{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3LMCLTTUNBFHE6CO76JJCMKFCK","short_pith_number":"pith:3LMCLTTU","schema_version":"1.0","canonical_sha256":"dad825ce74684a72784eff929131451289f37529e092b58b31ef14c5211a2804","source":{"kind":"arxiv","id":"2512.24731","version":2},"attestation_state":"computed","paper":{"title":"EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingxuan Li, Longyin Wen, Shu Zhang, Yicheng He, Yiming Cui, Yiwei Wang, Yulei Niu","submitted_at":"2025-12-31T08:58:30Z","abstract_excerpt":"Sound effects build an essential layer of multimodal storytelling, shaping the emotional atmosphere and the narrative semantics of videos. Despite recent advancement in video-text-to-audio (VT2A), the current formulation faces three key limitations: First, an imbalance between visual and textual conditioning that leads to visual dominance; Second, the absence of a concrete definition for fine-grained controllable generation; Third, weak instruction understanding and following, as existing datasets rely on brief categorical tags. To address these limitations, we introduce EchoFoley, a new task "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2512.24731","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-31T08:58:30Z","cross_cats_sorted":[],"title_canon_sha256":"68d75ef57bb739579b42b6a8217dcaa5f5771955b90b70e0222031a6a656b969","abstract_canon_sha256":"301042d6706050ccb1a2317939f88f2ab27d26026462ef78ed5925a816a5d38d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:24.407929Z","signature_b64":"rA3rctTqDYXc35QAe5MjAj/StEGKfZeLD7sB9a9FrubthDr+ZavR9hFn7FPDtpx6GN1kfZwZ4bC1+Ar/QZ8xCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dad825ce74684a72784eff929131451289f37529e092b58b31ef14c5211a2804","last_reissued_at":"2026-06-24T01:14:24.407467Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:24.407467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingxuan Li, Longyin Wen, Shu Zhang, Yicheng He, Yiming Cui, Yiwei Wang, Yulei Niu","submitted_at":"2025-12-31T08:58:30Z","abstract_excerpt":"Sound effects build an essential layer of multimodal storytelling, shaping the emotional atmosphere and the narrative semantics of videos. Despite recent advancement in video-text-to-audio (VT2A), the current formulation faces three key limitations: First, an imbalance between visual and textual conditioning that leads to visual dominance; Second, the absence of a concrete definition for fine-grained controllable generation; Third, weak instruction understanding and following, as existing datasets rely on brief categorical tags. To address these limitations, we introduce EchoFoley, a new task "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.24731","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/2512.24731/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2512.24731","created_at":"2026-06-24T01:14:24.407527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.24731v2","created_at":"2026-06-24T01:14:24.407527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.24731","created_at":"2026-06-24T01:14:24.407527+00:00"},{"alias_kind":"pith_short_12","alias_value":"3LMCLTTUNBFH","created_at":"2026-06-24T01:14:24.407527+00:00"},{"alias_kind":"pith_short_16","alias_value":"3LMCLTTUNBFHE6CO","created_at":"2026-06-24T01:14:24.407527+00:00"},{"alias_kind":"pith_short_8","alias_value":"3LMCLTTU","created_at":"2026-06-24T01:14:24.407527+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3LMCLTTUNBFHE6CO76JJCMKFCK","json":"https://pith.science/pith/3LMCLTTUNBFHE6CO76JJCMKFCK.json","graph_json":"https://pith.science/api/pith-number/3LMCLTTUNBFHE6CO76JJCMKFCK/graph.json","events_json":"https://pith.science/api/pith-number/3LMCLTTUNBFHE6CO76JJCMKFCK/events.json","paper":"https://pith.science/paper/3LMCLTTU"},"agent_actions":{"view_html":"https://pith.science/pith/3LMCLTTUNBFHE6CO76JJCMKFCK","download_json":"https://pith.science/pith/3LMCLTTUNBFHE6CO76JJCMKFCK.json","view_paper":"https://pith.science/paper/3LMCLTTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.24731&json=true","fetch_graph":"https://pith.science/api/pith-number/3LMCLTTUNBFHE6CO76JJCMKFCK/graph.json","fetch_events":"https://pith.science/api/pith-number/3LMCLTTUNBFHE6CO76JJCMKFCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3LMCLTTUNBFHE6CO76JJCMKFCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3LMCLTTUNBFHE6CO76JJCMKFCK/action/storage_attestation","attest_author":"https://pith.science/pith/3LMCLTTUNBFHE6CO76JJCMKFCK/action/author_attestation","sign_citation":"https://pith.science/pith/3LMCLTTUNBFHE6CO76JJCMKFCK/action/citation_signature","submit_replication":"https://pith.science/pith/3LMCLTTUNBFHE6CO76JJCMKFCK/action/replication_record"}},"created_at":"2026-06-24T01:14:24.407527+00:00","updated_at":"2026-06-24T01:14:24.407527+00:00"}