{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2RJ7AVND3B32DRLHY3DIXFQISK","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":"2a8e338f593f260f4874c6dc2dc0d0acd594db49d44ac1b43378392378cf8b74","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-10T00:23:33Z","title_canon_sha256":"fa5623c507938825c365948aff39ede19a1229c9816e5cd975852b99d6055d67"},"schema_version":"1.0","source":{"id":"2106.05438","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.05438","created_at":"2026-07-05T02:48:01Z"},{"alias_kind":"arxiv_version","alias_value":"2106.05438v1","created_at":"2026-07-05T02:48:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05438","created_at":"2026-07-05T02:48:01Z"},{"alias_kind":"pith_short_12","alias_value":"2RJ7AVND3B32","created_at":"2026-07-05T02:48:01Z"},{"alias_kind":"pith_short_16","alias_value":"2RJ7AVND3B32DRLH","created_at":"2026-07-05T02:48:01Z"},{"alias_kind":"pith_short_8","alias_value":"2RJ7AVND","created_at":"2026-07-05T02:48:01Z"}],"graph_snapshots":[{"event_id":"sha256:8e2768f852b60ab1be9eeaa59cbd936b9b524bb2840b2cc20fc67abe624090ce","target":"graph","created_at":"2026-07-05T02:48:01Z","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/2106.05438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in representation learning have demonstrated an ability to represent information from different modalities such as video, text, and audio in a single high-level embedding vector. In this work we present a self-supervised learning framework that is able to learn a representation that captures finer levels of granularity across different modalities such as concepts or events represented by visual objects or spoken words. Our framework relies on a discretized embedding space created via vector quantization that is shared across different modalities. Beyond the shared embedding spa","authors_text":"Alexander H. Liu, Andrew Rouditchenko, Aude Oliva, Cheng-I Jeff Lai, James Glass, SouYoung Jin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-10T00:23:33Z","title":"Cross-Modal Discrete Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05438","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":"sha256:0b83c050a1663c9a85e95f04322e1e8ab29ff27ee7914257f00541d966262cb8","target":"record","created_at":"2026-07-05T02:48:01Z","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":"2a8e338f593f260f4874c6dc2dc0d0acd594db49d44ac1b43378392378cf8b74","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-10T00:23:33Z","title_canon_sha256":"fa5623c507938825c365948aff39ede19a1229c9816e5cd975852b99d6055d67"},"schema_version":"1.0","source":{"id":"2106.05438","kind":"arxiv","version":1}},"canonical_sha256":"d453f055a3d877a1c567c6c68b960892b83ed0d7a3caa1f91fa82f9fff38b6b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d453f055a3d877a1c567c6c68b960892b83ed0d7a3caa1f91fa82f9fff38b6b7","first_computed_at":"2026-07-05T02:48:01.801219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:01.801219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tnc+hIzKVuluStT//8xoTekH89DEJ3UPgwjpcUdtZBpVNToT51icNumq8+dCu9qV5G6fBbLNZGF9kZb3iqwPAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:01.801649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.05438","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b83c050a1663c9a85e95f04322e1e8ab29ff27ee7914257f00541d966262cb8","sha256:8e2768f852b60ab1be9eeaa59cbd936b9b524bb2840b2cc20fc67abe624090ce"],"state_sha256":"4d910274600bb6e3ed7f3c99ea48f8f54302871fb904d07bd9b427e0aeac0b8a"}