{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:DFO3HCMFQCQCCMH7IK2VRROC5O","short_pith_number":"pith:DFO3HCMF","canonical_record":{"source":{"id":"1604.06838","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-23T00:28:17Z","cross_cats_sorted":[],"title_canon_sha256":"e003f3f3f477ea432553c2d895e8d2b29955d3040e282d8d7fcc68d0b59b2698","abstract_canon_sha256":"12967f674362e969c8608606b57c38c8db4417e39f965245fd36dcfc04313742"},"schema_version":"1.0"},"canonical_sha256":"195db3898580a02130ff42b558c5c2eb91783e209deb5984f5b33383453d5052","source":{"kind":"arxiv","id":"1604.06838","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.06838","created_at":"2026-05-18T00:56:46Z"},{"alias_kind":"arxiv_version","alias_value":"1604.06838v2","created_at":"2026-05-18T00:56:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.06838","created_at":"2026-05-18T00:56:46Z"},{"alias_kind":"pith_short_12","alias_value":"DFO3HCMFQCQC","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"DFO3HCMFQCQCCMH7","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"DFO3HCMF","created_at":"2026-05-18T12:30:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:DFO3HCMFQCQCCMH7IK2VRROC5O","target":"record","payload":{"canonical_record":{"source":{"id":"1604.06838","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-23T00:28:17Z","cross_cats_sorted":[],"title_canon_sha256":"e003f3f3f477ea432553c2d895e8d2b29955d3040e282d8d7fcc68d0b59b2698","abstract_canon_sha256":"12967f674362e969c8608606b57c38c8db4417e39f965245fd36dcfc04313742"},"schema_version":"1.0"},"canonical_sha256":"195db3898580a02130ff42b558c5c2eb91783e209deb5984f5b33383453d5052","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:46.182632Z","signature_b64":"Tx02QT1MvqJv03hse+r/urewOm1zutPUxgujK0Rdxm8Hy/de9awXnZBcmhGfwdpD5DaHGEnRJelasAjNyBeJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"195db3898580a02130ff42b558c5c2eb91783e209deb5984f5b33383453d5052","last_reissued_at":"2026-05-18T00:56:46.182054Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:46.182054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1604.06838","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":"2026-05-18T00:56:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jaou1vFYOv+BmZNqC0AVCQef19lix+WXfO02mIc6kp/NPV0XrAa8qjgq13Qhb6A02D1GtMWJX/1rc7Bz817mBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T05:13:16.297869Z"},"content_sha256":"530d091e9e5e09fe45f3fe01233b9a1a593ece625b1ee36e96ab1e6d2c560f93","schema_version":"1.0","event_id":"sha256:530d091e9e5e09fe45f3fe01233b9a1a593ece625b1ee36e96ab1e6d2c560f93"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:DFO3HCMFQCQCCMH7IK2VRROC5O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Word2VisualVec: Image and Video to Sentence Matching by Visual Feature Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cees G. M. Snoek, Jianfeng Dong, Xirong Li","submitted_at":"2016-04-23T00:28:17Z","abstract_excerpt":"This paper strives to find the sentence best describing the content of an image or video. Different from existing works, which rely on a joint subspace for image / video to sentence matching, we propose to do so in a visual space only. We contribute Word2VisualVec, a deep neural network architecture that learns to predict a deep visual encoding of textual input based on sentence vectorization and a multi-layer perceptron. We thoroughly analyze its architectural design, by varying the sentence vectorization strategy, network depth and the deep feature to predict for image to sentence matching. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.06838","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":""},"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":"2026-05-18T00:56:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VT800RJf8pBMcScTSimylgmJpo1I7//Pwxcqp2fLfzRk48BhkaXySPqsw/Da0buQFUmQ/bvgF1KXMzWcKaZ5Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T05:13:16.298605Z"},"content_sha256":"083e5d921b051bf6f4df3a87eb3b83619e2f02b60abe41db38fd75badc2653f7","schema_version":"1.0","event_id":"sha256:083e5d921b051bf6f4df3a87eb3b83619e2f02b60abe41db38fd75badc2653f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DFO3HCMFQCQCCMH7IK2VRROC5O/bundle.json","state_url":"https://pith.science/pith/DFO3HCMFQCQCCMH7IK2VRROC5O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DFO3HCMFQCQCCMH7IK2VRROC5O/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":"2026-06-08T05:13:16Z","links":{"resolver":"https://pith.science/pith/DFO3HCMFQCQCCMH7IK2VRROC5O","bundle":"https://pith.science/pith/DFO3HCMFQCQCCMH7IK2VRROC5O/bundle.json","state":"https://pith.science/pith/DFO3HCMFQCQCCMH7IK2VRROC5O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DFO3HCMFQCQCCMH7IK2VRROC5O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:DFO3HCMFQCQCCMH7IK2VRROC5O","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":"12967f674362e969c8608606b57c38c8db4417e39f965245fd36dcfc04313742","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-23T00:28:17Z","title_canon_sha256":"e003f3f3f477ea432553c2d895e8d2b29955d3040e282d8d7fcc68d0b59b2698"},"schema_version":"1.0","source":{"id":"1604.06838","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.06838","created_at":"2026-05-18T00:56:46Z"},{"alias_kind":"arxiv_version","alias_value":"1604.06838v2","created_at":"2026-05-18T00:56:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.06838","created_at":"2026-05-18T00:56:46Z"},{"alias_kind":"pith_short_12","alias_value":"DFO3HCMFQCQC","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"DFO3HCMFQCQCCMH7","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"DFO3HCMF","created_at":"2026-05-18T12:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:083e5d921b051bf6f4df3a87eb3b83619e2f02b60abe41db38fd75badc2653f7","target":"graph","created_at":"2026-05-18T00:56:46Z","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":"This paper strives to find the sentence best describing the content of an image or video. Different from existing works, which rely on a joint subspace for image / video to sentence matching, we propose to do so in a visual space only. We contribute Word2VisualVec, a deep neural network architecture that learns to predict a deep visual encoding of textual input based on sentence vectorization and a multi-layer perceptron. We thoroughly analyze its architectural design, by varying the sentence vectorization strategy, network depth and the deep feature to predict for image to sentence matching. ","authors_text":"Cees G. M. Snoek, Jianfeng Dong, Xirong Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-23T00:28:17Z","title":"Word2VisualVec: Image and Video to Sentence Matching by Visual Feature Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.06838","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":"sha256:530d091e9e5e09fe45f3fe01233b9a1a593ece625b1ee36e96ab1e6d2c560f93","target":"record","created_at":"2026-05-18T00:56:46Z","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":"12967f674362e969c8608606b57c38c8db4417e39f965245fd36dcfc04313742","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-23T00:28:17Z","title_canon_sha256":"e003f3f3f477ea432553c2d895e8d2b29955d3040e282d8d7fcc68d0b59b2698"},"schema_version":"1.0","source":{"id":"1604.06838","kind":"arxiv","version":2}},"canonical_sha256":"195db3898580a02130ff42b558c5c2eb91783e209deb5984f5b33383453d5052","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"195db3898580a02130ff42b558c5c2eb91783e209deb5984f5b33383453d5052","first_computed_at":"2026-05-18T00:56:46.182054Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:56:46.182054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tx02QT1MvqJv03hse+r/urewOm1zutPUxgujK0Rdxm8Hy/de9awXnZBcmhGfwdpD5DaHGEnRJelasAjNyBeJCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:56:46.182632Z","signed_message":"canonical_sha256_bytes"},"source_id":"1604.06838","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:530d091e9e5e09fe45f3fe01233b9a1a593ece625b1ee36e96ab1e6d2c560f93","sha256:083e5d921b051bf6f4df3a87eb3b83619e2f02b60abe41db38fd75badc2653f7"],"state_sha256":"c31d5349773255baba58871a1a2f93ebebb3cb1fc6aa8656174549d1e0571b6c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cgbfp3FdrrPyMGlF6e3UtpnV7K/fvDDUGm16w+7u9AY0ZuYXCzwbQwAfiHLBbp21RnZGFlBRdKUSXUntqh1HBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T05:13:16.302372Z","bundle_sha256":"91fac8113cf96d485c922abb27ec7e3308dd842f3e7f73e69016b122b5b171b4"}}