{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5JC7MTSOXOOJTH6PQYS2HU7MH3","short_pith_number":"pith:5JC7MTSO","canonical_record":{"source":{"id":"2412.01356","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-02T10:34:05Z","cross_cats_sorted":[],"title_canon_sha256":"ad57becdd649bb228c6582fd46c24dec5fcd3e0ea8e5952cab9d9fd2ca5059b7","abstract_canon_sha256":"665a269466cf5776fc93b58b978ffffa48e3f9e8cdc025c82ee472ad90844437"},"schema_version":"1.0"},"canonical_sha256":"ea45f64e4ebb9c999fcf8625a3d3ec3edd6df84e179ffc18254591267d183ba9","source":{"kind":"arxiv","id":"2412.01356","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01356","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01356v1","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01356","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"pith_short_12","alias_value":"5JC7MTSOXOOJ","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"pith_short_16","alias_value":"5JC7MTSOXOOJTH6P","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"pith_short_8","alias_value":"5JC7MTSO","created_at":"2026-07-05T09:42:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5JC7MTSOXOOJTH6PQYS2HU7MH3","target":"record","payload":{"canonical_record":{"source":{"id":"2412.01356","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-02T10:34:05Z","cross_cats_sorted":[],"title_canon_sha256":"ad57becdd649bb228c6582fd46c24dec5fcd3e0ea8e5952cab9d9fd2ca5059b7","abstract_canon_sha256":"665a269466cf5776fc93b58b978ffffa48e3f9e8cdc025c82ee472ad90844437"},"schema_version":"1.0"},"canonical_sha256":"ea45f64e4ebb9c999fcf8625a3d3ec3edd6df84e179ffc18254591267d183ba9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:58.655089Z","signature_b64":"K/9j4UwsuGnR+yQeejQAg9NBvO2m+OMxxoig4esA7hpo1OO4yveQOFHgYyJ8jf9qaPGBb5VU0NK+xad6r7B7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea45f64e4ebb9c999fcf8625a3d3ec3edd6df84e179ffc18254591267d183ba9","last_reissued_at":"2026-07-05T09:42:58.654458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:58.654458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.01356","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":"2026-07-05T09:42:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YiuNzbtwUNWdopPEuqB1FFuDc8t5oSUXRe/thumIbSysJm/tAXh+IQiYL3LY8x84kqgrNNpZ8nRyfo1U2w4ADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T07:06:51.124854Z"},"content_sha256":"cc654cbd3d6e927dfc75765943551b7c8fc1c9f9eef02abdb60ed21b23e258f9","schema_version":"1.0","event_id":"sha256:cc654cbd3d6e927dfc75765943551b7c8fc1c9f9eef02abdb60ed21b23e258f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5JC7MTSOXOOJTH6PQYS2HU7MH3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text-based Audio Retrieval by Learning from Similarities between Audio Captions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Huang Xie, Khazar Khorrami, Okko R\\\"as\\\"anen, Tuomas Virtanen","submitted_at":"2024-12-02T10:34:05Z","abstract_excerpt":"This paper proposes to use similarities of audio captions for estimating audio-caption relevances to be used for training text-based audio retrieval systems. Current audio-caption datasets (e.g., Clotho) contain audio samples paired with annotated captions, but lack relevance information about audio samples and captions beyond the annotated ones. Besides, mainstream approaches (e.g., CLAP) usually treat the annotated pairs as positives and consider all other audio-caption combinations as negatives, assuming a binary relevance between audio samples and captions. To infer the relevance between a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01356","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/2412.01356/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":"2026-07-05T09:42:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XWOX7ncujYnNKlzT6NbvxjZ2Cs7gVcPWy+KPDt1qeff0OHLwqIQHHfGwh71yfH+sCXwfGkGLzupl7qR7Uc16DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T07:06:51.125248Z"},"content_sha256":"14a71503d7553a12077ce3f916bde49c204dab12bf77e3588107f21e2167807a","schema_version":"1.0","event_id":"sha256:14a71503d7553a12077ce3f916bde49c204dab12bf77e3588107f21e2167807a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5JC7MTSOXOOJTH6PQYS2HU7MH3/bundle.json","state_url":"https://pith.science/pith/5JC7MTSOXOOJTH6PQYS2HU7MH3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5JC7MTSOXOOJTH6PQYS2HU7MH3/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":"2026-08-18T07:06:51Z","links":{"resolver":"https://pith.science/pith/5JC7MTSOXOOJTH6PQYS2HU7MH3","bundle":"https://pith.science/pith/5JC7MTSOXOOJTH6PQYS2HU7MH3/bundle.json","state":"https://pith.science/pith/5JC7MTSOXOOJTH6PQYS2HU7MH3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5JC7MTSOXOOJTH6PQYS2HU7MH3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5JC7MTSOXOOJTH6PQYS2HU7MH3","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":"665a269466cf5776fc93b58b978ffffa48e3f9e8cdc025c82ee472ad90844437","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-02T10:34:05Z","title_canon_sha256":"ad57becdd649bb228c6582fd46c24dec5fcd3e0ea8e5952cab9d9fd2ca5059b7"},"schema_version":"1.0","source":{"id":"2412.01356","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01356","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01356v1","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01356","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"pith_short_12","alias_value":"5JC7MTSOXOOJ","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"pith_short_16","alias_value":"5JC7MTSOXOOJTH6P","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"pith_short_8","alias_value":"5JC7MTSO","created_at":"2026-07-05T09:42:58Z"}],"graph_snapshots":[{"event_id":"sha256:14a71503d7553a12077ce3f916bde49c204dab12bf77e3588107f21e2167807a","target":"graph","created_at":"2026-07-05T09:42:58Z","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/2412.01356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes to use similarities of audio captions for estimating audio-caption relevances to be used for training text-based audio retrieval systems. Current audio-caption datasets (e.g., Clotho) contain audio samples paired with annotated captions, but lack relevance information about audio samples and captions beyond the annotated ones. Besides, mainstream approaches (e.g., CLAP) usually treat the annotated pairs as positives and consider all other audio-caption combinations as negatives, assuming a binary relevance between audio samples and captions. To infer the relevance between a","authors_text":"Huang Xie, Khazar Khorrami, Okko R\\\"as\\\"anen, Tuomas Virtanen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-02T10:34:05Z","title":"Text-based Audio Retrieval by Learning from Similarities between Audio Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01356","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:cc654cbd3d6e927dfc75765943551b7c8fc1c9f9eef02abdb60ed21b23e258f9","target":"record","created_at":"2026-07-05T09:42:58Z","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":"665a269466cf5776fc93b58b978ffffa48e3f9e8cdc025c82ee472ad90844437","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-02T10:34:05Z","title_canon_sha256":"ad57becdd649bb228c6582fd46c24dec5fcd3e0ea8e5952cab9d9fd2ca5059b7"},"schema_version":"1.0","source":{"id":"2412.01356","kind":"arxiv","version":1}},"canonical_sha256":"ea45f64e4ebb9c999fcf8625a3d3ec3edd6df84e179ffc18254591267d183ba9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea45f64e4ebb9c999fcf8625a3d3ec3edd6df84e179ffc18254591267d183ba9","first_computed_at":"2026-07-05T09:42:58.654458Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:58.654458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K/9j4UwsuGnR+yQeejQAg9NBvO2m+OMxxoig4esA7hpo1OO4yveQOFHgYyJ8jf9qaPGBb5VU0NK+xad6r7B7BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:58.655089Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01356","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc654cbd3d6e927dfc75765943551b7c8fc1c9f9eef02abdb60ed21b23e258f9","sha256:14a71503d7553a12077ce3f916bde49c204dab12bf77e3588107f21e2167807a"],"state_sha256":"0c0d8c9e76e1e035aa141b6f8fc55d41be60230a4afcb1f17cf5f0e404cfd417"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tsqf9caizJpWJPZLWPuPSUPKzmc+n+NKzPBJ9GfA6DON31783X2HhUb+5LyWwZuQH7j6niQOlzdA/k9eW2xxAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T07:06:51.127922Z","bundle_sha256":"532fa43f73325bd56cc00b83e34a0c331710b28a3848ff41e8943cc0b25f5ecd"}}