{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:USZUZ2RA2TRN447EOSIVZG7H5R","short_pith_number":"pith:USZUZ2RA","canonical_record":{"source":{"id":"2201.03809","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-01-11T06:59:21Z","cross_cats_sorted":["cs.GR","cs.MM","eess.AS"],"title_canon_sha256":"074a98159309957db78d3b3edbc4f876075eddbdc82b0885432084539a8695f9","abstract_canon_sha256":"febd60506c4d91564c155eeb6d5b429000e8ed0856fc2c84e0de792bb53075e9"},"schema_version":"1.0"},"canonical_sha256":"a4b34cea20d4e2de73e474915c9be7ec4b2239a5c5eb07a388b0b7059a2f642c","source":{"kind":"arxiv","id":"2201.03809","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.03809","created_at":"2026-07-05T04:30:20Z"},{"alias_kind":"arxiv_version","alias_value":"2201.03809v2","created_at":"2026-07-05T04:30:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.03809","created_at":"2026-07-05T04:30:20Z"},{"alias_kind":"pith_short_12","alias_value":"USZUZ2RA2TRN","created_at":"2026-07-05T04:30:20Z"},{"alias_kind":"pith_short_16","alias_value":"USZUZ2RA2TRN447E","created_at":"2026-07-05T04:30:20Z"},{"alias_kind":"pith_short_8","alias_value":"USZUZ2RA","created_at":"2026-07-05T04:30:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:USZUZ2RA2TRN447EOSIVZG7H5R","target":"record","payload":{"canonical_record":{"source":{"id":"2201.03809","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-01-11T06:59:21Z","cross_cats_sorted":["cs.GR","cs.MM","eess.AS"],"title_canon_sha256":"074a98159309957db78d3b3edbc4f876075eddbdc82b0885432084539a8695f9","abstract_canon_sha256":"febd60506c4d91564c155eeb6d5b429000e8ed0856fc2c84e0de792bb53075e9"},"schema_version":"1.0"},"canonical_sha256":"a4b34cea20d4e2de73e474915c9be7ec4b2239a5c5eb07a388b0b7059a2f642c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:20.712563Z","signature_b64":"fKWwCle8IElKEi5L2fxD3gQodYfP0ZwgatqSs8nKUGrtar+5a12MB3oVrZfhAdP+wa5+DE3LcdO5nl/lu+kpAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4b34cea20d4e2de73e474915c9be7ec4b2239a5c5eb07a388b0b7059a2f642c","last_reissued_at":"2026-07-05T04:30:20.712098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:20.712098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.03809","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:30:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aVRhzNBENMnRLIVq3IMVYSJFgDu60xciEjQxJFbvitUXH8/bMYYCV4gUTi4CLdfZii4TkLX/hPdIbAwCTaT1AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:38:23.413890Z"},"content_sha256":"d3b3ec913287cbf497acbcbcfb474e40d2eacd18869b44311379ed58b4965a50","schema_version":"1.0","event_id":"sha256:d3b3ec913287cbf497acbcbcfb474e40d2eacd18869b44311379ed58b4965a50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:USZUZ2RA2TRN447EOSIVZG7H5R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Music2Video: Automatic Generation of Music Video with fusion of audio and text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Joel Jang, Sumin Shin, Yoonjeon Kim","submitted_at":"2022-01-11T06:59:21Z","abstract_excerpt":"Creation of images using generative adversarial networks has been widely adapted into multi-modal regime with the advent of multi-modal representation models pre-trained on large corpus. Various modalities sharing a common representation space could be utilized to guide the generative models to create images from text or even from audio source. Departing from the previous methods that solely rely on either text or audio, we exploit the expressiveness of both modality. Based on the fusion of text and audio, we create video whose content is consistent with the distinct modalities that are provid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.03809","kind":"arxiv","version":2},"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/2201.03809/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":"2026-07-05T04:30:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QbbWXYsfOE0vUUffNFDj7o4kahI01X6mHI8uuYgS0eBGGUPWA+sXm2OrkvRn2jB02+cZfOMOPTFVyD4dhs5YCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:38:23.421746Z"},"content_sha256":"4e27501ae649268e727c9b2b0597f3cf6f9ed2552b042a2ebced9e46ad0506ca","schema_version":"1.0","event_id":"sha256:4e27501ae649268e727c9b2b0597f3cf6f9ed2552b042a2ebced9e46ad0506ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/USZUZ2RA2TRN447EOSIVZG7H5R/bundle.json","state_url":"https://pith.science/pith/USZUZ2RA2TRN447EOSIVZG7H5R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/USZUZ2RA2TRN447EOSIVZG7H5R/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":"2026-08-17T23:38:23Z","links":{"resolver":"https://pith.science/pith/USZUZ2RA2TRN447EOSIVZG7H5R","bundle":"https://pith.science/pith/USZUZ2RA2TRN447EOSIVZG7H5R/bundle.json","state":"https://pith.science/pith/USZUZ2RA2TRN447EOSIVZG7H5R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/USZUZ2RA2TRN447EOSIVZG7H5R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:USZUZ2RA2TRN447EOSIVZG7H5R","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":"febd60506c4d91564c155eeb6d5b429000e8ed0856fc2c84e0de792bb53075e9","cross_cats_sorted":["cs.GR","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-01-11T06:59:21Z","title_canon_sha256":"074a98159309957db78d3b3edbc4f876075eddbdc82b0885432084539a8695f9"},"schema_version":"1.0","source":{"id":"2201.03809","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.03809","created_at":"2026-07-05T04:30:20Z"},{"alias_kind":"arxiv_version","alias_value":"2201.03809v2","created_at":"2026-07-05T04:30:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.03809","created_at":"2026-07-05T04:30:20Z"},{"alias_kind":"pith_short_12","alias_value":"USZUZ2RA2TRN","created_at":"2026-07-05T04:30:20Z"},{"alias_kind":"pith_short_16","alias_value":"USZUZ2RA2TRN447E","created_at":"2026-07-05T04:30:20Z"},{"alias_kind":"pith_short_8","alias_value":"USZUZ2RA","created_at":"2026-07-05T04:30:20Z"}],"graph_snapshots":[{"event_id":"sha256:4e27501ae649268e727c9b2b0597f3cf6f9ed2552b042a2ebced9e46ad0506ca","target":"graph","created_at":"2026-07-05T04:30:20Z","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/2201.03809/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Creation of images using generative adversarial networks has been widely adapted into multi-modal regime with the advent of multi-modal representation models pre-trained on large corpus. Various modalities sharing a common representation space could be utilized to guide the generative models to create images from text or even from audio source. Departing from the previous methods that solely rely on either text or audio, we exploit the expressiveness of both modality. Based on the fusion of text and audio, we create video whose content is consistent with the distinct modalities that are provid","authors_text":"Joel Jang, Sumin Shin, Yoonjeon Kim","cross_cats":["cs.GR","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-01-11T06:59:21Z","title":"Music2Video: Automatic Generation of Music Video with fusion of audio and text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.03809","kind":"arxiv","version":2},"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:d3b3ec913287cbf497acbcbcfb474e40d2eacd18869b44311379ed58b4965a50","target":"record","created_at":"2026-07-05T04:30:20Z","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":"febd60506c4d91564c155eeb6d5b429000e8ed0856fc2c84e0de792bb53075e9","cross_cats_sorted":["cs.GR","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-01-11T06:59:21Z","title_canon_sha256":"074a98159309957db78d3b3edbc4f876075eddbdc82b0885432084539a8695f9"},"schema_version":"1.0","source":{"id":"2201.03809","kind":"arxiv","version":2}},"canonical_sha256":"a4b34cea20d4e2de73e474915c9be7ec4b2239a5c5eb07a388b0b7059a2f642c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4b34cea20d4e2de73e474915c9be7ec4b2239a5c5eb07a388b0b7059a2f642c","first_computed_at":"2026-07-05T04:30:20.712098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:30:20.712098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fKWwCle8IElKEi5L2fxD3gQodYfP0ZwgatqSs8nKUGrtar+5a12MB3oVrZfhAdP+wa5+DE3LcdO5nl/lu+kpAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:30:20.712563Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.03809","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3b3ec913287cbf497acbcbcfb474e40d2eacd18869b44311379ed58b4965a50","sha256:4e27501ae649268e727c9b2b0597f3cf6f9ed2552b042a2ebced9e46ad0506ca"],"state_sha256":"475d807276ab4bb86cc2c66cc61055338a04e6a5fa2e8b40667cec165de0db59"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YUiiX7Y99KFShFEYYg5w7BLasrABu0yCrQwoywUABwZuAstzCkcJTy/sBmI/Dus/TdRxoXacePvjjWaHf5rgDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:38:23.490534Z","bundle_sha256":"70406aadbd0d4d72ddc46ce9dac604a1180b04621c97694a73070be493a5d4d1"}}