{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:CTCC7UVNTMQMIECRPESE4B3RVS","short_pith_number":"pith:CTCC7UVN","canonical_record":{"source":{"id":"1808.02559","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-07T21:33:37Z","cross_cats_sorted":[],"title_canon_sha256":"0181c4f60fd28a820d7dd5a726a4e5c6b6de8a3b756451ca1626ad6c465d871e","abstract_canon_sha256":"5820497671f32344368feb28bbeb4d55efd904e17e3043196d7e04e59289fe91"},"schema_version":"1.0"},"canonical_sha256":"14c42fd2ad9b20c4105179244e0771ac970da1798f36ef8baa8f7570a09e28a7","source":{"kind":"arxiv","id":"1808.02559","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.02559","created_at":"2026-05-18T00:08:35Z"},{"alias_kind":"arxiv_version","alias_value":"1808.02559v1","created_at":"2026-05-18T00:08:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.02559","created_at":"2026-05-18T00:08:35Z"},{"alias_kind":"pith_short_12","alias_value":"CTCC7UVNTMQM","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"CTCC7UVNTMQMIECR","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"CTCC7UVN","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:CTCC7UVNTMQMIECRPESE4B3RVS","target":"record","payload":{"canonical_record":{"source":{"id":"1808.02559","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-07T21:33:37Z","cross_cats_sorted":[],"title_canon_sha256":"0181c4f60fd28a820d7dd5a726a4e5c6b6de8a3b756451ca1626ad6c465d871e","abstract_canon_sha256":"5820497671f32344368feb28bbeb4d55efd904e17e3043196d7e04e59289fe91"},"schema_version":"1.0"},"canonical_sha256":"14c42fd2ad9b20c4105179244e0771ac970da1798f36ef8baa8f7570a09e28a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:35.031920Z","signature_b64":"qj9k41RTxds5ZuqcfXqmt4CbvJ03rO4btVH5/eAk6iF4RZLK+XwO5BzEWCNoVQZsATr9kIojZJ7lNtOyQCWEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14c42fd2ad9b20c4105179244e0771ac970da1798f36ef8baa8f7570a09e28a7","last_reissued_at":"2026-05-18T00:08:35.031379Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:35.031379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.02559","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":"2026-05-18T00:08:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IuMbAY2xYwjlRTrwxj8fh5JYpoK2ZGIP3HokPph4BC4bRzwBvNd6FZDgsL2QNMC2/qoeCGybq2bFv0fkzIWKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T04:44:43.458816Z"},"content_sha256":"f60e0d8e89b957ce79e914457267fb21e96decfc2a2e217bd00ec5a2310f3f73","schema_version":"1.0","event_id":"sha256:f60e0d8e89b957ce79e914457267fb21e96decfc2a2e217bd00ec5a2310f3f73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:CTCC7UVNTMQMIECRPESE4B3RVS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Joint Sequence Fusion Model for Video Question Answering and Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gunhee Kim, Jongseok Kim, Youngjae Yu","submitted_at":"2018-08-07T21:33:37Z","abstract_excerpt":"We present an approach named JSFusion (Joint Sequence Fusion) that can measure semantic similarity between any pairs of multimodal sequence data (e.g. a video clip and a language sentence). Our multimodal matching network consists of two key components. First, the Joint Semantic Tensor composes a dense pairwise representation of two sequence data into a 3D tensor. Then, the Convolutional Hierarchical Decoder computes their similarity score by discovering hidden hierarchical matches between the two sequence modalities. Both modules leverage hierarchical attention mechanisms that learn to promot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.02559","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":"2026-05-18T00:08:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mrc9BeNgatb9TYq52wxijVpN3x0VznDktc3QbQ5oSI7Zetd93b6GNuh6iPXbN8yddlE5/0iiBkoFNv77c5DhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T04:44:43.459161Z"},"content_sha256":"3d2f36ae33d988d00ce7fbed412ac8fa6cb4319a5a4920939d12705b86ac30f1","schema_version":"1.0","event_id":"sha256:3d2f36ae33d988d00ce7fbed412ac8fa6cb4319a5a4920939d12705b86ac30f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CTCC7UVNTMQMIECRPESE4B3RVS/bundle.json","state_url":"https://pith.science/pith/CTCC7UVNTMQMIECRPESE4B3RVS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CTCC7UVNTMQMIECRPESE4B3RVS/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":"2026-06-04T04:44:43Z","links":{"resolver":"https://pith.science/pith/CTCC7UVNTMQMIECRPESE4B3RVS","bundle":"https://pith.science/pith/CTCC7UVNTMQMIECRPESE4B3RVS/bundle.json","state":"https://pith.science/pith/CTCC7UVNTMQMIECRPESE4B3RVS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CTCC7UVNTMQMIECRPESE4B3RVS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CTCC7UVNTMQMIECRPESE4B3RVS","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":"5820497671f32344368feb28bbeb4d55efd904e17e3043196d7e04e59289fe91","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-07T21:33:37Z","title_canon_sha256":"0181c4f60fd28a820d7dd5a726a4e5c6b6de8a3b756451ca1626ad6c465d871e"},"schema_version":"1.0","source":{"id":"1808.02559","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.02559","created_at":"2026-05-18T00:08:35Z"},{"alias_kind":"arxiv_version","alias_value":"1808.02559v1","created_at":"2026-05-18T00:08:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.02559","created_at":"2026-05-18T00:08:35Z"},{"alias_kind":"pith_short_12","alias_value":"CTCC7UVNTMQM","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"CTCC7UVNTMQMIECR","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"CTCC7UVN","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:3d2f36ae33d988d00ce7fbed412ac8fa6cb4319a5a4920939d12705b86ac30f1","target":"graph","created_at":"2026-05-18T00:08:35Z","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":"We present an approach named JSFusion (Joint Sequence Fusion) that can measure semantic similarity between any pairs of multimodal sequence data (e.g. a video clip and a language sentence). Our multimodal matching network consists of two key components. First, the Joint Semantic Tensor composes a dense pairwise representation of two sequence data into a 3D tensor. Then, the Convolutional Hierarchical Decoder computes their similarity score by discovering hidden hierarchical matches between the two sequence modalities. Both modules leverage hierarchical attention mechanisms that learn to promot","authors_text":"Gunhee Kim, Jongseok Kim, Youngjae Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-07T21:33:37Z","title":"A Joint Sequence Fusion Model for Video Question Answering and Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.02559","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:f60e0d8e89b957ce79e914457267fb21e96decfc2a2e217bd00ec5a2310f3f73","target":"record","created_at":"2026-05-18T00:08:35Z","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":"5820497671f32344368feb28bbeb4d55efd904e17e3043196d7e04e59289fe91","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-07T21:33:37Z","title_canon_sha256":"0181c4f60fd28a820d7dd5a726a4e5c6b6de8a3b756451ca1626ad6c465d871e"},"schema_version":"1.0","source":{"id":"1808.02559","kind":"arxiv","version":1}},"canonical_sha256":"14c42fd2ad9b20c4105179244e0771ac970da1798f36ef8baa8f7570a09e28a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14c42fd2ad9b20c4105179244e0771ac970da1798f36ef8baa8f7570a09e28a7","first_computed_at":"2026-05-18T00:08:35.031379Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:08:35.031379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qj9k41RTxds5ZuqcfXqmt4CbvJ03rO4btVH5/eAk6iF4RZLK+XwO5BzEWCNoVQZsATr9kIojZJ7lNtOyQCWEDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:08:35.031920Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.02559","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f60e0d8e89b957ce79e914457267fb21e96decfc2a2e217bd00ec5a2310f3f73","sha256:3d2f36ae33d988d00ce7fbed412ac8fa6cb4319a5a4920939d12705b86ac30f1"],"state_sha256":"ad03e3b3b1b57215d9206e8b81cb767bbf4f64af78bd8b8228a265f53aa490fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vPlCm49BH9jNrQ48pmUILsNdiDq+cDCPu0bqEgUev7pxkUkcePJyZLsqdJGB5ytXD7zGkBYKxNQmCBX/1ehRBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T04:44:43.461269Z","bundle_sha256":"84ab53ac3f18aee09ac99a3bc7925a2824722e1903ed970d4a56bde4b2b49fe1"}}