{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZKJQZZKEC5Z6NRY3JKIA2DHQWR","short_pith_number":"pith:ZKJQZZKE","canonical_record":{"source":{"id":"2104.03435","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-08T00:02:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5dca85799db363f9d835d36c3ce8f86897311620663344919c87be950736a73b","abstract_canon_sha256":"020c52ee506208779635c16f59e01d923a7d812a4cbdf50292d688880188fe41"},"schema_version":"1.0"},"canonical_sha256":"ca930ce5441773e6c71b4a900d0cf0b448df1ca4f9eeb09981f4ec3a3e1c2240","source":{"kind":"arxiv","id":"2104.03435","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.03435","created_at":"2026-07-05T02:30:17Z"},{"alias_kind":"arxiv_version","alias_value":"2104.03435v1","created_at":"2026-07-05T02:30:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.03435","created_at":"2026-07-05T02:30:17Z"},{"alias_kind":"pith_short_12","alias_value":"ZKJQZZKEC5Z6","created_at":"2026-07-05T02:30:17Z"},{"alias_kind":"pith_short_16","alias_value":"ZKJQZZKEC5Z6NRY3","created_at":"2026-07-05T02:30:17Z"},{"alias_kind":"pith_short_8","alias_value":"ZKJQZZKE","created_at":"2026-07-05T02:30:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZKJQZZKEC5Z6NRY3JKIA2DHQWR","target":"record","payload":{"canonical_record":{"source":{"id":"2104.03435","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-08T00:02:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5dca85799db363f9d835d36c3ce8f86897311620663344919c87be950736a73b","abstract_canon_sha256":"020c52ee506208779635c16f59e01d923a7d812a4cbdf50292d688880188fe41"},"schema_version":"1.0"},"canonical_sha256":"ca930ce5441773e6c71b4a900d0cf0b448df1ca4f9eeb09981f4ec3a3e1c2240","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:17.289279Z","signature_b64":"1EY/Jskd4rVSfLW/50mh2Vlt5CkjWTkXez6Sc/xTc/J2YljEp5coJa3T/bTeLR73XLmBeMFsArnwmVWaUpXADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca930ce5441773e6c71b4a900d0cf0b448df1ca4f9eeb09981f4ec3a3e1c2240","last_reissued_at":"2026-07-05T02:30:17.288877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:17.288877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.03435","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":"2026-07-05T02:30:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z0siTmRlC8QUfemR24jS+5eDE3IYirQbW7FxijQ+eL3K+9fbjGClxkfZD3+zhPoVwBdplpBl+fDFkOnMLd0xDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:16:58.141480Z"},"content_sha256":"b5c4155b4b9f92e633f0b686768079d4f365b181dd120deed63f52923af4cb7c","schema_version":"1.0","event_id":"sha256:b5c4155b4b9f92e633f0b686768079d4f365b181dd120deed63f52923af4cb7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZKJQZZKEC5Z6NRY3JKIA2DHQWR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Fusion Refiner Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"David Yang, Ser-Nam Lim, Sethuraman Sankaran","submitted_at":"2021-04-08T00:02:01Z","abstract_excerpt":"Tasks that rely on multi-modal information typically include a fusion module that combines information from different modalities. In this work, we develop a Refiner Fusion Network (ReFNet) that enables fusion modules to combine strong unimodal representation with strong multimodal representations. ReFNet combines the fusion network with a decoding/defusing module, which imposes a modality-centric responsibility condition. This approach addresses a big gap in existing multimodal fusion frameworks by ensuring that both unimodal and fused representations are strongly encoded in the latent fusion "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.03435","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.03435/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:30:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cUkASpl4KPdTsXEHrdcHEBYxG93M6sPCkkCg4Qwni2fITsc0HkNOdY1tOudqz/YGBmHRQng8IxiQiPx4ynY7AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:16:58.142406Z"},"content_sha256":"51ef108c45c360c49e9c6e10ffcc41811016cc3b7f75be96e5eb4a12b02eb2b6","schema_version":"1.0","event_id":"sha256:51ef108c45c360c49e9c6e10ffcc41811016cc3b7f75be96e5eb4a12b02eb2b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZKJQZZKEC5Z6NRY3JKIA2DHQWR/bundle.json","state_url":"https://pith.science/pith/ZKJQZZKEC5Z6NRY3JKIA2DHQWR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZKJQZZKEC5Z6NRY3JKIA2DHQWR/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":"2026-08-05T06:16:58Z","links":{"resolver":"https://pith.science/pith/ZKJQZZKEC5Z6NRY3JKIA2DHQWR","bundle":"https://pith.science/pith/ZKJQZZKEC5Z6NRY3JKIA2DHQWR/bundle.json","state":"https://pith.science/pith/ZKJQZZKEC5Z6NRY3JKIA2DHQWR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZKJQZZKEC5Z6NRY3JKIA2DHQWR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZKJQZZKEC5Z6NRY3JKIA2DHQWR","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":"020c52ee506208779635c16f59e01d923a7d812a4cbdf50292d688880188fe41","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-08T00:02:01Z","title_canon_sha256":"5dca85799db363f9d835d36c3ce8f86897311620663344919c87be950736a73b"},"schema_version":"1.0","source":{"id":"2104.03435","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.03435","created_at":"2026-07-05T02:30:17Z"},{"alias_kind":"arxiv_version","alias_value":"2104.03435v1","created_at":"2026-07-05T02:30:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.03435","created_at":"2026-07-05T02:30:17Z"},{"alias_kind":"pith_short_12","alias_value":"ZKJQZZKEC5Z6","created_at":"2026-07-05T02:30:17Z"},{"alias_kind":"pith_short_16","alias_value":"ZKJQZZKEC5Z6NRY3","created_at":"2026-07-05T02:30:17Z"},{"alias_kind":"pith_short_8","alias_value":"ZKJQZZKE","created_at":"2026-07-05T02:30:17Z"}],"graph_snapshots":[{"event_id":"sha256:51ef108c45c360c49e9c6e10ffcc41811016cc3b7f75be96e5eb4a12b02eb2b6","target":"graph","created_at":"2026-07-05T02:30:17Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2104.03435/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tasks that rely on multi-modal information typically include a fusion module that combines information from different modalities. In this work, we develop a Refiner Fusion Network (ReFNet) that enables fusion modules to combine strong unimodal representation with strong multimodal representations. ReFNet combines the fusion network with a decoding/defusing module, which imposes a modality-centric responsibility condition. This approach addresses a big gap in existing multimodal fusion frameworks by ensuring that both unimodal and fused representations are strongly encoded in the latent fusion ","authors_text":"David Yang, Ser-Nam Lim, Sethuraman Sankaran","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-08T00:02:01Z","title":"Multimodal Fusion Refiner Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.03435","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:b5c4155b4b9f92e633f0b686768079d4f365b181dd120deed63f52923af4cb7c","target":"record","created_at":"2026-07-05T02:30:17Z","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":"020c52ee506208779635c16f59e01d923a7d812a4cbdf50292d688880188fe41","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-08T00:02:01Z","title_canon_sha256":"5dca85799db363f9d835d36c3ce8f86897311620663344919c87be950736a73b"},"schema_version":"1.0","source":{"id":"2104.03435","kind":"arxiv","version":1}},"canonical_sha256":"ca930ce5441773e6c71b4a900d0cf0b448df1ca4f9eeb09981f4ec3a3e1c2240","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca930ce5441773e6c71b4a900d0cf0b448df1ca4f9eeb09981f4ec3a3e1c2240","first_computed_at":"2026-07-05T02:30:17.288877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:30:17.288877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1EY/Jskd4rVSfLW/50mh2Vlt5CkjWTkXez6Sc/xTc/J2YljEp5coJa3T/bTeLR73XLmBeMFsArnwmVWaUpXADw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:30:17.289279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.03435","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5c4155b4b9f92e633f0b686768079d4f365b181dd120deed63f52923af4cb7c","sha256:51ef108c45c360c49e9c6e10ffcc41811016cc3b7f75be96e5eb4a12b02eb2b6"],"state_sha256":"db359f13c5c054a1c09372636d1ecba4d5cefb79575ab06ab40b1f9b6b531333"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qwXu57qWFh5tGxVyR/DhcjXzuWXecRNrvssq2SQLOyB5ySU292Id5rp+WikSygHOeOcnBeldWXTLEozULtLWDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:16:58.149917Z","bundle_sha256":"fd9f08c869b2b95e30ab03209ebc08c130da3ddc02a69dc713bde4c3e6172f14"}}