{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LEMQKMJDLTA6MJDQIJT6CI6M77","short_pith_number":"pith:LEMQKMJD","schema_version":"1.0","canonical_sha256":"59190531235cc1e624704267e123ccffe3039bff15f3063dd92978548dcb3d1f","source":{"kind":"arxiv","id":"2112.08995","version":2},"attestation_state":"computed","paper":{"title":"Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jack Hessel, Rowan Zellers, Ximing Lu, Yanpeng Zhao, Yejin Choi, Youngjae Yu","submitted_at":"2021-12-16T16:22:10Z","abstract_excerpt":"Machines that can represent and describe environmental soundscapes have practical potential, e.g., for audio tagging and captioning systems. Prevailing learning paradigms have been relying on parallel audio-text data, which is, however, scarcely available on the web. We propose VIP-ANT that induces \\textbf{A}udio-\\textbf{T}ext alignment without using any parallel audio-text data. Our key idea is to share the image modality between bi-modal image-text representations and bi-modal image-audio representations; the image modality functions as a pivot and connects audio and text in a tri-modal embe"},"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":"2112.08995","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-12-16T16:22:10Z","cross_cats_sorted":["cs.CL","cs.CV","eess.AS"],"title_canon_sha256":"ef57156d8e68381b88736c7ddfa1cc41e3170b5a378417feadf6d2763472ce92","abstract_canon_sha256":"81a5fd188bb096ed31329803dd29872073fb046376eb58539a3505d6fd4d85d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:50.571237Z","signature_b64":"Zadx1ZRQY2d5rTyh3BlLCP1nPb+F5fbxdiLJWGy8Q0CMfbZ/Y2ixFJ22fQLasARIqpu3oddii3h1tv6gaycsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59190531235cc1e624704267e123ccffe3039bff15f3063dd92978548dcb3d1f","last_reissued_at":"2026-07-05T04:19:50.570813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:50.570813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jack Hessel, Rowan Zellers, Ximing Lu, Yanpeng Zhao, Yejin Choi, Youngjae Yu","submitted_at":"2021-12-16T16:22:10Z","abstract_excerpt":"Machines that can represent and describe environmental soundscapes have practical potential, e.g., for audio tagging and captioning systems. Prevailing learning paradigms have been relying on parallel audio-text data, which is, however, scarcely available on the web. We propose VIP-ANT that induces \\textbf{A}udio-\\textbf{T}ext alignment without using any parallel audio-text data. Our key idea is to share the image modality between bi-modal image-text representations and bi-modal image-audio representations; the image modality functions as a pivot and connects audio and text in a tri-modal embe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08995","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/2112.08995/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":"2112.08995","created_at":"2026-07-05T04:19:50.570863+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08995v2","created_at":"2026-07-05T04:19:50.570863+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08995","created_at":"2026-07-05T04:19:50.570863+00:00"},{"alias_kind":"pith_short_12","alias_value":"LEMQKMJDLTA6","created_at":"2026-07-05T04:19:50.570863+00:00"},{"alias_kind":"pith_short_16","alias_value":"LEMQKMJDLTA6MJDQ","created_at":"2026-07-05T04:19:50.570863+00:00"},{"alias_kind":"pith_short_8","alias_value":"LEMQKMJD","created_at":"2026-07-05T04:19:50.570863+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/LEMQKMJDLTA6MJDQIJT6CI6M77","json":"https://pith.science/pith/LEMQKMJDLTA6MJDQIJT6CI6M77.json","graph_json":"https://pith.science/api/pith-number/LEMQKMJDLTA6MJDQIJT6CI6M77/graph.json","events_json":"https://pith.science/api/pith-number/LEMQKMJDLTA6MJDQIJT6CI6M77/events.json","paper":"https://pith.science/paper/LEMQKMJD"},"agent_actions":{"view_html":"https://pith.science/pith/LEMQKMJDLTA6MJDQIJT6CI6M77","download_json":"https://pith.science/pith/LEMQKMJDLTA6MJDQIJT6CI6M77.json","view_paper":"https://pith.science/paper/LEMQKMJD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08995&json=true","fetch_graph":"https://pith.science/api/pith-number/LEMQKMJDLTA6MJDQIJT6CI6M77/graph.json","fetch_events":"https://pith.science/api/pith-number/LEMQKMJDLTA6MJDQIJT6CI6M77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LEMQKMJDLTA6MJDQIJT6CI6M77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LEMQKMJDLTA6MJDQIJT6CI6M77/action/storage_attestation","attest_author":"https://pith.science/pith/LEMQKMJDLTA6MJDQIJT6CI6M77/action/author_attestation","sign_citation":"https://pith.science/pith/LEMQKMJDLTA6MJDQIJT6CI6M77/action/citation_signature","submit_replication":"https://pith.science/pith/LEMQKMJDLTA6MJDQIJT6CI6M77/action/replication_record"}},"created_at":"2026-07-05T04:19:50.570863+00:00","updated_at":"2026-07-05T04:19:50.570863+00:00"}