{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KZ36N6RJ42UZSXBDA7H642OV2D","short_pith_number":"pith:KZ36N6RJ","canonical_record":{"source":{"id":"2012.04124","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-08T00:16:13Z","cross_cats_sorted":[],"title_canon_sha256":"d1100844045738e5111a2aa85235ba692e09352676fb6a35bcef9508d17affc0","abstract_canon_sha256":"96b264e3b42ab779035a2f0e06d8eb28a3bdd0220fbab390d73cc5fdb1c05078"},"schema_version":"1.0"},"canonical_sha256":"5677e6fa29e6a9995c2307cfee69d5d0d9f778801f42fa4bc17ee990d2a7d914","source":{"kind":"arxiv","id":"2012.04124","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.04124","created_at":"2026-07-05T03:16:30Z"},{"alias_kind":"arxiv_version","alias_value":"2012.04124v2","created_at":"2026-07-05T03:16:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04124","created_at":"2026-07-05T03:16:30Z"},{"alias_kind":"pith_short_12","alias_value":"KZ36N6RJ42UZ","created_at":"2026-07-05T03:16:30Z"},{"alias_kind":"pith_short_16","alias_value":"KZ36N6RJ42UZSXBD","created_at":"2026-07-05T03:16:30Z"},{"alias_kind":"pith_short_8","alias_value":"KZ36N6RJ","created_at":"2026-07-05T03:16:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KZ36N6RJ42UZSXBDA7H642OV2D","target":"record","payload":{"canonical_record":{"source":{"id":"2012.04124","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-08T00:16:13Z","cross_cats_sorted":[],"title_canon_sha256":"d1100844045738e5111a2aa85235ba692e09352676fb6a35bcef9508d17affc0","abstract_canon_sha256":"96b264e3b42ab779035a2f0e06d8eb28a3bdd0220fbab390d73cc5fdb1c05078"},"schema_version":"1.0"},"canonical_sha256":"5677e6fa29e6a9995c2307cfee69d5d0d9f778801f42fa4bc17ee990d2a7d914","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:16:30.578492Z","signature_b64":"lmr+hS+o6QI++KMg6SdhLD7DDLHPopqoePoKp7zRo8UbmTf0r20L9BuXdFAWR+NJzM4LmotIj6G5GJxmp1lXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5677e6fa29e6a9995c2307cfee69d5d0d9f778801f42fa4bc17ee990d2a7d914","last_reissued_at":"2026-07-05T03:16:30.577953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:16:30.577953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.04124","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:16:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qbzx1O/MwYcFkx40EoQnwymqBjAiEfUxIW3+gsl1NQppAKE39mV0CCll1Uq/sWsPSByXF93TmxNOGEmQixMWBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:47:05.239457Z"},"content_sha256":"2cd1dec553e1fd8c91594308cc460012ffd2aeeab40c9d7830a407c2447ad3e6","schema_version":"1.0","event_id":"sha256:2cd1dec553e1fd8c91594308cc460012ffd2aeeab40c9d7830a407c2447ad3e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KZ36N6RJ42UZSXBDA7H642OV2D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Parameter Efficient Multimodal Transformers for Video Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gunhee Kim, Jan Kautz, Sangho Lee, Thomas Breuel, Yale Song, Youngjae Yu","submitted_at":"2020-12-08T00:16:13Z","abstract_excerpt":"The recent success of Transformers in the language domain has motivated adapting it to a multimodal setting, where a new visual model is trained in tandem with an already pretrained language model. However, due to the excessive memory requirements from Transformers, existing work typically fixes the language model and train only the vision module, which limits its ability to learn cross-modal information in an end-to-end manner. In this work, we focus on reducing the parameters of multimodal Transformers in the context of audio-visual video representation learning. We alleviate the high memory"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04124","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/2012.04124/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":"2026-07-05T03:16:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IfGBmggUMmxPVnRxNEQwGsZOGTwu0Z6r9Ca6gSwzLqz/a7jpd7o5iUkUQ90qesmk2g4aiQjJh+L5uOx1tP3nBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:47:05.240033Z"},"content_sha256":"f2f1dfcd044ce873b1688d5c71eca6774b4946375eb7d75021fc62cf54f0be77","schema_version":"1.0","event_id":"sha256:f2f1dfcd044ce873b1688d5c71eca6774b4946375eb7d75021fc62cf54f0be77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KZ36N6RJ42UZSXBDA7H642OV2D/bundle.json","state_url":"https://pith.science/pith/KZ36N6RJ42UZSXBDA7H642OV2D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KZ36N6RJ42UZSXBDA7H642OV2D/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":"2026-08-06T02:47:05Z","links":{"resolver":"https://pith.science/pith/KZ36N6RJ42UZSXBDA7H642OV2D","bundle":"https://pith.science/pith/KZ36N6RJ42UZSXBDA7H642OV2D/bundle.json","state":"https://pith.science/pith/KZ36N6RJ42UZSXBDA7H642OV2D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KZ36N6RJ42UZSXBDA7H642OV2D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KZ36N6RJ42UZSXBDA7H642OV2D","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":"96b264e3b42ab779035a2f0e06d8eb28a3bdd0220fbab390d73cc5fdb1c05078","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-08T00:16:13Z","title_canon_sha256":"d1100844045738e5111a2aa85235ba692e09352676fb6a35bcef9508d17affc0"},"schema_version":"1.0","source":{"id":"2012.04124","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.04124","created_at":"2026-07-05T03:16:30Z"},{"alias_kind":"arxiv_version","alias_value":"2012.04124v2","created_at":"2026-07-05T03:16:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04124","created_at":"2026-07-05T03:16:30Z"},{"alias_kind":"pith_short_12","alias_value":"KZ36N6RJ42UZ","created_at":"2026-07-05T03:16:30Z"},{"alias_kind":"pith_short_16","alias_value":"KZ36N6RJ42UZSXBD","created_at":"2026-07-05T03:16:30Z"},{"alias_kind":"pith_short_8","alias_value":"KZ36N6RJ","created_at":"2026-07-05T03:16:30Z"}],"graph_snapshots":[{"event_id":"sha256:f2f1dfcd044ce873b1688d5c71eca6774b4946375eb7d75021fc62cf54f0be77","target":"graph","created_at":"2026-07-05T03:16:30Z","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/2012.04124/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent success of Transformers in the language domain has motivated adapting it to a multimodal setting, where a new visual model is trained in tandem with an already pretrained language model. However, due to the excessive memory requirements from Transformers, existing work typically fixes the language model and train only the vision module, which limits its ability to learn cross-modal information in an end-to-end manner. In this work, we focus on reducing the parameters of multimodal Transformers in the context of audio-visual video representation learning. We alleviate the high memory","authors_text":"Gunhee Kim, Jan Kautz, Sangho Lee, Thomas Breuel, Yale Song, Youngjae Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-08T00:16:13Z","title":"Parameter Efficient Multimodal Transformers for Video Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04124","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":"sha256:2cd1dec553e1fd8c91594308cc460012ffd2aeeab40c9d7830a407c2447ad3e6","target":"record","created_at":"2026-07-05T03:16:30Z","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":"96b264e3b42ab779035a2f0e06d8eb28a3bdd0220fbab390d73cc5fdb1c05078","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-08T00:16:13Z","title_canon_sha256":"d1100844045738e5111a2aa85235ba692e09352676fb6a35bcef9508d17affc0"},"schema_version":"1.0","source":{"id":"2012.04124","kind":"arxiv","version":2}},"canonical_sha256":"5677e6fa29e6a9995c2307cfee69d5d0d9f778801f42fa4bc17ee990d2a7d914","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5677e6fa29e6a9995c2307cfee69d5d0d9f778801f42fa4bc17ee990d2a7d914","first_computed_at":"2026-07-05T03:16:30.577953Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:16:30.577953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lmr+hS+o6QI++KMg6SdhLD7DDLHPopqoePoKp7zRo8UbmTf0r20L9BuXdFAWR+NJzM4LmotIj6G5GJxmp1lXCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:16:30.578492Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.04124","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2cd1dec553e1fd8c91594308cc460012ffd2aeeab40c9d7830a407c2447ad3e6","sha256:f2f1dfcd044ce873b1688d5c71eca6774b4946375eb7d75021fc62cf54f0be77"],"state_sha256":"53f9384cb2df67ab73bcb549d1563e8cbb1f5cf73af27e69509e47a541b5cd04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mOKAByxwH8+1qfMh6QFEgyWcnweFlA9pw0dpiK+c3ZJ7SJjtNGAyw07KdvGzsUEBCIcB0RW6IFIR24uSjY08Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:47:05.243503Z","bundle_sha256":"200ed6b73d74a16a44927569ca33f3d76592f9fed7989a76d2bf50bbeb22dec4"}}