{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:A52ZRHYOMM4V72QU5N4FXMHWO4","short_pith_number":"pith:A52ZRHYO","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"},"canonical_sha256":"0775989f0e63395fea14eb785bb0f6772580545bbd884259407c990e071602f6","source":{"kind":"arxiv","id":"2506.01111","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01111","created_at":"2026-07-05T11:13:46Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01111v1","created_at":"2026-07-05T11:13:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01111","created_at":"2026-07-05T11:13:46Z"},{"alias_kind":"pith_short_12","alias_value":"A52ZRHYOMM4V","created_at":"2026-07-05T11:13:46Z"},{"alias_kind":"pith_short_16","alias_value":"A52ZRHYOMM4V72QU","created_at":"2026-07-05T11:13:46Z"},{"alias_kind":"pith_short_8","alias_value":"A52ZRHYO","created_at":"2026-07-05T11:13:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:A52ZRHYOMM4V72QU5N4FXMHWO4","target":"record","payload":{"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"},"canonical_sha256":"0775989f0e63395fea14eb785bb0f6772580545bbd884259407c990e071602f6","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"},"source_kind":"arxiv","source_id":"2506.01111","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":"2026-07-05T11:13:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XPLJLKTo3adXr9yOl09meOPMopzjvPHy9yPe8JP9jQOnyFOaHsVTtsEmxZr+03/dznoFKAsJ06pKZVtvOGGfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T00:01:56.037590Z"},"content_sha256":"54dc2ccddb22841f84cd18d8585a386dd85ac2e08a453f8411d19abadbf14bb3","schema_version":"1.0","event_id":"sha256:54dc2ccddb22841f84cd18d8585a386dd85ac2e08a453f8411d19abadbf14bb3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:A52ZRHYOMM4V72QU5N4FXMHWO4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zuUfPTBvhqdM+azIShsGWqK9Sk7HXdwpB57Fir26+1tndJ8ZNilg77XgI4DLlXALwyDGddKJthMTUlcJEyUsBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T00:01:56.038534Z"},"content_sha256":"c75f9101e9db0e4a15155ee28e73fe41105222f3c31a348c8ab6cf0a064b1d34","schema_version":"1.0","event_id":"sha256:c75f9101e9db0e4a15155ee28e73fe41105222f3c31a348c8ab6cf0a064b1d34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A52ZRHYOMM4V72QU5N4FXMHWO4/bundle.json","state_url":"https://pith.science/pith/A52ZRHYOMM4V72QU5N4FXMHWO4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A52ZRHYOMM4V72QU5N4FXMHWO4/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":"2026-08-15T00:01:56Z","links":{"resolver":"https://pith.science/pith/A52ZRHYOMM4V72QU5N4FXMHWO4","bundle":"https://pith.science/pith/A52ZRHYOMM4V72QU5N4FXMHWO4/bundle.json","state":"https://pith.science/pith/A52ZRHYOMM4V72QU5N4FXMHWO4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A52ZRHYOMM4V72QU5N4FXMHWO4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A52ZRHYOMM4V72QU5N4FXMHWO4","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":"7d765abd7e46f5292e939a41dec91068097f663d74a8d30f7870d3638d8d1187","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-01T18:29:17Z","title_canon_sha256":"dc06be108eeaf1a4062f66bd2325551b3b1fa123ede587e84590b40485326eff"},"schema_version":"1.0","source":{"id":"2506.01111","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01111","created_at":"2026-07-05T11:13:46Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01111v1","created_at":"2026-07-05T11:13:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01111","created_at":"2026-07-05T11:13:46Z"},{"alias_kind":"pith_short_12","alias_value":"A52ZRHYOMM4V","created_at":"2026-07-05T11:13:46Z"},{"alias_kind":"pith_short_16","alias_value":"A52ZRHYOMM4V72QU","created_at":"2026-07-05T11:13:46Z"},{"alias_kind":"pith_short_8","alias_value":"A52ZRHYO","created_at":"2026-07-05T11:13:46Z"}],"graph_snapshots":[{"event_id":"sha256:c75f9101e9db0e4a15155ee28e73fe41105222f3c31a348c8ab6cf0a064b1d34","target":"graph","created_at":"2026-07-05T11:13:46Z","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/2506.01111/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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,","authors_text":"Benyou Wang, Liyan Zhao, Owen Lee, Qilin Sun, Shunian Chen, Xinyuan Xie, Zhan Su, Zheshu Chen","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-01T18:29:17Z","title":"FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01111","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":"sha256:54dc2ccddb22841f84cd18d8585a386dd85ac2e08a453f8411d19abadbf14bb3","target":"record","created_at":"2026-07-05T11:13:46Z","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":"7d765abd7e46f5292e939a41dec91068097f663d74a8d30f7870d3638d8d1187","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-01T18:29:17Z","title_canon_sha256":"dc06be108eeaf1a4062f66bd2325551b3b1fa123ede587e84590b40485326eff"},"schema_version":"1.0","source":{"id":"2506.01111","kind":"arxiv","version":1}},"canonical_sha256":"0775989f0e63395fea14eb785bb0f6772580545bbd884259407c990e071602f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0775989f0e63395fea14eb785bb0f6772580545bbd884259407c990e071602f6","first_computed_at":"2026-07-05T11:13:46.568121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:46.568121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NpFt5d8A3MnKwbrDGep6ZnU1mVvWwTo0mk+PTmPHoUx0em+iFMTzZdgRhlvp2jtL5SJWktcVPmpamjrfoNCBBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:46.568672Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01111","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54dc2ccddb22841f84cd18d8585a386dd85ac2e08a453f8411d19abadbf14bb3","sha256:c75f9101e9db0e4a15155ee28e73fe41105222f3c31a348c8ab6cf0a064b1d34"],"state_sha256":"e5e05f3321f674177e3f061e6ab70ed3b7279f06d7b9fc3d052079db6750bba4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ye9YB+By/tfBFIIkCuA+TYLT13Q6A3kL/hpiPN55LEglmz5gU+MTf+9wpuRb72ABU4hkdAO8I22Zjo4dQrwtCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T00:01:56.045859Z","bundle_sha256":"5060155f0af0bcabd40b10e88c7ad196ae90a34ab66dbad8a289b2022dd2cbfd"}}