{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:YQWVR77TXRSFDVDI7BEZLW6CPT","short_pith_number":"pith:YQWVR77T","canonical_record":{"source":{"id":"1609.08124","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-26T19:14:12Z","cross_cats_sorted":[],"title_canon_sha256":"35157ed78949456049774293f59578c7e3de3b7eb1c6c043a7f1c895e9a75801","abstract_canon_sha256":"01de924187bf024b59bf774c1672994a6543c0a6717e04686826c7dade9b6af7"},"schema_version":"1.0"},"canonical_sha256":"c42d58fff3bc6451d468f84995dbc27cf0839e4583e21f1e96d135f8f774312f","source":{"kind":"arxiv","id":"1609.08124","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.08124","created_at":"2026-05-18T01:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"1609.08124v1","created_at":"2026-05-18T01:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.08124","created_at":"2026-05-18T01:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"YQWVR77TXRSF","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"YQWVR77TXRSFDVDI","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"YQWVR77T","created_at":"2026-05-18T12:30:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:YQWVR77TXRSFDVDI7BEZLW6CPT","target":"record","payload":{"canonical_record":{"source":{"id":"1609.08124","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-26T19:14:12Z","cross_cats_sorted":[],"title_canon_sha256":"35157ed78949456049774293f59578c7e3de3b7eb1c6c043a7f1c895e9a75801","abstract_canon_sha256":"01de924187bf024b59bf774c1672994a6543c0a6717e04686826c7dade9b6af7"},"schema_version":"1.0"},"canonical_sha256":"c42d58fff3bc6451d468f84995dbc27cf0839e4583e21f1e96d135f8f774312f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:54.370751Z","signature_b64":"R+89doHTjWWBtFAD/48QXZTLN1pANQvy7Uid/P1CVjckh5isUNNV7I7h3JOTMonS41m287snb82q5vqUrhSTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c42d58fff3bc6451d468f84995dbc27cf0839e4583e21f1e96d135f8f774312f","last_reissued_at":"2026-05-18T01:03:54.370117Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:54.370117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.08124","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":"2026-05-18T01:03:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mgY4225+yLaYEdO1qL3hX0zNMm7c8Zi+TCePQPuZES5SitE0cbvWmL90QHE3hqS7Yvevs2fPZpzfATwJWFV8DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T09:19:30.419830Z"},"content_sha256":"f078b0526b45c534e3883067093991483ac1f298540fad515f6fae3753396d8d","schema_version":"1.0","event_id":"sha256:f078b0526b45c534e3883067093991483ac1f298540fad515f6fae3753396d8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:YQWVR77TXRSFDVDI7BEZLW6CPT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Language-Visual Embedding for Movie Understanding with Natural-Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Atousa Torabi, Leonid Sigal, Niket Tandon","submitted_at":"2016-09-26T19:14:12Z","abstract_excerpt":"Learning a joint language-visual embedding has a number of very appealing properties and can result in variety of practical application, including natural language image/video annotation and search. In this work, we study three different joint language-visual neural network model architectures. We evaluate our models on large scale LSMDC16 movie dataset for two tasks: 1) Standard Ranking for video annotation and retrieval 2) Our proposed movie multiple-choice test. This test facilitate automatic evaluation of visual-language models for natural language video annotation based on human activitie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.08124","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":""},"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":"2026-05-18T01:03:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ArVHTC3lbxQWBpK142MD99ui4ETtDIEFwAzHrBAY+M1w0yOR7HrkDm5ZcArqWsMqmkFkbHAAsSPo6y3D6al5Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T09:19:30.420566Z"},"content_sha256":"6c0d8c2d4091c92701df780a7e680c5c3b76cd4e93cd15052c5697ab4e291250","schema_version":"1.0","event_id":"sha256:6c0d8c2d4091c92701df780a7e680c5c3b76cd4e93cd15052c5697ab4e291250"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YQWVR77TXRSFDVDI7BEZLW6CPT/bundle.json","state_url":"https://pith.science/pith/YQWVR77TXRSFDVDI7BEZLW6CPT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YQWVR77TXRSFDVDI7BEZLW6CPT/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":"2026-05-24T09:19:30Z","links":{"resolver":"https://pith.science/pith/YQWVR77TXRSFDVDI7BEZLW6CPT","bundle":"https://pith.science/pith/YQWVR77TXRSFDVDI7BEZLW6CPT/bundle.json","state":"https://pith.science/pith/YQWVR77TXRSFDVDI7BEZLW6CPT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YQWVR77TXRSFDVDI7BEZLW6CPT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:YQWVR77TXRSFDVDI7BEZLW6CPT","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":"01de924187bf024b59bf774c1672994a6543c0a6717e04686826c7dade9b6af7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-26T19:14:12Z","title_canon_sha256":"35157ed78949456049774293f59578c7e3de3b7eb1c6c043a7f1c895e9a75801"},"schema_version":"1.0","source":{"id":"1609.08124","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.08124","created_at":"2026-05-18T01:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"1609.08124v1","created_at":"2026-05-18T01:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.08124","created_at":"2026-05-18T01:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"YQWVR77TXRSF","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"YQWVR77TXRSFDVDI","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"YQWVR77T","created_at":"2026-05-18T12:30:53Z"}],"graph_snapshots":[{"event_id":"sha256:6c0d8c2d4091c92701df780a7e680c5c3b76cd4e93cd15052c5697ab4e291250","target":"graph","created_at":"2026-05-18T01:03:54Z","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"},"paper":{"abstract_excerpt":"Learning a joint language-visual embedding has a number of very appealing properties and can result in variety of practical application, including natural language image/video annotation and search. In this work, we study three different joint language-visual neural network model architectures. We evaluate our models on large scale LSMDC16 movie dataset for two tasks: 1) Standard Ranking for video annotation and retrieval 2) Our proposed movie multiple-choice test. This test facilitate automatic evaluation of visual-language models for natural language video annotation based on human activitie","authors_text":"Atousa Torabi, Leonid Sigal, Niket Tandon","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-26T19:14:12Z","title":"Learning Language-Visual Embedding for Movie Understanding with Natural-Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.08124","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:f078b0526b45c534e3883067093991483ac1f298540fad515f6fae3753396d8d","target":"record","created_at":"2026-05-18T01:03:54Z","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":"01de924187bf024b59bf774c1672994a6543c0a6717e04686826c7dade9b6af7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-26T19:14:12Z","title_canon_sha256":"35157ed78949456049774293f59578c7e3de3b7eb1c6c043a7f1c895e9a75801"},"schema_version":"1.0","source":{"id":"1609.08124","kind":"arxiv","version":1}},"canonical_sha256":"c42d58fff3bc6451d468f84995dbc27cf0839e4583e21f1e96d135f8f774312f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c42d58fff3bc6451d468f84995dbc27cf0839e4583e21f1e96d135f8f774312f","first_computed_at":"2026-05-18T01:03:54.370117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:54.370117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R+89doHTjWWBtFAD/48QXZTLN1pANQvy7Uid/P1CVjckh5isUNNV7I7h3JOTMonS41m287snb82q5vqUrhSTBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:54.370751Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.08124","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f078b0526b45c534e3883067093991483ac1f298540fad515f6fae3753396d8d","sha256:6c0d8c2d4091c92701df780a7e680c5c3b76cd4e93cd15052c5697ab4e291250"],"state_sha256":"49cff79392e16f146e002fd99740de2a5b2667ea02ead2afe7e52a2e204402c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KjnYt2T7j+P49Q1QBdjLB0BppAyi3dsbj5EQHqg8IiqWTLzRzQ1762LNMlDtJes/2j5KdW/pk7gDsibZrtnHDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T09:19:30.424958Z","bundle_sha256":"cf3ee282a0e28528dbeb327cb89db8908d8110243b64a5fddf2ca7b5c311c5eb"}}