{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:N3HPCEOSR5IBBAXRKHA7EU4QMO","short_pith_number":"pith:N3HPCEOS","canonical_record":{"source":{"id":"2203.07086","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T13:15:09Z","cross_cats_sorted":[],"title_canon_sha256":"af4da665cde887b93b6b2439a63a602286ec4c88cbad9c8b93a64c9aeab3a2ee","abstract_canon_sha256":"e4a5e2ea6724bda19888c80c4bc57c8798c3fee4a4aa2c5f7f49974b73d5df85"},"schema_version":"1.0"},"canonical_sha256":"6ecef111d28f501082f151c1f25390639fc0e0e14ab5ac44d5b77d0df912fb28","source":{"kind":"arxiv","id":"2203.07086","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:N3HPCEOSR5IBBAXRKHA7EU4QMO","target":"record","payload":{"canonical_record":{"source":{"id":"2203.07086","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-14T13:15:09Z","cross_cats_sorted":[],"title_canon_sha256":"af4da665cde887b93b6b2439a63a602286ec4c88cbad9c8b93a64c9aeab3a2ee","abstract_canon_sha256":"e4a5e2ea6724bda19888c80c4bc57c8798c3fee4a4aa2c5f7f49974b73d5df85"},"schema_version":"1.0"},"canonical_sha256":"6ecef111d28f501082f151c1f25390639fc0e0e14ab5ac44d5b77d0df912fb28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:59.304266Z","signature_b64":"XWBqdY9+MNFE5pGaVnOvtUTtaXpi8+UBOLoyF9p/MhJEl4DjRJiYJ+4EzMTlcvBOy5Oql3AqVE5GGGEH3houAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ecef111d28f501082f151c1f25390639fc0e0e14ab5ac44d5b77d0df912fb28","last_reissued_at":"2026-07-05T04:04:59.303770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:59.303770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.07086","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:04:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ghdVSrLjqDKQDF/FF7Hz4Xe5t86UglTvJULzMUTlvHkFiuUQ6nMVqfUGrJdrt/dds0hA3osGYKYb5kTRhlTFDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T12:20:23.322421Z"},"content_sha256":"c36742a74ef286a2b9ddd392b9207ae5fdd29c100ecdfc94f41f28d7c1ef0a69","schema_version":"1.0","event_id":"sha256:c36742a74ef286a2b9ddd392b9207ae5fdd29c100ecdfc94f41f28d7c1ef0a69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:N3HPCEOSR5IBBAXRKHA7EU4QMO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Kunitsyn, Andrei Ivaniuta, Maksim Dzabraev, Maksim Kalashnikov","submitted_at":"2022-03-14T13:15:09Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07086","kind":"arxiv","version":1},"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/2203.07086/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":"2026-07-05T04:04:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mx9+MOYOK2NMw/5TEqXrrN2RHE1L2QJ0nV7YaSvz3bRX3v2NuZwwUb5LTvG1QAEWJedbqOkXjRR/1/GvR7UhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T12:20:23.323064Z"},"content_sha256":"225953ed5ef6c856012c3517ef010b1f89f9ae2d485e1c17102ec44ec2f4850e","schema_version":"1.0","event_id":"sha256:225953ed5ef6c856012c3517ef010b1f89f9ae2d485e1c17102ec44ec2f4850e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N3HPCEOSR5IBBAXRKHA7EU4QMO/bundle.json","state_url":"https://pith.science/pith/N3HPCEOSR5IBBAXRKHA7EU4QMO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N3HPCEOSR5IBBAXRKHA7EU4QMO/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":"2026-07-08T12:20:23Z","links":{"resolver":"https://pith.science/pith/N3HPCEOSR5IBBAXRKHA7EU4QMO","bundle":"https://pith.science/pith/N3HPCEOSR5IBBAXRKHA7EU4QMO/bundle.json","state":"https://pith.science/pith/N3HPCEOSR5IBBAXRKHA7EU4QMO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N3HPCEOSR5IBBAXRKHA7EU4QMO/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Yd3yWzSVelqazz13PbN4dQ/gLnCfIYrsbA8Yrue6Z0zdhY2JQzaiFPfpuxJK4Mx2K30ikzsvYztKXJkKo9FBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T12:20:23.326074Z","bundle_sha256":"0091bb747acf3f0d7629643c7aa5598c563ffd966afae040e72a6a140f5984fb"}}