{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7R27IQAXYQLVIBU4HMPHVCAMG6","short_pith_number":"pith:7R27IQAX","canonical_record":{"source":{"id":"1810.03414","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-08T12:52:36Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"9300bb4246f6db5258071f06d327f72836a87940ae5090d248b77caeb9db21d0","abstract_canon_sha256":"2b0c7c57b5df3278321a7d2359dca2f540e737f038dd731a3374036fd426c90c"},"schema_version":"1.0"},"canonical_sha256":"fc75f44017c41754069c3b1e7a880c37bad9bb3410aae0c5af3cdb44dc624d4d","source":{"kind":"arxiv","id":"1810.03414","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03414","created_at":"2026-05-18T00:03:51Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03414v1","created_at":"2026-05-18T00:03:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03414","created_at":"2026-05-18T00:03:51Z"},{"alias_kind":"pith_short_12","alias_value":"7R27IQAXYQLV","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7R27IQAXYQLVIBU4","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7R27IQAX","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7R27IQAXYQLVIBU4HMPHVCAMG6","target":"record","payload":{"canonical_record":{"source":{"id":"1810.03414","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-08T12:52:36Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"9300bb4246f6db5258071f06d327f72836a87940ae5090d248b77caeb9db21d0","abstract_canon_sha256":"2b0c7c57b5df3278321a7d2359dca2f540e737f038dd731a3374036fd426c90c"},"schema_version":"1.0"},"canonical_sha256":"fc75f44017c41754069c3b1e7a880c37bad9bb3410aae0c5af3cdb44dc624d4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:51.370125Z","signature_b64":"d14ZdSKq1zGE0iwIZVW1kitZZgQz1UHzbV9hdsek926RAqsGMqdVYcr6YzTzrPtUAA0KDqPtGodF67JgUvh0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc75f44017c41754069c3b1e7a880c37bad9bb3410aae0c5af3cdb44dc624d4d","last_reissued_at":"2026-05-18T00:03:51.369595Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:51.369595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.03414","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":"2026-05-18T00:03:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F1WIphF8AU3i0vdXmnYU7EKpgZpyC8QBaOwGHYE5e/UGaXvkUnSzpS+qHUqybJZ9i5kWNOrpC4se61eSsSHxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T21:10:12.662662Z"},"content_sha256":"3994b9bb3d41f51ca3b573a68afa10ddaf20ebe620c314ce5daa9795d04b6aa2","schema_version":"1.0","event_id":"sha256:3994b9bb3d41f51ca3b573a68afa10ddaf20ebe620c314ce5daa9795d04b6aa2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7R27IQAXYQLVIBU4HMPHVCAMG6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dense Multimodal Fusion for Hierarchically Joint Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Di Hu, Feiping Nie, Xuelong Li","submitted_at":"2018-10-08T12:52:36Z","abstract_excerpt":"Multiple modalities can provide more valuable information than single one by describing the same contents in various ways. Hence, it is highly expected to learn effective joint representation by fusing the features of different modalities. However, previous methods mainly focus on fusing the shallow features or high-level representations generated by unimodal deep networks, which only capture part of the hierarchical correlations across modalities. In this paper, we propose to densely integrate the representations by greedily stacking multiple shared layers between different modality-specific "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03414","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":"2026-05-18T00:03:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aDqVujtdZSvnElD3BfoG803gfj+Lfgo2ZjV4N0krgVON6tABJ1wHpj25o8m38WDje5YkdKAFfYEjDTC1LPKbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T21:10:12.663475Z"},"content_sha256":"dd775633be40424819cb5eadd9249c2cceefe99cd408828645eee4fe6418f7c6","schema_version":"1.0","event_id":"sha256:dd775633be40424819cb5eadd9249c2cceefe99cd408828645eee4fe6418f7c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7R27IQAXYQLVIBU4HMPHVCAMG6/bundle.json","state_url":"https://pith.science/pith/7R27IQAXYQLVIBU4HMPHVCAMG6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7R27IQAXYQLVIBU4HMPHVCAMG6/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":"2026-06-06T21:10:12Z","links":{"resolver":"https://pith.science/pith/7R27IQAXYQLVIBU4HMPHVCAMG6","bundle":"https://pith.science/pith/7R27IQAXYQLVIBU4HMPHVCAMG6/bundle.json","state":"https://pith.science/pith/7R27IQAXYQLVIBU4HMPHVCAMG6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7R27IQAXYQLVIBU4HMPHVCAMG6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7R27IQAXYQLVIBU4HMPHVCAMG6","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":"2b0c7c57b5df3278321a7d2359dca2f540e737f038dd731a3374036fd426c90c","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-08T12:52:36Z","title_canon_sha256":"9300bb4246f6db5258071f06d327f72836a87940ae5090d248b77caeb9db21d0"},"schema_version":"1.0","source":{"id":"1810.03414","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03414","created_at":"2026-05-18T00:03:51Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03414v1","created_at":"2026-05-18T00:03:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03414","created_at":"2026-05-18T00:03:51Z"},{"alias_kind":"pith_short_12","alias_value":"7R27IQAXYQLV","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7R27IQAXYQLVIBU4","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7R27IQAX","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:dd775633be40424819cb5eadd9249c2cceefe99cd408828645eee4fe6418f7c6","target":"graph","created_at":"2026-05-18T00:03:51Z","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"},"paper":{"abstract_excerpt":"Multiple modalities can provide more valuable information than single one by describing the same contents in various ways. Hence, it is highly expected to learn effective joint representation by fusing the features of different modalities. However, previous methods mainly focus on fusing the shallow features or high-level representations generated by unimodal deep networks, which only capture part of the hierarchical correlations across modalities. In this paper, we propose to densely integrate the representations by greedily stacking multiple shared layers between different modality-specific ","authors_text":"Di Hu, Feiping Nie, Xuelong Li","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-08T12:52:36Z","title":"Dense Multimodal Fusion for Hierarchically Joint Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03414","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":"sha256:3994b9bb3d41f51ca3b573a68afa10ddaf20ebe620c314ce5daa9795d04b6aa2","target":"record","created_at":"2026-05-18T00:03:51Z","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":"2b0c7c57b5df3278321a7d2359dca2f540e737f038dd731a3374036fd426c90c","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-08T12:52:36Z","title_canon_sha256":"9300bb4246f6db5258071f06d327f72836a87940ae5090d248b77caeb9db21d0"},"schema_version":"1.0","source":{"id":"1810.03414","kind":"arxiv","version":1}},"canonical_sha256":"fc75f44017c41754069c3b1e7a880c37bad9bb3410aae0c5af3cdb44dc624d4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc75f44017c41754069c3b1e7a880c37bad9bb3410aae0c5af3cdb44dc624d4d","first_computed_at":"2026-05-18T00:03:51.369595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:51.369595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d14ZdSKq1zGE0iwIZVW1kitZZgQz1UHzbV9hdsek926RAqsGMqdVYcr6YzTzrPtUAA0KDqPtGodF67JgUvh0Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:51.370125Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.03414","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3994b9bb3d41f51ca3b573a68afa10ddaf20ebe620c314ce5daa9795d04b6aa2","sha256:dd775633be40424819cb5eadd9249c2cceefe99cd408828645eee4fe6418f7c6"],"state_sha256":"07b63d691b6faf4de9ad551ae9b86c71eff6076573eeda2dab30c813ffd6982f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rKblw1Wp/pqwTH349LBTXipAOVtIopuzX2VNAxbr29qfFS4FfrSkVOKQxZjXE2rh9l55lSNhpoPiSdqJ5XxKAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T21:10:12.667178Z","bundle_sha256":"828f42e8dbe36812d5b5528b22c6b98cf759982257a48c2a170ed9f6903eb532"}}