{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OHCIT4CCVZ4OCMLIRAAWRMRDBM","short_pith_number":"pith:OHCIT4CC","canonical_record":{"source":{"id":"2605.22996","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T19:51:20Z","cross_cats_sorted":[],"title_canon_sha256":"5129958c7a511f58e43df83842b4d2b732085df4f7a7e591df2408f1c6467106","abstract_canon_sha256":"cd1e4a7eda56bc1aed657ee76005caab7904bce178715061e0c36fe568a1a5fa"},"schema_version":"1.0"},"canonical_sha256":"71c489f042ae78e13168880168b2230b3027fbe2326e525db24ee02cac58ddf7","source":{"kind":"arxiv","id":"2605.22996","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22996","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22996v1","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22996","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"pith_short_12","alias_value":"OHCIT4CCVZ4O","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"pith_short_16","alias_value":"OHCIT4CCVZ4OCMLI","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"pith_short_8","alias_value":"OHCIT4CC","created_at":"2026-05-25T02:01:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OHCIT4CCVZ4OCMLIRAAWRMRDBM","target":"record","payload":{"canonical_record":{"source":{"id":"2605.22996","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T19:51:20Z","cross_cats_sorted":[],"title_canon_sha256":"5129958c7a511f58e43df83842b4d2b732085df4f7a7e591df2408f1c6467106","abstract_canon_sha256":"cd1e4a7eda56bc1aed657ee76005caab7904bce178715061e0c36fe568a1a5fa"},"schema_version":"1.0"},"canonical_sha256":"71c489f042ae78e13168880168b2230b3027fbe2326e525db24ee02cac58ddf7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:33.719051Z","signature_b64":"yifrrfWnUVeDdQR4aUzELlsu8RclDK5XE/Un0CuSisB3TIX2hCtG71KgGcvsK+BOCA2vRxDxd/w528rlm61UAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71c489f042ae78e13168880168b2230b3027fbe2326e525db24ee02cac58ddf7","last_reissued_at":"2026-05-25T02:01:33.718346Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:33.718346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.22996","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":"2026-05-25T02:01:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fY9fpOpwxjkMz40pgSBOIgo6RZgCz+1n4PvCOj7vOiiWxrJrkYazu2WvT5fSQ+RXN0q8MUt0wPVOjRScjr5QAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T00:31:51.632143Z"},"content_sha256":"3e60857fe64afa35484fe201e68bb52f1a362afd329854743bc790a995be2714","schema_version":"1.0","event_id":"sha256:3e60857fe64afa35484fe201e68bb52f1a362afd329854743bc790a995be2714"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OHCIT4CCVZ4OCMLIRAAWRMRDBM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoMoGen: COntrollable MOtion Dynamics and Interactions with Mask-Guided Video GENeration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adil Meric, Benjamin Busam, Christian Theobalt, Lin Geng Foo, Mert Kiray, Rishabh Dabral","submitted_at":"2026-05-21T19:51:20Z","abstract_excerpt":"We present CoMoGen, a controllable video generation framework that generates realistic interactive dynamics from a single binary mask sequence conditioned on an input image. CoMoGen introduces a lightweight MaskAdapter that encodes binary mask sequences into a latent residual signal, injected into the Multi Modal Diffusion Transformer (MMDiT) model through a cosine-weighted schedule. Unlike the hierarchical coarse-to-fine design of UNet architectures, MMDiT operates as a sequence of uniform transformer blocks, making it difficult to identify which layers are responsible for the motion generati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22996","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/2605.22996/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":"2026-05-25T02:01:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g5YLgzt/9VeBuOyDMp/kOf8hwOeDPKwdgyR4m7MDmI0rp6nwP1iWT5zPTWodyliqtjSYmHPPHJ+nUiCDOkxdDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T00:31:51.632540Z"},"content_sha256":"42db9046ecb6adff212e59f8b2cdcda23081b17c9c851c4fbe22bfe930fa718b","schema_version":"1.0","event_id":"sha256:42db9046ecb6adff212e59f8b2cdcda23081b17c9c851c4fbe22bfe930fa718b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OHCIT4CCVZ4OCMLIRAAWRMRDBM/bundle.json","state_url":"https://pith.science/pith/OHCIT4CCVZ4OCMLIRAAWRMRDBM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OHCIT4CCVZ4OCMLIRAAWRMRDBM/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":"2026-05-28T00:31:51Z","links":{"resolver":"https://pith.science/pith/OHCIT4CCVZ4OCMLIRAAWRMRDBM","bundle":"https://pith.science/pith/OHCIT4CCVZ4OCMLIRAAWRMRDBM/bundle.json","state":"https://pith.science/pith/OHCIT4CCVZ4OCMLIRAAWRMRDBM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OHCIT4CCVZ4OCMLIRAAWRMRDBM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OHCIT4CCVZ4OCMLIRAAWRMRDBM","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":"cd1e4a7eda56bc1aed657ee76005caab7904bce178715061e0c36fe568a1a5fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T19:51:20Z","title_canon_sha256":"5129958c7a511f58e43df83842b4d2b732085df4f7a7e591df2408f1c6467106"},"schema_version":"1.0","source":{"id":"2605.22996","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22996","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22996v1","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22996","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"pith_short_12","alias_value":"OHCIT4CCVZ4O","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"pith_short_16","alias_value":"OHCIT4CCVZ4OCMLI","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"pith_short_8","alias_value":"OHCIT4CC","created_at":"2026-05-25T02:01:33Z"}],"graph_snapshots":[{"event_id":"sha256:42db9046ecb6adff212e59f8b2cdcda23081b17c9c851c4fbe22bfe930fa718b","target":"graph","created_at":"2026-05-25T02:01:33Z","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/2605.22996/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present CoMoGen, a controllable video generation framework that generates realistic interactive dynamics from a single binary mask sequence conditioned on an input image. CoMoGen introduces a lightweight MaskAdapter that encodes binary mask sequences into a latent residual signal, injected into the Multi Modal Diffusion Transformer (MMDiT) model through a cosine-weighted schedule. Unlike the hierarchical coarse-to-fine design of UNet architectures, MMDiT operates as a sequence of uniform transformer blocks, making it difficult to identify which layers are responsible for the motion generati","authors_text":"Adil Meric, Benjamin Busam, Christian Theobalt, Lin Geng Foo, Mert Kiray, Rishabh Dabral","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T19:51:20Z","title":"CoMoGen: COntrollable MOtion Dynamics and Interactions with Mask-Guided Video GENeration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22996","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":"sha256:3e60857fe64afa35484fe201e68bb52f1a362afd329854743bc790a995be2714","target":"record","created_at":"2026-05-25T02:01:33Z","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":"cd1e4a7eda56bc1aed657ee76005caab7904bce178715061e0c36fe568a1a5fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T19:51:20Z","title_canon_sha256":"5129958c7a511f58e43df83842b4d2b732085df4f7a7e591df2408f1c6467106"},"schema_version":"1.0","source":{"id":"2605.22996","kind":"arxiv","version":1}},"canonical_sha256":"71c489f042ae78e13168880168b2230b3027fbe2326e525db24ee02cac58ddf7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71c489f042ae78e13168880168b2230b3027fbe2326e525db24ee02cac58ddf7","first_computed_at":"2026-05-25T02:01:33.718346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:33.718346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yifrrfWnUVeDdQR4aUzELlsu8RclDK5XE/Un0CuSisB3TIX2hCtG71KgGcvsK+BOCA2vRxDxd/w528rlm61UAA==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:33.719051Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22996","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e60857fe64afa35484fe201e68bb52f1a362afd329854743bc790a995be2714","sha256:42db9046ecb6adff212e59f8b2cdcda23081b17c9c851c4fbe22bfe930fa718b"],"state_sha256":"71f89fc9f7f5aeb3a82078a58c9c22cfbb3150da6803f6cb97befc6b33700c4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AvVzEcd0WacNV1KCFIJgFL8Xo4+OlIoWtS5sJL3vlEnCwls1YWcoXS/qDHznRsY19iKcr/vv2Rn5uIIEu3tLCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T00:31:51.634621Z","bundle_sha256":"ca6678ab784a74b56cb12cf49e8d683f92c0a647ad3cd74c5f89ee43b0282bca"}}