{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:OUCC4DXXEAG5ZXXN4GFAHORKTA","short_pith_number":"pith:OUCC4DXX","canonical_record":{"source":{"id":"2103.10699","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-19T09:16:39Z","cross_cats_sorted":[],"title_canon_sha256":"58c74d6a52d8e2f43db9e5f74e7ecc779539eb04824bb7fe0ef6f809c19f9089","abstract_canon_sha256":"6de52a60f9cceb63ef66420100ab165e623f7b81a58754f56cdd428d9ff78513"},"schema_version":"1.0"},"canonical_sha256":"75042e0ef7200ddcdeede18a03ba2a981105f628823057538bac6e518ad13b19","source":{"kind":"arxiv","id":"2103.10699","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.10699","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"arxiv_version","alias_value":"2103.10699v1","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10699","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"pith_short_12","alias_value":"OUCC4DXXEAG5","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"OUCC4DXXEAG5ZXXN","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"OUCC4DXX","created_at":"2026-07-05T03:29:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:OUCC4DXXEAG5ZXXN4GFAHORKTA","target":"record","payload":{"canonical_record":{"source":{"id":"2103.10699","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-19T09:16:39Z","cross_cats_sorted":[],"title_canon_sha256":"58c74d6a52d8e2f43db9e5f74e7ecc779539eb04824bb7fe0ef6f809c19f9089","abstract_canon_sha256":"6de52a60f9cceb63ef66420100ab165e623f7b81a58754f56cdd428d9ff78513"},"schema_version":"1.0"},"canonical_sha256":"75042e0ef7200ddcdeede18a03ba2a981105f628823057538bac6e518ad13b19","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:47.908401Z","signature_b64":"qZ3NzEfdzC8CkVSznFzMq2sJGDhJqt53MGuy5Yq5+yoOHKJXMAjuUkP6RaTMED5vkV1QGfPb585Ew+XlZk0qAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75042e0ef7200ddcdeede18a03ba2a981105f628823057538bac6e518ad13b19","last_reissued_at":"2026-07-05T03:29:47.907713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:47.907713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.10699","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":"2026-07-05T03:29:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2C0LCRsopZgB6g22LALrZDo6M7kr7eZtYJmx3Qu6xUemM2Dib3LMKNpXlAuXITVoOMNIpGGNmTO4KTN03cvDBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:13:20.898591Z"},"content_sha256":"ed24d0c291ed122b26e4d65a6f889ab7d22af53819cd65235284c9e0475a854a","schema_version":"1.0","event_id":"sha256:ed24d0c291ed122b26e4d65a6f889ab7d22af53819cd65235284c9e0475a854a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:OUCC4DXXEAG5ZXXN4GFAHORKTA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MDMMT: Multidomain Multimodal Transformer for Video Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksandr Petiushko, Maksim Dzabraev, Maksim Kalashnikov, Stepan Komkov","submitted_at":"2021-03-19T09:16:39Z","abstract_excerpt":"We present a new state-of-the-art on the text to video retrieval task on MSRVTT and LSMDC benchmarks where our model outperforms all previous solutions by a large margin. Moreover, state-of-the-art results are achieved with a single model on two datasets without finetuning. This multidomain generalisation is achieved by a proper combination of different video caption datasets. We show that training on different datasets can improve test results of each other. Additionally we check intersection between many popular datasets and found that MSRVTT has a significant overlap between the test and th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10699","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/2103.10699/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":"2026-07-05T03:29:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dDYHJcJ9ec1i0pXsTNibQac4rxWw8Tw6rUCndUmcrMLdFe8j5gNcdqPV8SnM2XV6hRO7aLxUtVZUbqZXyLZbAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:13:20.898975Z"},"content_sha256":"dfd114ff78758108c493d698e88f9cb98e7714fed2b1832e999930461d367377","schema_version":"1.0","event_id":"sha256:dfd114ff78758108c493d698e88f9cb98e7714fed2b1832e999930461d367377"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OUCC4DXXEAG5ZXXN4GFAHORKTA/bundle.json","state_url":"https://pith.science/pith/OUCC4DXXEAG5ZXXN4GFAHORKTA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OUCC4DXXEAG5ZXXN4GFAHORKTA/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":"2026-07-08T19:13:20Z","links":{"resolver":"https://pith.science/pith/OUCC4DXXEAG5ZXXN4GFAHORKTA","bundle":"https://pith.science/pith/OUCC4DXXEAG5ZXXN4GFAHORKTA/bundle.json","state":"https://pith.science/pith/OUCC4DXXEAG5ZXXN4GFAHORKTA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OUCC4DXXEAG5ZXXN4GFAHORKTA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:OUCC4DXXEAG5ZXXN4GFAHORKTA","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":"6de52a60f9cceb63ef66420100ab165e623f7b81a58754f56cdd428d9ff78513","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-19T09:16:39Z","title_canon_sha256":"58c74d6a52d8e2f43db9e5f74e7ecc779539eb04824bb7fe0ef6f809c19f9089"},"schema_version":"1.0","source":{"id":"2103.10699","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.10699","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"arxiv_version","alias_value":"2103.10699v1","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10699","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"pith_short_12","alias_value":"OUCC4DXXEAG5","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"OUCC4DXXEAG5ZXXN","created_at":"2026-07-05T03:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"OUCC4DXX","created_at":"2026-07-05T03:29:47Z"}],"graph_snapshots":[{"event_id":"sha256:dfd114ff78758108c493d698e88f9cb98e7714fed2b1832e999930461d367377","target":"graph","created_at":"2026-07-05T03:29:47Z","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/2103.10699/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a new state-of-the-art on the text to video retrieval task on MSRVTT and LSMDC benchmarks where our model outperforms all previous solutions by a large margin. Moreover, state-of-the-art results are achieved with a single model on two datasets without finetuning. This multidomain generalisation is achieved by a proper combination of different video caption datasets. We show that training on different datasets can improve test results of each other. Additionally we check intersection between many popular datasets and found that MSRVTT has a significant overlap between the test and th","authors_text":"Aleksandr Petiushko, Maksim Dzabraev, Maksim Kalashnikov, Stepan Komkov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-19T09:16:39Z","title":"MDMMT: Multidomain Multimodal Transformer for Video Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10699","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:ed24d0c291ed122b26e4d65a6f889ab7d22af53819cd65235284c9e0475a854a","target":"record","created_at":"2026-07-05T03:29:47Z","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":"6de52a60f9cceb63ef66420100ab165e623f7b81a58754f56cdd428d9ff78513","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-19T09:16:39Z","title_canon_sha256":"58c74d6a52d8e2f43db9e5f74e7ecc779539eb04824bb7fe0ef6f809c19f9089"},"schema_version":"1.0","source":{"id":"2103.10699","kind":"arxiv","version":1}},"canonical_sha256":"75042e0ef7200ddcdeede18a03ba2a981105f628823057538bac6e518ad13b19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75042e0ef7200ddcdeede18a03ba2a981105f628823057538bac6e518ad13b19","first_computed_at":"2026-07-05T03:29:47.907713Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:29:47.907713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qZ3NzEfdzC8CkVSznFzMq2sJGDhJqt53MGuy5Yq5+yoOHKJXMAjuUkP6RaTMED5vkV1QGfPb585Ew+XlZk0qAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:29:47.908401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.10699","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed24d0c291ed122b26e4d65a6f889ab7d22af53819cd65235284c9e0475a854a","sha256:dfd114ff78758108c493d698e88f9cb98e7714fed2b1832e999930461d367377"],"state_sha256":"3241bdba7499b6942c3e3027c1e6f14d836d29f6858dd644fe86be0cdb784914"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MSKMixF038gDIzt/SoZ+q+9QyjDBVwQu7htSrAqOn/pqEHNI0i8WQmK0rm5j6GEIr9IrBGDJSCjm0InxXmZ0Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T19:13:20.901061Z","bundle_sha256":"c8484d7de54dfbbc61b2a948136ed5ae83ec485d8ada57301de1afa6c7aac0ba"}}