{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FBIQBZOUTPAQJAWCDO5DMDZBFC","short_pith_number":"pith:FBIQBZOU","canonical_record":{"source":{"id":"2407.18244","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-25T17:58:03Z","cross_cats_sorted":[],"title_canon_sha256":"c80515b2688a1549cde4551eb79c115932bb94878271206917ee0746ac94ab2f","abstract_canon_sha256":"a278356765ca4b2d8d69a8b6b49396288481731a4362e0c2cd365712ebe05666"},"schema_version":"1.0"},"canonical_sha256":"285100e5d49bc10482c21bba360f2128a8ee8b984a5a90dc692036ba52916772","source":{"kind":"arxiv","id":"2407.18244","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18244","created_at":"2026-07-05T08:48:36Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18244v1","created_at":"2026-07-05T08:48:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18244","created_at":"2026-07-05T08:48:36Z"},{"alias_kind":"pith_short_12","alias_value":"FBIQBZOUTPAQ","created_at":"2026-07-05T08:48:36Z"},{"alias_kind":"pith_short_16","alias_value":"FBIQBZOUTPAQJAWC","created_at":"2026-07-05T08:48:36Z"},{"alias_kind":"pith_short_8","alias_value":"FBIQBZOU","created_at":"2026-07-05T08:48:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FBIQBZOUTPAQJAWCDO5DMDZBFC","target":"record","payload":{"canonical_record":{"source":{"id":"2407.18244","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-25T17:58:03Z","cross_cats_sorted":[],"title_canon_sha256":"c80515b2688a1549cde4551eb79c115932bb94878271206917ee0746ac94ab2f","abstract_canon_sha256":"a278356765ca4b2d8d69a8b6b49396288481731a4362e0c2cd365712ebe05666"},"schema_version":"1.0"},"canonical_sha256":"285100e5d49bc10482c21bba360f2128a8ee8b984a5a90dc692036ba52916772","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:36.580235Z","signature_b64":"M08o+PiwnZ4XOSw7jSi2AvoUffYUtwxPMQCvUqYZqgnwoVXWBd9iKyti6RCqAlfxsMMEQOfetMhp4Uw2anCfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"285100e5d49bc10482c21bba360f2128a8ee8b984a5a90dc692036ba52916772","last_reissued_at":"2026-07-05T08:48:36.579790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:36.579790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.18244","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":"2026-07-05T08:48:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MMhuUNZQocf4mc5BHhbqoYByenYeYheRXB7havWuZWa1tZ0SwxV2pdLehCPIRDTtzIzyStANW04++R7MIaKeAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T10:47:18.330335Z"},"content_sha256":"f5482b7709e1858ec1cb0231e14c21f4eedcf63be045f6bb0fce71fd09759158","schema_version":"1.0","event_id":"sha256:f5482b7709e1858ec1cb0231e14c21f4eedcf63be045f6bb0fce71fd09759158"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FBIQBZOUTPAQJAWCDO5DMDZBFC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RefMask3D: Language-Guided Transformer for 3D Referring Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Henghui Ding, Shuting He","submitted_at":"2024-07-25T17:58:03Z","abstract_excerpt":"3D referring segmentation is an emerging and challenging vision-language task that aims to segment the object described by a natural language expression in a point cloud scene. The key challenge behind this task is vision-language feature fusion and alignment. In this work, we propose RefMask3D to explore the comprehensive multi-modal feature interaction and understanding. First, we propose a Geometry-Enhanced Group-Word Attention to integrate language with geometrically coherent sub-clouds through cross-modal group-word attention, which effectively addresses the challenges posed by the sparse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18244","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/2407.18244/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":"2026-07-05T08:48:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M4qH4gf7nqWnsrBI9bjwBHvqMH24RiRu/KyBQkqKDMYBtPYBzsugbP85HoJc+0SHarIKY7xApuXWGB1rNivnDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T10:47:18.331243Z"},"content_sha256":"37f929bb34605e89344170ef1705c198d94636440154786b3b764580d4f6684b","schema_version":"1.0","event_id":"sha256:37f929bb34605e89344170ef1705c198d94636440154786b3b764580d4f6684b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FBIQBZOUTPAQJAWCDO5DMDZBFC/bundle.json","state_url":"https://pith.science/pith/FBIQBZOUTPAQJAWCDO5DMDZBFC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FBIQBZOUTPAQJAWCDO5DMDZBFC/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":"2026-08-23T10:47:18Z","links":{"resolver":"https://pith.science/pith/FBIQBZOUTPAQJAWCDO5DMDZBFC","bundle":"https://pith.science/pith/FBIQBZOUTPAQJAWCDO5DMDZBFC/bundle.json","state":"https://pith.science/pith/FBIQBZOUTPAQJAWCDO5DMDZBFC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FBIQBZOUTPAQJAWCDO5DMDZBFC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FBIQBZOUTPAQJAWCDO5DMDZBFC","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":"a278356765ca4b2d8d69a8b6b49396288481731a4362e0c2cd365712ebe05666","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-25T17:58:03Z","title_canon_sha256":"c80515b2688a1549cde4551eb79c115932bb94878271206917ee0746ac94ab2f"},"schema_version":"1.0","source":{"id":"2407.18244","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18244","created_at":"2026-07-05T08:48:36Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18244v1","created_at":"2026-07-05T08:48:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18244","created_at":"2026-07-05T08:48:36Z"},{"alias_kind":"pith_short_12","alias_value":"FBIQBZOUTPAQ","created_at":"2026-07-05T08:48:36Z"},{"alias_kind":"pith_short_16","alias_value":"FBIQBZOUTPAQJAWC","created_at":"2026-07-05T08:48:36Z"},{"alias_kind":"pith_short_8","alias_value":"FBIQBZOU","created_at":"2026-07-05T08:48:36Z"}],"graph_snapshots":[{"event_id":"sha256:37f929bb34605e89344170ef1705c198d94636440154786b3b764580d4f6684b","target":"graph","created_at":"2026-07-05T08:48:36Z","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/2407.18244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D referring segmentation is an emerging and challenging vision-language task that aims to segment the object described by a natural language expression in a point cloud scene. The key challenge behind this task is vision-language feature fusion and alignment. In this work, we propose RefMask3D to explore the comprehensive multi-modal feature interaction and understanding. First, we propose a Geometry-Enhanced Group-Word Attention to integrate language with geometrically coherent sub-clouds through cross-modal group-word attention, which effectively addresses the challenges posed by the sparse","authors_text":"Henghui Ding, Shuting He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-25T17:58:03Z","title":"RefMask3D: Language-Guided Transformer for 3D Referring Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18244","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:f5482b7709e1858ec1cb0231e14c21f4eedcf63be045f6bb0fce71fd09759158","target":"record","created_at":"2026-07-05T08:48:36Z","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":"a278356765ca4b2d8d69a8b6b49396288481731a4362e0c2cd365712ebe05666","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-25T17:58:03Z","title_canon_sha256":"c80515b2688a1549cde4551eb79c115932bb94878271206917ee0746ac94ab2f"},"schema_version":"1.0","source":{"id":"2407.18244","kind":"arxiv","version":1}},"canonical_sha256":"285100e5d49bc10482c21bba360f2128a8ee8b984a5a90dc692036ba52916772","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"285100e5d49bc10482c21bba360f2128a8ee8b984a5a90dc692036ba52916772","first_computed_at":"2026-07-05T08:48:36.579790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:36.579790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M08o+PiwnZ4XOSw7jSi2AvoUffYUtwxPMQCvUqYZqgnwoVXWBd9iKyti6RCqAlfxsMMEQOfetMhp4Uw2anCfCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:36.580235Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.18244","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5482b7709e1858ec1cb0231e14c21f4eedcf63be045f6bb0fce71fd09759158","sha256:37f929bb34605e89344170ef1705c198d94636440154786b3b764580d4f6684b"],"state_sha256":"d896c605b5f570ca7c453e57741401dd433e7ecafb2a4f1cdbda2f9b48381312"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VNCbLw2k9YSOVj6ju5QyqiDa61kdiBzcDRwC92Quud5UaGPNIqFH9jdIaKqGmEolwSvcBien34p8Z0yLDUKOAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T10:47:18.337491Z","bundle_sha256":"8897f006a7bd286334bdda1d06dad3231ca80f7baf2c053a0abb4438a7d53c9c"}}