{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:SMJAPFB5C6JW5A5LPJVHYELPFL","short_pith_number":"pith:SMJAPFB5","canonical_record":{"source":{"id":"2209.14275","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-09-28T17:39:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"689f1eba60cd8e232e6f3aea93e2f905c8141ad0a520e2fca273e9cb9b7148a0","abstract_canon_sha256":"c43301e71d3b85324feaf081e2e8fadbadf00f16831b88f5e6c72e280d452584"},"schema_version":"1.0"},"canonical_sha256":"931207943d17936e83ab7a6a7c116f2af75da09ed48bf431b3212c07705b75a3","source":{"kind":"arxiv","id":"2209.14275","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14275","created_at":"2026-07-05T05:01:49Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14275v1","created_at":"2026-07-05T05:01:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14275","created_at":"2026-07-05T05:01:49Z"},{"alias_kind":"pith_short_12","alias_value":"SMJAPFB5C6JW","created_at":"2026-07-05T05:01:49Z"},{"alias_kind":"pith_short_16","alias_value":"SMJAPFB5C6JW5A5L","created_at":"2026-07-05T05:01:49Z"},{"alias_kind":"pith_short_8","alias_value":"SMJAPFB5","created_at":"2026-07-05T05:01:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:SMJAPFB5C6JW5A5LPJVHYELPFL","target":"record","payload":{"canonical_record":{"source":{"id":"2209.14275","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-09-28T17:39:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"689f1eba60cd8e232e6f3aea93e2f905c8141ad0a520e2fca273e9cb9b7148a0","abstract_canon_sha256":"c43301e71d3b85324feaf081e2e8fadbadf00f16831b88f5e6c72e280d452584"},"schema_version":"1.0"},"canonical_sha256":"931207943d17936e83ab7a6a7c116f2af75da09ed48bf431b3212c07705b75a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:01:49.444723Z","signature_b64":"16WbZB7fRzOzm3lQH5Q8oZFa5TLgJRZn4k3zUBrrk59FlhA3RtxSpQrEKvEdXWi+PFzB2DB41zLt0knQT7BeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"931207943d17936e83ab7a6a7c116f2af75da09ed48bf431b3212c07705b75a3","last_reissued_at":"2026-07-05T05:01:49.444387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:01:49.444387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.14275","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":"2026-07-05T05:01:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tHu2YAM10uJvCuh0ikgt74aKl7fIh45IGl4E8MdXL5PCeJ8ROuByz8aQzEAxEmguPxC8cnLatJ/8TRttY6+CBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:07:32.125643Z"},"content_sha256":"0288aeeee67866eb180e9c9e49569601ac1ecc735517f88aaef49547d84c5cee","schema_version":"1.0","event_id":"sha256:0288aeeee67866eb180e9c9e49569601ac1ecc735517f88aaef49547d84c5cee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:SMJAPFB5C6JW5A5LPJVHYELPFL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audio Retrieval with WavText5K and CLAP Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.AS","authors_text":"Benjamin Elizalde, Huaming Wang, Soham Deshmukh","submitted_at":"2022-09-28T17:39:26Z","abstract_excerpt":"Audio-Text retrieval takes a natural language query to retrieve relevant audio files in a database. Conversely, Text-Audio retrieval takes an audio file as a query to retrieve relevant natural language descriptions. Most of the literature train retrieval systems with one audio captioning dataset, but evaluating the benefit of training with multiple datasets is underexplored. Moreover, retrieval systems have to learn the alignment between elaborated sentences describing audio content of variable length ranging from a few seconds to several minutes. In this work, we propose a new collection of w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14275","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/2209.14275/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":"2026-07-05T05:01:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eerbJSMLuk6z3o+6DP5m9pdF/QtdL5OXXCqqTRSuGGDoDhM+5QsSzVAVHigCMbYap5rCtCwAFci6v7R0+CDmDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:07:32.126255Z"},"content_sha256":"9d89455199431e16cdae7ecd9bf08ea71afb46ee2db0e70c1bd98c1fb8516987","schema_version":"1.0","event_id":"sha256:9d89455199431e16cdae7ecd9bf08ea71afb46ee2db0e70c1bd98c1fb8516987"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SMJAPFB5C6JW5A5LPJVHYELPFL/bundle.json","state_url":"https://pith.science/pith/SMJAPFB5C6JW5A5LPJVHYELPFL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SMJAPFB5C6JW5A5LPJVHYELPFL/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":"2026-08-03T22:07:32Z","links":{"resolver":"https://pith.science/pith/SMJAPFB5C6JW5A5LPJVHYELPFL","bundle":"https://pith.science/pith/SMJAPFB5C6JW5A5LPJVHYELPFL/bundle.json","state":"https://pith.science/pith/SMJAPFB5C6JW5A5LPJVHYELPFL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SMJAPFB5C6JW5A5LPJVHYELPFL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SMJAPFB5C6JW5A5LPJVHYELPFL","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":"c43301e71d3b85324feaf081e2e8fadbadf00f16831b88f5e6c72e280d452584","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-09-28T17:39:26Z","title_canon_sha256":"689f1eba60cd8e232e6f3aea93e2f905c8141ad0a520e2fca273e9cb9b7148a0"},"schema_version":"1.0","source":{"id":"2209.14275","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14275","created_at":"2026-07-05T05:01:49Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14275v1","created_at":"2026-07-05T05:01:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14275","created_at":"2026-07-05T05:01:49Z"},{"alias_kind":"pith_short_12","alias_value":"SMJAPFB5C6JW","created_at":"2026-07-05T05:01:49Z"},{"alias_kind":"pith_short_16","alias_value":"SMJAPFB5C6JW5A5L","created_at":"2026-07-05T05:01:49Z"},{"alias_kind":"pith_short_8","alias_value":"SMJAPFB5","created_at":"2026-07-05T05:01:49Z"}],"graph_snapshots":[{"event_id":"sha256:9d89455199431e16cdae7ecd9bf08ea71afb46ee2db0e70c1bd98c1fb8516987","target":"graph","created_at":"2026-07-05T05:01:49Z","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/2209.14275/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Text retrieval takes a natural language query to retrieve relevant audio files in a database. Conversely, Text-Audio retrieval takes an audio file as a query to retrieve relevant natural language descriptions. Most of the literature train retrieval systems with one audio captioning dataset, but evaluating the benefit of training with multiple datasets is underexplored. Moreover, retrieval systems have to learn the alignment between elaborated sentences describing audio content of variable length ranging from a few seconds to several minutes. In this work, we propose a new collection of w","authors_text":"Benjamin Elizalde, Huaming Wang, Soham Deshmukh","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-09-28T17:39:26Z","title":"Audio Retrieval with WavText5K and CLAP Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14275","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":"sha256:0288aeeee67866eb180e9c9e49569601ac1ecc735517f88aaef49547d84c5cee","target":"record","created_at":"2026-07-05T05:01:49Z","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":"c43301e71d3b85324feaf081e2e8fadbadf00f16831b88f5e6c72e280d452584","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-09-28T17:39:26Z","title_canon_sha256":"689f1eba60cd8e232e6f3aea93e2f905c8141ad0a520e2fca273e9cb9b7148a0"},"schema_version":"1.0","source":{"id":"2209.14275","kind":"arxiv","version":1}},"canonical_sha256":"931207943d17936e83ab7a6a7c116f2af75da09ed48bf431b3212c07705b75a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"931207943d17936e83ab7a6a7c116f2af75da09ed48bf431b3212c07705b75a3","first_computed_at":"2026-07-05T05:01:49.444387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:01:49.444387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"16WbZB7fRzOzm3lQH5Q8oZFa5TLgJRZn4k3zUBrrk59FlhA3RtxSpQrEKvEdXWi+PFzB2DB41zLt0knQT7BeAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:01:49.444723Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.14275","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0288aeeee67866eb180e9c9e49569601ac1ecc735517f88aaef49547d84c5cee","sha256:9d89455199431e16cdae7ecd9bf08ea71afb46ee2db0e70c1bd98c1fb8516987"],"state_sha256":"56f8c2838e6b80f481c01e6dc33b3e4e6881944d1af49065a8699f3579c7e7a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oOIo+gM9tgSf2M5QUUFhiLBWAUMmjBTsoqRLEdqbLeXqaYCMKvc1CynF1O9XLZGMyFd6VohaGgOavP6mimHlCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:07:32.131923Z","bundle_sha256":"13d8b95e93243eac60456d192bff9284084f36a3b5ca44f7c60f801d35d0361c"}}