{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DKM7QFJEHBRKWTEPEJWLUIJRHP","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":"bb869a64cecd748b9af3f34cb9c3d8956a4e13d470e307ec00d4585cd8948ade","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-25T06:51:35Z","title_canon_sha256":"e01363f01c5deecb156443ee94a17e944e001362915dd373c5d71b3fac0368b8"},"schema_version":"1.0","source":{"id":"2211.13929","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.13929","created_at":"2026-07-05T07:27:41Z"},{"alias_kind":"arxiv_version","alias_value":"2211.13929v5","created_at":"2026-07-05T07:27:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13929","created_at":"2026-07-05T07:27:41Z"},{"alias_kind":"pith_short_12","alias_value":"DKM7QFJEHBRK","created_at":"2026-07-05T07:27:41Z"},{"alias_kind":"pith_short_16","alias_value":"DKM7QFJEHBRKWTEP","created_at":"2026-07-05T07:27:41Z"},{"alias_kind":"pith_short_8","alias_value":"DKM7QFJE","created_at":"2026-07-05T07:27:41Z"}],"graph_snapshots":[{"event_id":"sha256:d162705293fc5cd94ce4ac98975b044998647b136b6bb91699d7d5d192177122","target":"graph","created_at":"2026-07-05T07:27:41Z","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/2211.13929/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present XKD, a novel self-supervised framework to learn meaningful representations from unlabelled videos. XKD is trained with two pseudo objectives. First, masked data reconstruction is performed to learn modality-specific representations from audio and visual streams. Next, self-supervised cross-modal knowledge distillation is performed between the two modalities through a teacher-student setup to learn complementary information. We introduce a novel domain alignment strategy to tackle domain discrepancy between audio and visual modalities enabling effective cross-modal knowledge distilla","authors_text":"Ali Etemad, Pritam Sarkar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-25T06:51:35Z","title":"XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13929","kind":"arxiv","version":5},"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":"sha256:2b31085871fd047904dc6de14aeddf995d7deee2b633102dcb565ce0469f539e","target":"record","created_at":"2026-07-05T07:27:41Z","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":"bb869a64cecd748b9af3f34cb9c3d8956a4e13d470e307ec00d4585cd8948ade","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-25T06:51:35Z","title_canon_sha256":"e01363f01c5deecb156443ee94a17e944e001362915dd373c5d71b3fac0368b8"},"schema_version":"1.0","source":{"id":"2211.13929","kind":"arxiv","version":5}},"canonical_sha256":"1a99f815243862ab4c8f226cba21313bed32c47824e595f5272309c44edd71a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a99f815243862ab4c8f226cba21313bed32c47824e595f5272309c44edd71a8","first_computed_at":"2026-07-05T07:27:41.973452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:27:41.973452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k3bL9ak7O/agcVbC9Pak0ow6ZFMQe4Nws81GtRn8mDPP7kCiVIoySj5NCIzHVDiyzDDu+MdSdZ8JI2eEF7ZfCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:27:41.973984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.13929","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b31085871fd047904dc6de14aeddf995d7deee2b633102dcb565ce0469f539e","sha256:d162705293fc5cd94ce4ac98975b044998647b136b6bb91699d7d5d192177122"],"state_sha256":"7e357ce7fd1eb40aa85adc98c6129be7e15ab68c458111982097385db158901e"}