5AE2DVAXGYE6OCDP/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":"2026-08-12T19:09:57Z","links":{"resolver":"https://pith.science/pith/ZDGD7KZ4SK5AE2DVAXGYE6OCDP","bundle":"https://pith.science/pith/ZDGD7KZ4SK5AE2DVAXGYE6OCDP/bundle.json","state":"https://pith.science/pith/ZDGD7KZ4SK5AE2DVAXGYE6OCDP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZDGD7KZ4SK5AE2DVAXGYE6OCDP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZDGD7KZ4SK5AE2DVAXGYE6OCDP","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":"60dc19a32bb92804661006c31f26bc1eb57fa21bab27a9d78e4e5f58ddb8f781","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-13T19:17:06Z","title_canon_sha256":"1916c31f8bc2019fe599c2573a6a65f195a4bcf16f7b5c63ad729d394b72cc6f"},"schema_version":"1.0","source":{"id":"2501.07647","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07647","created_at":"2026-07-05T10:00:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07647v1","created_at":"2026-07-05T10:00:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07647","created_at":"2026-07-05T10:00:48Z"},{"alias_kind":"pith_short_12","alias_value":"ZDGD7KZ4SK5A","created_at":"2026-07-05T10:00:48Z"},{"alias_kind":"pith_short_16","alias_value":"ZDGD7KZ4SK5AE2DV","created_at":"2026-07-05T10:00:48Z"},{"alias_kind":"pith_short_8","alias_value":"ZDGD7KZ4","created_at":"2026-07-05T10:00:48Z"}],"graph_snapshots":[{"event_id":"sha256:6482532c3ec262b8729edbe673f1a3a807135f062845873076ca9b32dc282091","target":"graph","created_at":"2026-07-05T10:00:48Z","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/2501.07647/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing video generation models struggle to follow complex text prompts and synthesize multiple objects, raising the need for additional grounding input for improved controllability. In this work, we propose to decompose videos into visual primitives - blob video representation, a general representation for controllable video generation. Based on blob conditions, we develop a blob-grounded video diffusion model named BlobGEN-Vid that allows users to control object motions and fine-grained object appearance. In particular, we introduce a masked 3D attention module that effectively improves reg","authors_text":"Arash Vahdat, Chao Liu, Sifei Liu, Weili Nie, Weixi Feng, William Yang Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-13T19:17:06Z","title":"BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07647","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:f2a89f22b36ab716475f807b737722d4c95a7e93e9e1b6eb475f54fe76b88a66","target":"record","created_at":"2026-07-05T10:00:48Z","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":"60dc19a32bb92804661006c31f26bc1eb57fa21bab27a9d78e4e5f58ddb8f781","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-13T19:17:06Z","title_canon_sha256":"1916c31f8bc2019fe599c2573a6a65f195a4bcf16f7b5c63ad729d394b72cc6f"},"schema_version":"1.0","source":{"id":"2501.07647","kind":"arxiv","version":1}},"canonical_sha256":"c8cc3fab3c92ba02687505cd8279c21bf1b73389fb88e1153e759db23fbbe33e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8cc3fab3c92ba02687505cd8279c21bf1b73389fb88e1153e759db23fbbe33e","first_computed_at":"2026-07-05T10:00:48.046487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:48.046487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uGXQNM90Ifo4geFZhMvzPeNNiAETSGP4h0Ui/VoSE0K/oeUHlDJ7fre+3Ns71Jalr/rMZZNe06LP/Rr3ExGDCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:48.046986Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.07647","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2a89f22b36ab716475f807b737722d4c95a7e93e9e1b6eb475f54fe76b88a66","sha256:6482532c3ec262b8729edbe673f1a3a807135f062845873076ca9b32dc282091"],"state_sha256":"5e0fb3e1c1dea2cee2fc21600a690a6aeb7336cce48f7eae3080b9f1a120c2ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tt5HYoWVespCICh57GRMOCgz2oIzEcVqQQ/MGMYi8MIcIFZpCCVNwpcI2NSUJvjR4gLkKGyKfm/Q5gW8eqGFDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T19:09:57.333445Z","bundle_sha256":"e139ababacf23f69c972ca44e51f00e425285cb226456dfea37a9d3ab31a8815"}}