{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:N3HPCEOSR5IBBAXRKHA7EU4QMO","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":"e4a5e2ea6724bda19888c80c4bc57c8798c3fee4a4aa2c5f7f49974b73d5df85","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T13:15:09Z","title_canon_sha256":"af4da665cde887b93b6b2439a63a602286ec4c88cbad9c8b93a64c9aeab3a2ee"},"schema_version":"1.0","source":{"id":"2203.07086","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.07086","created_at":"2026-07-05T04:04:59Z"},{"alias_kind":"arxiv_version","alias_value":"2203.07086v1","created_at":"2026-07-05T04:04:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.07086","created_at":"2026-07-05T04:04:59Z"},{"alias_kind":"pith_short_12","alias_value":"N3HPCEOSR5IB","created_at":"2026-07-05T04:04:59Z"},{"alias_kind":"pith_short_16","alias_value":"N3HPCEOSR5IBBAXR","created_at":"2026-07-05T04:04:59Z"},{"alias_kind":"pith_short_8","alias_value":"N3HPCEOS","created_at":"2026-07-05T04:04:59Z"}],"graph_snapshots":[{"event_id":"sha256:225953ed5ef6c856012c3517ef010b1f89f9ae2d485e1c17102ec44ec2f4850e","target":"graph","created_at":"2026-07-05T04:04:59Z","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/2203.07086/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work we present a new State-of-The-Art on the text-to-video retrieval task on MSR-VTT, LSMDC, MSVD, YouCook2 and TGIF obtained by a single model. Three different data sources are combined: weakly-supervised videos, crowd-labeled text-image pairs and text-video pairs. A careful analysis of available pre-trained networks helps to choose the best prior-knowledge ones. We introduce three-stage training procedure that provides high transfer knowledge efficiency and allows to use noisy datasets during training without prior knowledge degradation. Additionally, double positional encoding is u","authors_text":"Alexander Kunitsyn, Andrei Ivaniuta, Maksim Dzabraev, Maksim Kalashnikov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T13:15:09Z","title":"MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07086","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:c36742a74ef286a2b9ddd392b9207ae5fdd29c100ecdfc94f41f28d7c1ef0a69","target":"record","created_at":"2026-07-05T04:04:59Z","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":"e4a5e2ea6724bda19888c80c4bc57c8798c3fee4a4aa2c5f7f49974b73d5df85","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T13:15:09Z","title_canon_sha256":"af4da665cde887b93b6b2439a63a602286ec4c88cbad9c8b93a64c9aeab3a2ee"},"schema_version":"1.0","source":{"id":"2203.07086","kind":"arxiv","version":1}},"canonical_sha256":"6ecef111d28f501082f151c1f25390639fc0e0e14ab5ac44d5b77d0df912fb28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ecef111d28f501082f151c1f25390639fc0e0e14ab5ac44d5b77d0df912fb28","first_computed_at":"2026-07-05T04:04:59.303770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:04:59.303770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XWBqdY9+MNFE5pGaVnOvtUTtaXpi8+UBOLoyF9p/MhJEl4DjRJiYJ+4EzMTlcvBOy5Oql3AqVE5GGGEH3houAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:04:59.304266Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.07086","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c36742a74ef286a2b9ddd392b9207ae5fdd29c100ecdfc94f41f28d7c1ef0a69","sha256:225953ed5ef6c856012c3517ef010b1f89f9ae2d485e1c17102ec44ec2f4850e"],"state_sha256":"1ffc37b11952bd984b254546e547028ee74d9c7eac2aeb929b0b02f7731dc182"}