{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TSFQLRLVGYK6BHY6Y3DPPMEIC5","short_pith_number":"pith:TSFQLRLV","canonical_record":{"source":{"id":"2507.04959","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T13:01:50Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"a2e43f73610edfdda473aa82fc86634f3395010c1cf7ee93098b5e72a7fe72b6","abstract_canon_sha256":"15b0d212579bfe84883c50c2c6c8e3d3fcca84220abfa18e7ea22839a0f59a0c"},"schema_version":"1.0"},"canonical_sha256":"9c8b05c5753615e09f1ec6c6f7b0881766729d5b2c5d7488fd14f1fb350bee34","source":{"kind":"arxiv","id":"2507.04959","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04959","created_at":"2026-07-05T11:35:57Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04959v2","created_at":"2026-07-05T11:35:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04959","created_at":"2026-07-05T11:35:57Z"},{"alias_kind":"pith_short_12","alias_value":"TSFQLRLVGYK6","created_at":"2026-07-05T11:35:57Z"},{"alias_kind":"pith_short_16","alias_value":"TSFQLRLVGYK6BHY6","created_at":"2026-07-05T11:35:57Z"},{"alias_kind":"pith_short_8","alias_value":"TSFQLRLV","created_at":"2026-07-05T11:35:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TSFQLRLVGYK6BHY6Y3DPPMEIC5","target":"record","payload":{"canonical_record":{"source":{"id":"2507.04959","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T13:01:50Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"a2e43f73610edfdda473aa82fc86634f3395010c1cf7ee93098b5e72a7fe72b6","abstract_canon_sha256":"15b0d212579bfe84883c50c2c6c8e3d3fcca84220abfa18e7ea22839a0f59a0c"},"schema_version":"1.0"},"canonical_sha256":"9c8b05c5753615e09f1ec6c6f7b0881766729d5b2c5d7488fd14f1fb350bee34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:57.919407Z","signature_b64":"YLJ5zZ6816XHfFnNGaFdNKBxvyR+SHNfvHvq5hNw1zRn2XRZl7e0bDpXPdFq2NCxVDo51CIsEYpA9Ku/y2JsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c8b05c5753615e09f1ec6c6f7b0881766729d5b2c5d7488fd14f1fb350bee34","last_reissued_at":"2026-07-05T11:35:57.918929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:57.918929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.04959","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":"2026-07-05T11:35:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NJbPC+0KaHenbjz3CHvn3ia/RFA4+bQ4MEyYCGzA8OyxhPNut4e4WwhTXTZxbTqc0mNVSpeiImNVk7yGd+0XDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:49:42.292044Z"},"content_sha256":"6b075fa51b7529b4f7598005f69bc0a38a2f38014aaf8bac0bc89017f13e7194","schema_version":"1.0","event_id":"sha256:6b075fa51b7529b4f7598005f69bc0a38a2f38014aaf8bac0bc89017f13e7194"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TSFQLRLVGYK6BHY6Y3DPPMEIC5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hear-Your-Click: Interactive Object-Specific Video-to-Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Jiasheng Lu, Keyu Fan, Peiwu Qin, Qingyang Shi, Xinyu Zhang, Yingshan Liang, Yiran Wang, Zhicheng Du","submitted_at":"2025-07-07T13:01:50Z","abstract_excerpt":"Video-to-audio (V2A) generation shows great potential in fields such as film production. Despite significant advances, current V2A methods relying on global video information struggle with complex scenes and generating audio tailored to specific objects. To address these limitations, we introduce Hear-Your-Click, an interactive V2A framework enabling users to generate sounds for specific objects by clicking on the frame. To achieve this, we propose Object-aware Contrastive Audio-Visual Fine-tuning (OCAV) with a Mask-guided Visual Encoder (MVE) to obtain object-level visual features aligned wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04959","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/2507.04959/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":"2026-07-05T11:35:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UKzcPIJZYVugJ0RT72fCVFqa0qRcolU7xTCqISOND9yAiyp2tHIiPgymdokQYSPka77JNPNQR/4Gmjzc0yt2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:49:42.292753Z"},"content_sha256":"7ec7e7255dfd5b2b331d363f4422f7129c4993fb1ab1488f911a1653a5e54ca6","schema_version":"1.0","event_id":"sha256:7ec7e7255dfd5b2b331d363f4422f7129c4993fb1ab1488f911a1653a5e54ca6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TSFQLRLVGYK6BHY6Y3DPPMEIC5/bundle.json","state_url":"https://pith.science/pith/TSFQLRLVGYK6BHY6Y3DPPMEIC5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TSFQLRLVGYK6BHY6Y3DPPMEIC5/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":"2026-08-05T09:49:42Z","links":{"resolver":"https://pith.science/pith/TSFQLRLVGYK6BHY6Y3DPPMEIC5","bundle":"https://pith.science/pith/TSFQLRLVGYK6BHY6Y3DPPMEIC5/bundle.json","state":"https://pith.science/pith/TSFQLRLVGYK6BHY6Y3DPPMEIC5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TSFQLRLVGYK6BHY6Y3DPPMEIC5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TSFQLRLVGYK6BHY6Y3DPPMEIC5","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":"15b0d212579bfe84883c50c2c6c8e3d3fcca84220abfa18e7ea22839a0f59a0c","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T13:01:50Z","title_canon_sha256":"a2e43f73610edfdda473aa82fc86634f3395010c1cf7ee93098b5e72a7fe72b6"},"schema_version":"1.0","source":{"id":"2507.04959","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04959","created_at":"2026-07-05T11:35:57Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04959v2","created_at":"2026-07-05T11:35:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04959","created_at":"2026-07-05T11:35:57Z"},{"alias_kind":"pith_short_12","alias_value":"TSFQLRLVGYK6","created_at":"2026-07-05T11:35:57Z"},{"alias_kind":"pith_short_16","alias_value":"TSFQLRLVGYK6BHY6","created_at":"2026-07-05T11:35:57Z"},{"alias_kind":"pith_short_8","alias_value":"TSFQLRLV","created_at":"2026-07-05T11:35:57Z"}],"graph_snapshots":[{"event_id":"sha256:7ec7e7255dfd5b2b331d363f4422f7129c4993fb1ab1488f911a1653a5e54ca6","target":"graph","created_at":"2026-07-05T11:35:57Z","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/2507.04959/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-to-audio (V2A) generation shows great potential in fields such as film production. Despite significant advances, current V2A methods relying on global video information struggle with complex scenes and generating audio tailored to specific objects. To address these limitations, we introduce Hear-Your-Click, an interactive V2A framework enabling users to generate sounds for specific objects by clicking on the frame. To achieve this, we propose Object-aware Contrastive Audio-Visual Fine-tuning (OCAV) with a Mask-guided Visual Encoder (MVE) to obtain object-level visual features aligned wit","authors_text":"Jiasheng Lu, Keyu Fan, Peiwu Qin, Qingyang Shi, Xinyu Zhang, Yingshan Liang, Yiran Wang, Zhicheng Du","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T13:01:50Z","title":"Hear-Your-Click: Interactive Object-Specific Video-to-Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04959","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":"sha256:6b075fa51b7529b4f7598005f69bc0a38a2f38014aaf8bac0bc89017f13e7194","target":"record","created_at":"2026-07-05T11:35:57Z","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":"15b0d212579bfe84883c50c2c6c8e3d3fcca84220abfa18e7ea22839a0f59a0c","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T13:01:50Z","title_canon_sha256":"a2e43f73610edfdda473aa82fc86634f3395010c1cf7ee93098b5e72a7fe72b6"},"schema_version":"1.0","source":{"id":"2507.04959","kind":"arxiv","version":2}},"canonical_sha256":"9c8b05c5753615e09f1ec6c6f7b0881766729d5b2c5d7488fd14f1fb350bee34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c8b05c5753615e09f1ec6c6f7b0881766729d5b2c5d7488fd14f1fb350bee34","first_computed_at":"2026-07-05T11:35:57.918929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:57.918929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YLJ5zZ6816XHfFnNGaFdNKBxvyR+SHNfvHvq5hNw1zRn2XRZl7e0bDpXPdFq2NCxVDo51CIsEYpA9Ku/y2JsAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:57.919407Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.04959","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b075fa51b7529b4f7598005f69bc0a38a2f38014aaf8bac0bc89017f13e7194","sha256:7ec7e7255dfd5b2b331d363f4422f7129c4993fb1ab1488f911a1653a5e54ca6"],"state_sha256":"7852035453275ac60495274e927a01831a1d9d0798205dd694c718df087cddb6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VJGGPnoVcz7q3hnnu0obELUbX0XcLQapSr8FmQq69UjIKGBfdENixVbvGh40vHLwEfhE3H25zVByxZ2JubMJCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:49:42.299330Z","bundle_sha256":"47c3e8ecafce9e614f5952d9f8bf488626224c55f29e2cd1ec0b9bd2d5739f85"}}