{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A52ZRHYOMM4V72QU5N4FXMHWO4","short_pith_number":"pith:A52ZRHYO","schema_version":"1.0","canonical_sha256":"0775989f0e63395fea14eb785bb0f6772580545bbd884259407c990e071602f6","source":{"kind":"arxiv","id":"2506.01111","version":1},"attestation_state":"computed","paper":{"title":"FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Benyou Wang, Liyan Zhao, Owen Lee, Qilin Sun, Shunian Chen, Xinyuan Xie, Zhan Su, Zheshu Chen","submitted_at":"2025-06-01T18:29:17Z","abstract_excerpt":"High-quality, large-scale audio captioning is crucial for advancing audio understanding, yet current automated methods often generate captions that lack fine-grained detail and contextual accuracy, primarily due to their reliance on limited unimodal or superficial multimodal information. Drawing inspiration from human auditory perception, which adeptly integrates cross-modal cues and performs sophisticated auditory scene analysis, we introduce a novel two-stage automated pipeline. This pipeline first employs specialized pretrained models to extract diverse contextual cues (e.g., speech, music,"},"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":"2506.01111","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-01T18:29:17Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"dc06be108eeaf1a4062f66bd2325551b3b1fa123ede587e84590b40485326eff","abstract_canon_sha256":"7d765abd7e46f5292e939a41dec91068097f663d74a8d30f7870d3638d8d1187"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:46.568672Z","signature_b64":"NpFt5d8A3MnKwbrDGep6ZnU1mVvWwTo0mk+PTmPHoUx0em+iFMTzZdgRhlvp2jtL5SJWktcVPmpamjrfoNCBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0775989f0e63395fea14eb785bb0f6772580545bbd884259407c990e071602f6","last_reissued_at":"2026-07-05T11:13:46.568121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:46.568121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Benyou Wang, Liyan Zhao, Owen Lee, Qilin Sun, Shunian Chen, Xinyuan Xie, Zhan Su, Zheshu Chen","submitted_at":"2025-06-01T18:29:17Z","abstract_excerpt":"High-quality, large-scale audio captioning is crucial for advancing audio understanding, yet current automated methods often generate captions that lack fine-grained detail and contextual accuracy, primarily due to their reliance on limited unimodal or superficial multimodal information. Drawing inspiration from human auditory perception, which adeptly integrates cross-modal cues and performs sophisticated auditory scene analysis, we introduce a novel two-stage automated pipeline. This pipeline first employs specialized pretrained models to extract diverse contextual cues (e.g., speech, music,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01111","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/2506.01111/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":"2506.01111","created_at":"2026-07-05T11:13:46.568196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01111v1","created_at":"2026-07-05T11:13:46.568196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01111","created_at":"2026-07-05T11:13:46.568196+00:00"},{"alias_kind":"pith_short_12","alias_value":"A52ZRHYOMM4V","created_at":"2026-07-05T11:13:46.568196+00:00"},{"alias_kind":"pith_short_16","alias_value":"A52ZRHYOMM4V72QU","created_at":"2026-07-05T11:13:46.568196+00:00"},{"alias_kind":"pith_short_8","alias_value":"A52ZRHYO","created_at":"2026-07-05T11:13:46.568196+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21227","citing_title":"Bagpiper-Edit: Zero-Shot Open-Ended Audio Editing via Rich-Caption","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A52ZRHYOMM4V72QU5N4FXMHWO4","json":"https://pith.science/pith/A52ZRHYOMM4V72QU5N4FXMHWO4.json","graph_json":"https://pith.science/api/pith-number/A52ZRHYOMM4V72QU5N4FXMHWO4/graph.json","events_json":"https://pith.science/api/pith-number/A52ZRHYOMM4V72QU5N4FXMHWO4/events.json","paper":"https://pith.science/paper/A52ZRHYO"},"agent_actions":{"view_html":"https://pith.science/pith/A52ZRHYOMM4V72QU5N4FXMHWO4","download_json":"https://pith.science/pith/A52ZRHYOMM4V72QU5N4FXMHWO4.json","view_paper":"https://pith.science/paper/A52ZRHYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01111&json=true","fetch_graph":"https://pith.science/api/pith-number/A52ZRHYOMM4V72QU5N4FXMHWO4/graph.json","fetch_events":"https://pith.science/api/pith-number/A52ZRHYOMM4V72QU5N4FXMHWO4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A52ZRHYOMM4V72QU5N4FXMHWO4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A52ZRHYOMM4V72QU5N4FXMHWO4/action/storage_attestation","attest_author":"https://pith.science/pith/A52ZRHYOMM4V72QU5N4FXMHWO4/action/author_attestation","sign_citation":"https://pith.science/pith/A52ZRHYOMM4V72QU5N4FXMHWO4/action/citation_signature","submit_replication":"https://pith.science/pith/A52ZRHYOMM4V72QU5N4FXMHWO4/action/replication_record"}},"created_at":"2026-07-05T11:13:46.568196+00:00","updated_at":"2026-07-05T11:13:46.568196+00:00"}