{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2XW44G3QSI6CYGKYDUDTJUEFSU","short_pith_number":"pith:2XW44G3Q","canonical_record":{"source":{"id":"2306.02329","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-04T11:08:53Z","cross_cats_sorted":[],"title_canon_sha256":"c281d351d6c26fc1901a0834294618ac548d97fc6c2c6d41ae1e206e09787143","abstract_canon_sha256":"ba0653aa09f19575af8e4d48c2f37d62eac94c243d1783f6f459f8571e0d2868"},"schema_version":"1.0"},"canonical_sha256":"d5edce1b70923c2c19581d0734d0859505e87dde5eee2bb472520f58f8df77ab","source":{"kind":"arxiv","id":"2306.02329","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02329","created_at":"2026-07-05T06:19:05Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02329v1","created_at":"2026-07-05T06:19:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02329","created_at":"2026-07-05T06:19:05Z"},{"alias_kind":"pith_short_12","alias_value":"2XW44G3QSI6C","created_at":"2026-07-05T06:19:05Z"},{"alias_kind":"pith_short_16","alias_value":"2XW44G3QSI6CYGKY","created_at":"2026-07-05T06:19:05Z"},{"alias_kind":"pith_short_8","alias_value":"2XW44G3Q","created_at":"2026-07-05T06:19:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2XW44G3QSI6CYGKYDUDTJUEFSU","target":"record","payload":{"canonical_record":{"source":{"id":"2306.02329","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-04T11:08:53Z","cross_cats_sorted":[],"title_canon_sha256":"c281d351d6c26fc1901a0834294618ac548d97fc6c2c6d41ae1e206e09787143","abstract_canon_sha256":"ba0653aa09f19575af8e4d48c2f37d62eac94c243d1783f6f459f8571e0d2868"},"schema_version":"1.0"},"canonical_sha256":"d5edce1b70923c2c19581d0734d0859505e87dde5eee2bb472520f58f8df77ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:05.095209Z","signature_b64":"+KSCSBbHMT7G7mwUhtkb55KZQ7EVOYT9UDTNTTXiuhIubgA67s/eCyQPNj11qnAuj+gKFNqCnjcbe1kS6ZDADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5edce1b70923c2c19581d0734d0859505e87dde5eee2bb472520f58f8df77ab","last_reissued_at":"2026-07-05T06:19:05.094810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:05.094810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.02329","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":"2026-07-05T06:19:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"81+qJI8H85miw9qRDXpFrwEfjaECgIo3OCsOuZom9N5PbGGml+sbdZSG5JE8+ukNWW01rIqUtGPGn895vk9ZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:55:53.922133Z"},"content_sha256":"57e1e39eef6c60265da300a3a3ee63bede9bf3258a5f6dc86e2664f0a80ad63d","schema_version":"1.0","event_id":"sha256:57e1e39eef6c60265da300a3a3ee63bede9bf3258a5f6dc86e2664f0a80ad63d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2XW44G3QSI6CYGKYDUDTJUEFSU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandros Delitzas, Georgios Vlassis, Gregor Bachmann, Maria Parelli, Nikolas Hars, Sotirios Anagnostidis, Thomas Hofmann","submitted_at":"2023-06-04T11:08:53Z","abstract_excerpt":"Training models to apply common-sense linguistic knowledge and visual concepts from 2D images to 3D scene understanding is a promising direction that researchers have only recently started to explore. However, it still remains understudied whether 2D distilled knowledge can provide useful representations for downstream 3D vision-language tasks such as 3D question answering. In this paper, we propose a novel 3D pre-training Vision-Language method, namely Multi-CLIP, that enables a model to learn language-grounded and transferable 3D scene point cloud representations. We leverage the representat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02329","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/2306.02329/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":"2026-07-05T06:19:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uNGpbChATs0sarC+uPkyla7SaYdEgXM9QKGpAKq5y2XWPSryneli3r+jsoLMTKBf5J2DGOGuAgf95W+S+eNqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:55:53.922803Z"},"content_sha256":"df0e3e75ef01b01e082f0b863561d4213f02e10613e6d019d36dbd3f21d2e458","schema_version":"1.0","event_id":"sha256:df0e3e75ef01b01e082f0b863561d4213f02e10613e6d019d36dbd3f21d2e458"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2XW44G3QSI6CYGKYDUDTJUEFSU/bundle.json","state_url":"https://pith.science/pith/2XW44G3QSI6CYGKYDUDTJUEFSU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2XW44G3QSI6CYGKYDUDTJUEFSU/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":"2026-07-07T04:55:53Z","links":{"resolver":"https://pith.science/pith/2XW44G3QSI6CYGKYDUDTJUEFSU","bundle":"https://pith.science/pith/2XW44G3QSI6CYGKYDUDTJUEFSU/bundle.json","state":"https://pith.science/pith/2XW44G3QSI6CYGKYDUDTJUEFSU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2XW44G3QSI6CYGKYDUDTJUEFSU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2XW44G3QSI6CYGKYDUDTJUEFSU","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":"ba0653aa09f19575af8e4d48c2f37d62eac94c243d1783f6f459f8571e0d2868","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-04T11:08:53Z","title_canon_sha256":"c281d351d6c26fc1901a0834294618ac548d97fc6c2c6d41ae1e206e09787143"},"schema_version":"1.0","source":{"id":"2306.02329","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02329","created_at":"2026-07-05T06:19:05Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02329v1","created_at":"2026-07-05T06:19:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02329","created_at":"2026-07-05T06:19:05Z"},{"alias_kind":"pith_short_12","alias_value":"2XW44G3QSI6C","created_at":"2026-07-05T06:19:05Z"},{"alias_kind":"pith_short_16","alias_value":"2XW44G3QSI6CYGKY","created_at":"2026-07-05T06:19:05Z"},{"alias_kind":"pith_short_8","alias_value":"2XW44G3Q","created_at":"2026-07-05T06:19:05Z"}],"graph_snapshots":[{"event_id":"sha256:df0e3e75ef01b01e082f0b863561d4213f02e10613e6d019d36dbd3f21d2e458","target":"graph","created_at":"2026-07-05T06:19:05Z","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/2306.02329/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training models to apply common-sense linguistic knowledge and visual concepts from 2D images to 3D scene understanding is a promising direction that researchers have only recently started to explore. However, it still remains understudied whether 2D distilled knowledge can provide useful representations for downstream 3D vision-language tasks such as 3D question answering. In this paper, we propose a novel 3D pre-training Vision-Language method, namely Multi-CLIP, that enables a model to learn language-grounded and transferable 3D scene point cloud representations. We leverage the representat","authors_text":"Alexandros Delitzas, Georgios Vlassis, Gregor Bachmann, Maria Parelli, Nikolas Hars, Sotirios Anagnostidis, Thomas Hofmann","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-04T11:08:53Z","title":"Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02329","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":"sha256:57e1e39eef6c60265da300a3a3ee63bede9bf3258a5f6dc86e2664f0a80ad63d","target":"record","created_at":"2026-07-05T06:19:05Z","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":"ba0653aa09f19575af8e4d48c2f37d62eac94c243d1783f6f459f8571e0d2868","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-04T11:08:53Z","title_canon_sha256":"c281d351d6c26fc1901a0834294618ac548d97fc6c2c6d41ae1e206e09787143"},"schema_version":"1.0","source":{"id":"2306.02329","kind":"arxiv","version":1}},"canonical_sha256":"d5edce1b70923c2c19581d0734d0859505e87dde5eee2bb472520f58f8df77ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5edce1b70923c2c19581d0734d0859505e87dde5eee2bb472520f58f8df77ab","first_computed_at":"2026-07-05T06:19:05.094810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:05.094810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+KSCSBbHMT7G7mwUhtkb55KZQ7EVOYT9UDTNTTXiuhIubgA67s/eCyQPNj11qnAuj+gKFNqCnjcbe1kS6ZDADQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:05.095209Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.02329","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57e1e39eef6c60265da300a3a3ee63bede9bf3258a5f6dc86e2664f0a80ad63d","sha256:df0e3e75ef01b01e082f0b863561d4213f02e10613e6d019d36dbd3f21d2e458"],"state_sha256":"57e60b21d5d713f66ed41c1fc6029b05f0dba59834cc55dc9538538eb473a4c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m+N/DpXjxieOV4C3Bkqqy7SodT/jk4J2pa5GQSiCLRpvPUOfpCtG7o4a3S/3buNjKkTRNrHew8nMkP0el4k2BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:55:53.926921Z","bundle_sha256":"49847696d4b8c0dccceacc35836206e88ab15ba8a1d07181622fcad473e46d59"}}