{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LEMQKMJDLTA6MJDQIJT6CI6M77","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":"81a5fd188bb096ed31329803dd29872073fb046376eb58539a3505d6fd4d85d6","cross_cats_sorted":["cs.CL","cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-12-16T16:22:10Z","title_canon_sha256":"ef57156d8e68381b88736c7ddfa1cc41e3170b5a378417feadf6d2763472ce92"},"schema_version":"1.0","source":{"id":"2112.08995","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08995","created_at":"2026-07-05T04:19:50Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08995v2","created_at":"2026-07-05T04:19:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08995","created_at":"2026-07-05T04:19:50Z"},{"alias_kind":"pith_short_12","alias_value":"LEMQKMJDLTA6","created_at":"2026-07-05T04:19:50Z"},{"alias_kind":"pith_short_16","alias_value":"LEMQKMJDLTA6MJDQ","created_at":"2026-07-05T04:19:50Z"},{"alias_kind":"pith_short_8","alias_value":"LEMQKMJD","created_at":"2026-07-05T04:19:50Z"}],"graph_snapshots":[{"event_id":"sha256:b80dc178082baa4d071cc259bc609e201d7901b61bf52c76e07531b0cffc3032","target":"graph","created_at":"2026-07-05T04:19:50Z","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/2112.08995/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jack Hessel, Rowan Zellers, Ximing Lu, Yanpeng Zhao, Yejin Choi, Youngjae Yu","cross_cats":["cs.CL","cs.CV","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-12-16T16:22:10Z","title":"Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08995","kind":"arxiv","version":2},"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":"sha256:312e3da614d463391eb5758bba83e0e4e48050bdbe5c347954a902c270235257","target":"record","created_at":"2026-07-05T04:19:50Z","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":"81a5fd188bb096ed31329803dd29872073fb046376eb58539a3505d6fd4d85d6","cross_cats_sorted":["cs.CL","cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-12-16T16:22:10Z","title_canon_sha256":"ef57156d8e68381b88736c7ddfa1cc41e3170b5a378417feadf6d2763472ce92"},"schema_version":"1.0","source":{"id":"2112.08995","kind":"arxiv","version":2}},"canonical_sha256":"59190531235cc1e624704267e123ccffe3039bff15f3063dd92978548dcb3d1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59190531235cc1e624704267e123ccffe3039bff15f3063dd92978548dcb3d1f","first_computed_at":"2026-07-05T04:19:50.570813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:19:50.570813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zadx1ZRQY2d5rTyh3BlLCP1nPb+F5fbxdiLJWGy8Q0CMfbZ/Y2ixFJ22fQLasARIqpu3oddii3h1tv6gaycsCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:19:50.571237Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.08995","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:312e3da614d463391eb5758bba83e0e4e48050bdbe5c347954a902c270235257","sha256:b80dc178082baa4d071cc259bc609e201d7901b61bf52c76e07531b0cffc3032"],"state_sha256":"85553568a2eb1f2a8884d78931a554745e27bb4fc6bf88206faf592b2b13aa8c"}