{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4MNLFJLZS265SJ4NAHGPYCZLIY","short_pith_number":"pith:4MNLFJLZ","canonical_record":{"source":{"id":"2410.14944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-19T02:27:30Z","cross_cats_sorted":[],"title_canon_sha256":"fc70b9dbe226139a97b3205b46fd0d087d9b5d0df32c6b2fb2c1ebd55efeca16","abstract_canon_sha256":"c35c93aec03429f4d50e691d5aaad42abb5e108c1142dfe79d118e9969db6ce0"},"schema_version":"1.0"},"canonical_sha256":"e31ab2a57996bdd9278d01ccfc0b2b460a79b278335eda26c5a7e961f26f443f","source":{"kind":"arxiv","id":"2410.14944","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14944","created_at":"2026-07-05T09:22:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14944v1","created_at":"2026-07-05T09:22:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14944","created_at":"2026-07-05T09:22:47Z"},{"alias_kind":"pith_short_12","alias_value":"4MNLFJLZS265","created_at":"2026-07-05T09:22:47Z"},{"alias_kind":"pith_short_16","alias_value":"4MNLFJLZS265SJ4N","created_at":"2026-07-05T09:22:47Z"},{"alias_kind":"pith_short_8","alias_value":"4MNLFJLZ","created_at":"2026-07-05T09:22:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4MNLFJLZS265SJ4NAHGPYCZLIY","target":"record","payload":{"canonical_record":{"source":{"id":"2410.14944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-19T02:27:30Z","cross_cats_sorted":[],"title_canon_sha256":"fc70b9dbe226139a97b3205b46fd0d087d9b5d0df32c6b2fb2c1ebd55efeca16","abstract_canon_sha256":"c35c93aec03429f4d50e691d5aaad42abb5e108c1142dfe79d118e9969db6ce0"},"schema_version":"1.0"},"canonical_sha256":"e31ab2a57996bdd9278d01ccfc0b2b460a79b278335eda26c5a7e961f26f443f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:47.369107Z","signature_b64":"75gIlCtMi6Y1uggm0+SWQyEHCOb0CdPvf6YZyRjdgkKUFjZ68aDDgW0LtEkPYkYJssn/2RMG0vvqB5MMKjAWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e31ab2a57996bdd9278d01ccfc0b2b460a79b278335eda26c5a7e961f26f443f","last_reissued_at":"2026-07-05T09:22:47.368598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:47.368598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.14944","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":"2026-07-05T09:22:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zktAR1IZ4kwlxeKYGKcSt67DDcMJNVzBdnSQ/c4oE6Bxh2LwRZCZh+tlgv0d/0Ad6bRC3/duZpAOYRbW1kOFCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:39:05.781844Z"},"content_sha256":"63811910ad4910ed349ee96839e55b838df614398a6812b2f6bab63bfdab9cbd","schema_version":"1.0","event_id":"sha256:63811910ad4910ed349ee96839e55b838df614398a6812b2f6bab63bfdab9cbd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4MNLFJLZS265SJ4NAHGPYCZLIY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Part-Whole Relational Fusion Towards Multi-Modal Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengxin Li, Jungong Han, Shoukun Xu, Yi Liu","submitted_at":"2024-10-19T02:27:30Z","abstract_excerpt":"Multi-modal fusion has played a vital role in multi-modal scene understanding. Most existing methods focus on cross-modal fusion involving two modalities, often overlooking more complex multi-modal fusion, which is essential for real-world applications like autonomous driving, where visible, depth, event, LiDAR, etc., are used. Besides, few attempts for multi-modal fusion, \\emph{e.g.}, simple concatenation, cross-modal attention, and token selection, cannot well dig into the intrinsic shared and specific details of multiple modalities. To tackle the challenge, in this paper, we propose a Part-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14944","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/2410.14944/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":"2026-07-05T09:22:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N5bGQ7VyaLruGjmP/NEp86mgRZubet0gCHy7/XpK1v2QPYaC9Ie+ekVWlJSrEHmeDBeU1avtB6CU/eDQS7JHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:39:05.782216Z"},"content_sha256":"5ab6e19453fd29bdb95f835c774e04e166a9c9e7348cf1cc1cc2c18534572208","schema_version":"1.0","event_id":"sha256:5ab6e19453fd29bdb95f835c774e04e166a9c9e7348cf1cc1cc2c18534572208"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4MNLFJLZS265SJ4NAHGPYCZLIY/bundle.json","state_url":"https://pith.science/pith/4MNLFJLZS265SJ4NAHGPYCZLIY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4MNLFJLZS265SJ4NAHGPYCZLIY/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":"2026-07-07T12:39:05Z","links":{"resolver":"https://pith.science/pith/4MNLFJLZS265SJ4NAHGPYCZLIY","bundle":"https://pith.science/pith/4MNLFJLZS265SJ4NAHGPYCZLIY/bundle.json","state":"https://pith.science/pith/4MNLFJLZS265SJ4NAHGPYCZLIY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4MNLFJLZS265SJ4NAHGPYCZLIY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4MNLFJLZS265SJ4NAHGPYCZLIY","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":"c35c93aec03429f4d50e691d5aaad42abb5e108c1142dfe79d118e9969db6ce0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-19T02:27:30Z","title_canon_sha256":"fc70b9dbe226139a97b3205b46fd0d087d9b5d0df32c6b2fb2c1ebd55efeca16"},"schema_version":"1.0","source":{"id":"2410.14944","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14944","created_at":"2026-07-05T09:22:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14944v1","created_at":"2026-07-05T09:22:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14944","created_at":"2026-07-05T09:22:47Z"},{"alias_kind":"pith_short_12","alias_value":"4MNLFJLZS265","created_at":"2026-07-05T09:22:47Z"},{"alias_kind":"pith_short_16","alias_value":"4MNLFJLZS265SJ4N","created_at":"2026-07-05T09:22:47Z"},{"alias_kind":"pith_short_8","alias_value":"4MNLFJLZ","created_at":"2026-07-05T09:22:47Z"}],"graph_snapshots":[{"event_id":"sha256:5ab6e19453fd29bdb95f835c774e04e166a9c9e7348cf1cc1cc2c18534572208","target":"graph","created_at":"2026-07-05T09:22:47Z","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/2410.14944/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal fusion has played a vital role in multi-modal scene understanding. Most existing methods focus on cross-modal fusion involving two modalities, often overlooking more complex multi-modal fusion, which is essential for real-world applications like autonomous driving, where visible, depth, event, LiDAR, etc., are used. Besides, few attempts for multi-modal fusion, \\emph{e.g.}, simple concatenation, cross-modal attention, and token selection, cannot well dig into the intrinsic shared and specific details of multiple modalities. To tackle the challenge, in this paper, we propose a Part-","authors_text":"Chengxin Li, Jungong Han, Shoukun Xu, Yi Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-19T02:27:30Z","title":"Part-Whole Relational Fusion Towards Multi-Modal Scene Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14944","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":"sha256:63811910ad4910ed349ee96839e55b838df614398a6812b2f6bab63bfdab9cbd","target":"record","created_at":"2026-07-05T09:22:47Z","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":"c35c93aec03429f4d50e691d5aaad42abb5e108c1142dfe79d118e9969db6ce0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-19T02:27:30Z","title_canon_sha256":"fc70b9dbe226139a97b3205b46fd0d087d9b5d0df32c6b2fb2c1ebd55efeca16"},"schema_version":"1.0","source":{"id":"2410.14944","kind":"arxiv","version":1}},"canonical_sha256":"e31ab2a57996bdd9278d01ccfc0b2b460a79b278335eda26c5a7e961f26f443f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e31ab2a57996bdd9278d01ccfc0b2b460a79b278335eda26c5a7e961f26f443f","first_computed_at":"2026-07-05T09:22:47.368598Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:47.368598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"75gIlCtMi6Y1uggm0+SWQyEHCOb0CdPvf6YZyRjdgkKUFjZ68aDDgW0LtEkPYkYJssn/2RMG0vvqB5MMKjAWAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:47.369107Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.14944","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63811910ad4910ed349ee96839e55b838df614398a6812b2f6bab63bfdab9cbd","sha256:5ab6e19453fd29bdb95f835c774e04e166a9c9e7348cf1cc1cc2c18534572208"],"state_sha256":"ca7dea6c629dde35e12557dba64b5bfb4defd11a67f22a64dd22b7915f42f013"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hputF+EktxqYlcmiy+cY7v2yPL/YZzj8XfznEUXHB9cUGCuFCyKMmtGCIFMmpMsXirAHHaEaGFGuKUI52V4mCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:39:05.784202Z","bundle_sha256":"167ddbf35bd7c8c66725841f6c818649ca8d7f39b2c551d5183394f8e6911a4b"}}