{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HU52PQWJTTGCVOEHTMCKMJXZBF","short_pith_number":"pith:HU52PQWJ","canonical_record":{"source":{"id":"2509.04957","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-05T09:24:08Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"afa68ea04d884a662fefa159d6da98c4c01808f11fa179c88ea3d64c31edcc07","abstract_canon_sha256":"953d0f521ed91631cc05fca0288c8bccc6f23d6b02289f6c6d884d5bb6c562d7"},"schema_version":"1.0"},"canonical_sha256":"3d3ba7c2c99ccc2ab8879b04a626f909658a3a9295a304de4232f346517dbfd6","source":{"kind":"arxiv","id":"2509.04957","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04957","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04957v1","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04957","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"pith_short_12","alias_value":"HU52PQWJTTGC","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"pith_short_16","alias_value":"HU52PQWJTTGCVOEH","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"pith_short_8","alias_value":"HU52PQWJ","created_at":"2026-07-05T12:05:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HU52PQWJTTGCVOEHTMCKMJXZBF","target":"record","payload":{"canonical_record":{"source":{"id":"2509.04957","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-05T09:24:08Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"afa68ea04d884a662fefa159d6da98c4c01808f11fa179c88ea3d64c31edcc07","abstract_canon_sha256":"953d0f521ed91631cc05fca0288c8bccc6f23d6b02289f6c6d884d5bb6c562d7"},"schema_version":"1.0"},"canonical_sha256":"3d3ba7c2c99ccc2ab8879b04a626f909658a3a9295a304de4232f346517dbfd6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:33.311901Z","signature_b64":"v4NKYGYQfalU2diJhqwrsdcy1YjSh6gqnSW3dTAj8kYWNpPUYWgqbx73OHsGWHrbyfpPPh70Tu5EIegs+0SGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d3ba7c2c99ccc2ab8879b04a626f909658a3a9295a304de4232f346517dbfd6","last_reissued_at":"2026-07-05T12:05:33.311458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:33.311458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.04957","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":"2026-07-05T12:05:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QF7uSOP9zrUrnARfKBNyxfbFaQbVxW+fCjGSIVZLKbfE9me3kz1TmDebRTAS3fk2lF59Z+Met7NDh7hfGXn/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:47:25.387987Z"},"content_sha256":"b54507a1a332f6b2728786480ca6cccccc80f434b80376a4a09721467ceabd9a","schema_version":"1.0","event_id":"sha256:b54507a1a332f6b2728786480ca6cccccc80f434b80376a4a09721467ceabd9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HU52PQWJTTGCVOEHTMCKMJXZBF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Video-to-Audio Generation via Multiple Foundation Models Mapper","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Gehui Chen, Guan'an Wang, Jitao Sang, Xiaowen Huang","submitted_at":"2025-09-05T09:24:08Z","abstract_excerpt":"Recent Video-to-Audio (V2A) generation relies on extracting semantic and temporal features from video to condition generative models. Training these models from scratch is resource intensive. Consequently, leveraging foundation models (FMs) has gained traction due to their cross-modal knowledge transfer and generalization capabilities. One prior work has explored fine-tuning a lightweight mapper network to connect a pre-trained visual encoder with a text-to-audio generation model for V2A. Inspired by this, we introduce the Multiple Foundation Model Mapper (MFM-Mapper). Compared to the previous"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04957","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/2509.04957/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":"2026-07-05T12:05:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kym+DglJWiJZ74kpN8NMSXMzIdRDlGVARsCf78Kz/zUTGXy/myH6suFpBMHpdRpcQv8bgVUpB0Ao+gouRksqDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:47:25.388481Z"},"content_sha256":"4ce344671773831c3de0583be5f43069eb917faf76c5433cd879ac9776787aba","schema_version":"1.0","event_id":"sha256:4ce344671773831c3de0583be5f43069eb917faf76c5433cd879ac9776787aba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HU52PQWJTTGCVOEHTMCKMJXZBF/bundle.json","state_url":"https://pith.science/pith/HU52PQWJTTGCVOEHTMCKMJXZBF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HU52PQWJTTGCVOEHTMCKMJXZBF/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":"2026-08-06T06:47:25Z","links":{"resolver":"https://pith.science/pith/HU52PQWJTTGCVOEHTMCKMJXZBF","bundle":"https://pith.science/pith/HU52PQWJTTGCVOEHTMCKMJXZBF/bundle.json","state":"https://pith.science/pith/HU52PQWJTTGCVOEHTMCKMJXZBF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HU52PQWJTTGCVOEHTMCKMJXZBF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HU52PQWJTTGCVOEHTMCKMJXZBF","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":"953d0f521ed91631cc05fca0288c8bccc6f23d6b02289f6c6d884d5bb6c562d7","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-05T09:24:08Z","title_canon_sha256":"afa68ea04d884a662fefa159d6da98c4c01808f11fa179c88ea3d64c31edcc07"},"schema_version":"1.0","source":{"id":"2509.04957","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04957","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04957v1","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04957","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"pith_short_12","alias_value":"HU52PQWJTTGC","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"pith_short_16","alias_value":"HU52PQWJTTGCVOEH","created_at":"2026-07-05T12:05:33Z"},{"alias_kind":"pith_short_8","alias_value":"HU52PQWJ","created_at":"2026-07-05T12:05:33Z"}],"graph_snapshots":[{"event_id":"sha256:4ce344671773831c3de0583be5f43069eb917faf76c5433cd879ac9776787aba","target":"graph","created_at":"2026-07-05T12:05:33Z","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/2509.04957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Video-to-Audio (V2A) generation relies on extracting semantic and temporal features from video to condition generative models. Training these models from scratch is resource intensive. Consequently, leveraging foundation models (FMs) has gained traction due to their cross-modal knowledge transfer and generalization capabilities. One prior work has explored fine-tuning a lightweight mapper network to connect a pre-trained visual encoder with a text-to-audio generation model for V2A. Inspired by this, we introduce the Multiple Foundation Model Mapper (MFM-Mapper). Compared to the previous","authors_text":"Gehui Chen, Guan'an Wang, Jitao Sang, Xiaowen Huang","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-05T09:24:08Z","title":"Efficient Video-to-Audio Generation via Multiple Foundation Models Mapper"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04957","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:b54507a1a332f6b2728786480ca6cccccc80f434b80376a4a09721467ceabd9a","target":"record","created_at":"2026-07-05T12:05:33Z","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":"953d0f521ed91631cc05fca0288c8bccc6f23d6b02289f6c6d884d5bb6c562d7","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-05T09:24:08Z","title_canon_sha256":"afa68ea04d884a662fefa159d6da98c4c01808f11fa179c88ea3d64c31edcc07"},"schema_version":"1.0","source":{"id":"2509.04957","kind":"arxiv","version":1}},"canonical_sha256":"3d3ba7c2c99ccc2ab8879b04a626f909658a3a9295a304de4232f346517dbfd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d3ba7c2c99ccc2ab8879b04a626f909658a3a9295a304de4232f346517dbfd6","first_computed_at":"2026-07-05T12:05:33.311458Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:33.311458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v4NKYGYQfalU2diJhqwrsdcy1YjSh6gqnSW3dTAj8kYWNpPUYWgqbx73OHsGWHrbyfpPPh70Tu5EIegs+0SGBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:33.311901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.04957","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b54507a1a332f6b2728786480ca6cccccc80f434b80376a4a09721467ceabd9a","sha256:4ce344671773831c3de0583be5f43069eb917faf76c5433cd879ac9776787aba"],"state_sha256":"cafca3e6f37b6b3680c2a845ec2aed3b8a190b027bc7321b279ea9c890e0e17d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rcim2KChkjI8lDMVpQXalpAG7eEdKyR4U2ZhRsLfBF8UORwdoJg9VeL1txFXua1b6jcUjloKwh20B8ty1LHcAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:47:25.391796Z","bundle_sha256":"29362eda17c60f02b99aed6e5daafd2e57901539494f0dcf96054fbe209a1593"}}