{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Y7PLKJYHRVPF7MMIEW2B5XF3BO","short_pith_number":"pith:Y7PLKJYH","canonical_record":{"source":{"id":"1804.02516","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-07T06:59:45Z","cross_cats_sorted":[],"title_canon_sha256":"4dee3a77d7437a4f67a7a7712effa7996785943ef3a5cea7292536d89c874804","abstract_canon_sha256":"c331e9d6000b62421b0c01fe22d1cab441c40eb0c4e0b3d3be0ccbd4f0e780c9"},"schema_version":"1.0"},"canonical_sha256":"c7deb527078d5e5fb18825b41edcbb0b845fa01ff534a84c799430e1d42fc63a","source":{"kind":"arxiv","id":"1804.02516","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.02516","created_at":"2026-07-05T00:33:51Z"},{"alias_kind":"arxiv_version","alias_value":"1804.02516v2","created_at":"2026-07-05T00:33:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02516","created_at":"2026-07-05T00:33:51Z"},{"alias_kind":"pith_short_12","alias_value":"Y7PLKJYHRVPF","created_at":"2026-07-05T00:33:51Z"},{"alias_kind":"pith_short_16","alias_value":"Y7PLKJYHRVPF7MMI","created_at":"2026-07-05T00:33:51Z"},{"alias_kind":"pith_short_8","alias_value":"Y7PLKJYH","created_at":"2026-07-05T00:33:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Y7PLKJYHRVPF7MMIEW2B5XF3BO","target":"record","payload":{"canonical_record":{"source":{"id":"1804.02516","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-07T06:59:45Z","cross_cats_sorted":[],"title_canon_sha256":"4dee3a77d7437a4f67a7a7712effa7996785943ef3a5cea7292536d89c874804","abstract_canon_sha256":"c331e9d6000b62421b0c01fe22d1cab441c40eb0c4e0b3d3be0ccbd4f0e780c9"},"schema_version":"1.0"},"canonical_sha256":"c7deb527078d5e5fb18825b41edcbb0b845fa01ff534a84c799430e1d42fc63a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:33:51.947642Z","signature_b64":"QYmNG7JUhGCpLjk5ye3rbcEamIAijxAA5EINtgktfeLICh4EnL/oPi6NFjWk+Y2IQy+zYKnhVbclsSo7RdrbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7deb527078d5e5fb18825b41edcbb0b845fa01ff534a84c799430e1d42fc63a","last_reissued_at":"2026-07-05T00:33:51.947241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:33:51.947241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.02516","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":"2026-07-05T00:33:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pd3aTn6mVWKhxfriERjEuQvVge35xKRoQ4uUPt3sQZdxFByOmRwxwKant9KiZPS1OGBis4VlQ9pggsyT56gRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:43:57.323528Z"},"content_sha256":"59d9e0a3710b3c6242cb11f3f449404b4e9358f3489175467431a41cfbf0d646","schema_version":"1.0","event_id":"sha256:59d9e0a3710b3c6242cb11f3f449404b4e9358f3489175467431a41cfbf0d646"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Y7PLKJYHRVPF7MMIEW2B5XF3BO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning a Text-Video Embedding from Incomplete and Heterogeneous Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antoine Miech, Ivan Laptev, Josef Sivic","submitted_at":"2018-04-07T06:59:45Z","abstract_excerpt":"Joint understanding of video and language is an active research area with many applications. Prior work in this domain typically relies on learning text-video embeddings. One difficulty with this approach, however, is the lack of large-scale annotated video-caption datasets for training. To address this issue, we aim at learning text-video embeddings from heterogeneous data sources. To this end, we propose a Mixture-of-Embedding-Experts (MEE) model with ability to handle missing input modalities during training. As a result, our framework can learn improved text-video embeddings simultaneously"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02516","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/1804.02516/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":"2026-07-05T00:33:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sWJnTC+YeomEfERiEYt9nALNKdH23mvU2D0EJnyIweVmIbpRbfVQjoSS3q4tudPJpLh0H/XYON9MR78h9A5zCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:43:57.324079Z"},"content_sha256":"ea573beef575b1314a76c7879a863339b78b45cb5ab0202ac0ff1bc2a7060fa0","schema_version":"1.0","event_id":"sha256:ea573beef575b1314a76c7879a863339b78b45cb5ab0202ac0ff1bc2a7060fa0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y7PLKJYHRVPF7MMIEW2B5XF3BO/bundle.json","state_url":"https://pith.science/pith/Y7PLKJYHRVPF7MMIEW2B5XF3BO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y7PLKJYHRVPF7MMIEW2B5XF3BO/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":"2026-08-08T06:43:57Z","links":{"resolver":"https://pith.science/pith/Y7PLKJYHRVPF7MMIEW2B5XF3BO","bundle":"https://pith.science/pith/Y7PLKJYHRVPF7MMIEW2B5XF3BO/bundle.json","state":"https://pith.science/pith/Y7PLKJYHRVPF7MMIEW2B5XF3BO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y7PLKJYHRVPF7MMIEW2B5XF3BO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Y7PLKJYHRVPF7MMIEW2B5XF3BO","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":"c331e9d6000b62421b0c01fe22d1cab441c40eb0c4e0b3d3be0ccbd4f0e780c9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-07T06:59:45Z","title_canon_sha256":"4dee3a77d7437a4f67a7a7712effa7996785943ef3a5cea7292536d89c874804"},"schema_version":"1.0","source":{"id":"1804.02516","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.02516","created_at":"2026-07-05T00:33:51Z"},{"alias_kind":"arxiv_version","alias_value":"1804.02516v2","created_at":"2026-07-05T00:33:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02516","created_at":"2026-07-05T00:33:51Z"},{"alias_kind":"pith_short_12","alias_value":"Y7PLKJYHRVPF","created_at":"2026-07-05T00:33:51Z"},{"alias_kind":"pith_short_16","alias_value":"Y7PLKJYHRVPF7MMI","created_at":"2026-07-05T00:33:51Z"},{"alias_kind":"pith_short_8","alias_value":"Y7PLKJYH","created_at":"2026-07-05T00:33:51Z"}],"graph_snapshots":[{"event_id":"sha256:ea573beef575b1314a76c7879a863339b78b45cb5ab0202ac0ff1bc2a7060fa0","target":"graph","created_at":"2026-07-05T00:33:51Z","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/1804.02516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Joint understanding of video and language is an active research area with many applications. Prior work in this domain typically relies on learning text-video embeddings. One difficulty with this approach, however, is the lack of large-scale annotated video-caption datasets for training. To address this issue, we aim at learning text-video embeddings from heterogeneous data sources. To this end, we propose a Mixture-of-Embedding-Experts (MEE) model with ability to handle missing input modalities during training. As a result, our framework can learn improved text-video embeddings simultaneously","authors_text":"Antoine Miech, Ivan Laptev, Josef Sivic","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-07T06:59:45Z","title":"Learning a Text-Video Embedding from Incomplete and Heterogeneous Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02516","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":"sha256:59d9e0a3710b3c6242cb11f3f449404b4e9358f3489175467431a41cfbf0d646","target":"record","created_at":"2026-07-05T00:33:51Z","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":"c331e9d6000b62421b0c01fe22d1cab441c40eb0c4e0b3d3be0ccbd4f0e780c9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-07T06:59:45Z","title_canon_sha256":"4dee3a77d7437a4f67a7a7712effa7996785943ef3a5cea7292536d89c874804"},"schema_version":"1.0","source":{"id":"1804.02516","kind":"arxiv","version":2}},"canonical_sha256":"c7deb527078d5e5fb18825b41edcbb0b845fa01ff534a84c799430e1d42fc63a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7deb527078d5e5fb18825b41edcbb0b845fa01ff534a84c799430e1d42fc63a","first_computed_at":"2026-07-05T00:33:51.947241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:33:51.947241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QYmNG7JUhGCpLjk5ye3rbcEamIAijxAA5EINtgktfeLICh4EnL/oPi6NFjWk+Y2IQy+zYKnhVbclsSo7RdrbDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:33:51.947642Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.02516","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59d9e0a3710b3c6242cb11f3f449404b4e9358f3489175467431a41cfbf0d646","sha256:ea573beef575b1314a76c7879a863339b78b45cb5ab0202ac0ff1bc2a7060fa0"],"state_sha256":"c06e00c7488691362a4495ddb84028eb5258039d8de63776c33eba6f0b43f106"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eDBadYtJE7ksk99YuFI+aD3/EfC7SIJDr1Dm2FkbHP70xko85os8SPVLGZB+lNi0/shYQ2eGX8pnH0MYyPddDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:43:57.329515Z","bundle_sha256":"6c147846ee4c8d71b3d857511badb0dcbbfd7298480b1121f29715528093196d"}}