{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:5XAXNVYHAO74ZQRWMQDNGBCQAJ","short_pith_number":"pith:5XAXNVYH","canonical_record":{"source":{"id":"1412.4729","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-15T19:21:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"46be15540bde0f9b48641f72833a5e795e7d2ef811bbabd0f481d45439d1489f","abstract_canon_sha256":"ca4388753fa2669d77e9bc3432f044dca03b29657af6a109730d16855b351786"},"schema_version":"1.0"},"canonical_sha256":"edc176d70703bfccc2366406d304500260263ce0bbf6a2373b2505e02a00b360","source":{"kind":"arxiv","id":"1412.4729","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.4729","created_at":"2026-05-18T02:17:24Z"},{"alias_kind":"arxiv_version","alias_value":"1412.4729v3","created_at":"2026-05-18T02:17:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.4729","created_at":"2026-05-18T02:17:24Z"},{"alias_kind":"pith_short_12","alias_value":"5XAXNVYHAO74","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"5XAXNVYHAO74ZQRW","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"5XAXNVYH","created_at":"2026-05-18T12:28:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:5XAXNVYHAO74ZQRWMQDNGBCQAJ","target":"record","payload":{"canonical_record":{"source":{"id":"1412.4729","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-15T19:21:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"46be15540bde0f9b48641f72833a5e795e7d2ef811bbabd0f481d45439d1489f","abstract_canon_sha256":"ca4388753fa2669d77e9bc3432f044dca03b29657af6a109730d16855b351786"},"schema_version":"1.0"},"canonical_sha256":"edc176d70703bfccc2366406d304500260263ce0bbf6a2373b2505e02a00b360","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:17:24.270338Z","signature_b64":"JsA5wTMDNg9FDfvlfQiMjkioigH3JY7SkKf9fcNJkxwXcdBigRdu+ZZT6aINi5vPKhjMNlexWKZYOQH4xCHhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edc176d70703bfccc2366406d304500260263ce0bbf6a2373b2505e02a00b360","last_reissued_at":"2026-05-18T02:17:24.269599Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:17:24.269599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1412.4729","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:17:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BV2+/cMxcznijZXjmSzeQJFdWypn05WwBMBwXyVTUDaaKLyHsla7/B2cSKT/gdMzbGOppuI46pAA391DQijgDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T02:02:37.722179Z"},"content_sha256":"555f632de660c980b4bdc1198526f3d0ec3009768aa16191a2d12ded4857ab11","schema_version":"1.0","event_id":"sha256:555f632de660c980b4bdc1198526f3d0ec3009768aa16191a2d12ded4857ab11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:5XAXNVYHAO74ZQRWMQDNGBCQAJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Translating Videos to Natural Language Using Deep Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Huijuan Xu, Jeff Donahue, Kate Saenko, Marcus Rohrbach, Raymond Mooney, Subhashini Venugopalan","submitted_at":"2014-12-15T19:21:50Z","abstract_excerpt":"Solving the visual symbol grounding problem has long been a goal of artificial intelligence. The field appears to be advancing closer to this goal with recent breakthroughs in deep learning for natural language grounding in static images. In this paper, we propose to translate videos directly to sentences using a unified deep neural network with both convolutional and recurrent structure. Described video datasets are scarce, and most existing methods have been applied to toy domains with a small vocabulary of possible words. By transferring knowledge from 1.2M+ images with category labels and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.4729","kind":"arxiv","version":3},"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":"2026-05-18T02:17:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qf/VE20t2FqxMSHy38IXkj961poVJIVhFjVHCoRmiAPyvkwyL5aj2zp9XsELggY9IWKnaXa6998jCmKZTgxRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T02:02:37.722898Z"},"content_sha256":"e8ed52c55391125306b4c6bff330ab6da18b52a2ea499f40f4362e4ecd075c71","schema_version":"1.0","event_id":"sha256:e8ed52c55391125306b4c6bff330ab6da18b52a2ea499f40f4362e4ecd075c71"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5XAXNVYHAO74ZQRWMQDNGBCQAJ/bundle.json","state_url":"https://pith.science/pith/5XAXNVYHAO74ZQRWMQDNGBCQAJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5XAXNVYHAO74ZQRWMQDNGBCQAJ/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":"2026-05-20T02:02:37Z","links":{"resolver":"https://pith.science/pith/5XAXNVYHAO74ZQRWMQDNGBCQAJ","bundle":"https://pith.science/pith/5XAXNVYHAO74ZQRWMQDNGBCQAJ/bundle.json","state":"https://pith.science/pith/5XAXNVYHAO74ZQRWMQDNGBCQAJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5XAXNVYHAO74ZQRWMQDNGBCQAJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:5XAXNVYHAO74ZQRWMQDNGBCQAJ","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":"ca4388753fa2669d77e9bc3432f044dca03b29657af6a109730d16855b351786","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-15T19:21:50Z","title_canon_sha256":"46be15540bde0f9b48641f72833a5e795e7d2ef811bbabd0f481d45439d1489f"},"schema_version":"1.0","source":{"id":"1412.4729","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.4729","created_at":"2026-05-18T02:17:24Z"},{"alias_kind":"arxiv_version","alias_value":"1412.4729v3","created_at":"2026-05-18T02:17:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.4729","created_at":"2026-05-18T02:17:24Z"},{"alias_kind":"pith_short_12","alias_value":"5XAXNVYHAO74","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"5XAXNVYHAO74ZQRW","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"5XAXNVYH","created_at":"2026-05-18T12:28:16Z"}],"graph_snapshots":[{"event_id":"sha256:e8ed52c55391125306b4c6bff330ab6da18b52a2ea499f40f4362e4ecd075c71","target":"graph","created_at":"2026-05-18T02:17:24Z","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":"Solving the visual symbol grounding problem has long been a goal of artificial intelligence. The field appears to be advancing closer to this goal with recent breakthroughs in deep learning for natural language grounding in static images. In this paper, we propose to translate videos directly to sentences using a unified deep neural network with both convolutional and recurrent structure. Described video datasets are scarce, and most existing methods have been applied to toy domains with a small vocabulary of possible words. By transferring knowledge from 1.2M+ images with category labels and ","authors_text":"Huijuan Xu, Jeff Donahue, Kate Saenko, Marcus Rohrbach, Raymond Mooney, Subhashini Venugopalan","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-15T19:21:50Z","title":"Translating Videos to Natural Language Using Deep Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.4729","kind":"arxiv","version":3},"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":"sha256:555f632de660c980b4bdc1198526f3d0ec3009768aa16191a2d12ded4857ab11","target":"record","created_at":"2026-05-18T02:17:24Z","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":"ca4388753fa2669d77e9bc3432f044dca03b29657af6a109730d16855b351786","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-15T19:21:50Z","title_canon_sha256":"46be15540bde0f9b48641f72833a5e795e7d2ef811bbabd0f481d45439d1489f"},"schema_version":"1.0","source":{"id":"1412.4729","kind":"arxiv","version":3}},"canonical_sha256":"edc176d70703bfccc2366406d304500260263ce0bbf6a2373b2505e02a00b360","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edc176d70703bfccc2366406d304500260263ce0bbf6a2373b2505e02a00b360","first_computed_at":"2026-05-18T02:17:24.269599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:17:24.269599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JsA5wTMDNg9FDfvlfQiMjkioigH3JY7SkKf9fcNJkxwXcdBigRdu+ZZT6aINi5vPKhjMNlexWKZYOQH4xCHhDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:17:24.270338Z","signed_message":"canonical_sha256_bytes"},"source_id":"1412.4729","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:555f632de660c980b4bdc1198526f3d0ec3009768aa16191a2d12ded4857ab11","sha256:e8ed52c55391125306b4c6bff330ab6da18b52a2ea499f40f4362e4ecd075c71"],"state_sha256":"d162ce782a044132ccf243cd9c51651ddeb71b0ac77217d541cb620691b2a802"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HjHR2GzAxVvQnLmIRIuL1ubNbVnhko7O11f1hgPw5ufx/P+dXC6nF+pTmbIJ82KbH0iAGEDibjmLlO7IJPWvAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T02:02:37.727050Z","bundle_sha256":"e94582227129135c1032476577b825ae9e9a4aa4b920b076b444f5f41e3a2e13"}}