{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZBBY3PXSWK5JHKW6GESBPNE4UF","short_pith_number":"pith:ZBBY3PXS","canonical_record":{"source":{"id":"2301.04926","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-12T10:42:39Z","cross_cats_sorted":[],"title_canon_sha256":"cdc5066b715ddfd361ec330165948d72a4105bef9265a368d9bffb8f25df7817","abstract_canon_sha256":"5b02282bca0433f065cf77aca20da3a0d2906476914a8499106982c642a3dc47"},"schema_version":"1.0"},"canonical_sha256":"c8438dbef2b2ba93aade312417b49ca157e3e85e304abe349b2a3ad27f37af00","source":{"kind":"arxiv","id":"2301.04926","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.04926","created_at":"2026-07-05T05:58:40Z"},{"alias_kind":"arxiv_version","alias_value":"2301.04926v2","created_at":"2026-07-05T05:58:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04926","created_at":"2026-07-05T05:58:40Z"},{"alias_kind":"pith_short_12","alias_value":"ZBBY3PXSWK5J","created_at":"2026-07-05T05:58:40Z"},{"alias_kind":"pith_short_16","alias_value":"ZBBY3PXSWK5JHKW6","created_at":"2026-07-05T05:58:40Z"},{"alias_kind":"pith_short_8","alias_value":"ZBBY3PXS","created_at":"2026-07-05T05:58:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZBBY3PXSWK5JHKW6GESBPNE4UF","target":"record","payload":{"canonical_record":{"source":{"id":"2301.04926","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-12T10:42:39Z","cross_cats_sorted":[],"title_canon_sha256":"cdc5066b715ddfd361ec330165948d72a4105bef9265a368d9bffb8f25df7817","abstract_canon_sha256":"5b02282bca0433f065cf77aca20da3a0d2906476914a8499106982c642a3dc47"},"schema_version":"1.0"},"canonical_sha256":"c8438dbef2b2ba93aade312417b49ca157e3e85e304abe349b2a3ad27f37af00","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:40.443989Z","signature_b64":"mWssrgy4rw5EqdjwIhQeXp3NqPe1pZzWd02Xx9NrTnrSEDwm28Wcvb/f0ANXMp1EEbIuEKG/JSAelJBhrZ1dDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8438dbef2b2ba93aade312417b49ca157e3e85e304abe349b2a3ad27f37af00","last_reissued_at":"2026-07-05T05:58:40.443556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:40.443556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.04926","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:58:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wtdC1W0FTEVjSUY8Iv93n19WhnCG+Q2txAgJu6REpEa15tFo7bGxdjq+irE3FBxBxawomL3FOAV5ojTE5Bg3Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T18:59:52.335408Z"},"content_sha256":"364e66a2c2c5b461a83c65308402c09785097820c617e70021c7c862f207a728","schema_version":"1.0","event_id":"sha256:364e66a2c2c5b461a83c65308402c09785097820c617e70021c7c862f207a728"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZBBY3PXSWK5JHKW6GESBPNE4UF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lingdong Kong, Runnan Chen, Wenping Wang, Xinge Zhu, Yikang Li, Youquan Liu, Yuenan Hou, Yuexin Ma, Yu Qiao","submitted_at":"2023-01-12T10:42:39Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP to help the learning in 3D scene understanding has yet to be explored. In this paper, we make the first attempt to investigate how CLIP knowledge benefits 3D scene understanding. We propose CLIP2Scene, a simple yet effective framework that transfers CLIP knowledge from 2D image-text pre-trained models to a 3D point cloud network. We show that the pre-trained 3D network yields impressive performance on various downstream tasks, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04926","kind":"arxiv","version":2},"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/2301.04926/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":"2026-07-05T05:58:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8R3Qic9m+JV1eAFdFhR5GYMrYkOK4tRI9C8WC6DLHIEve72RKthTTlAy+F/MgvmUhlmgDQRpz5uAJrGyPvhdBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T18:59:52.335923Z"},"content_sha256":"d6f076239be4e4aa2beca416aec6ebcac2bc72560d1e25eebeb266b0ab91a5b9","schema_version":"1.0","event_id":"sha256:d6f076239be4e4aa2beca416aec6ebcac2bc72560d1e25eebeb266b0ab91a5b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZBBY3PXSWK5JHKW6GESBPNE4UF/bundle.json","state_url":"https://pith.science/pith/ZBBY3PXSWK5JHKW6GESBPNE4UF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZBBY3PXSWK5JHKW6GESBPNE4UF/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":"2026-08-16T18:59:52Z","links":{"resolver":"https://pith.science/pith/ZBBY3PXSWK5JHKW6GESBPNE4UF","bundle":"https://pith.science/pith/ZBBY3PXSWK5JHKW6GESBPNE4UF/bundle.json","state":"https://pith.science/pith/ZBBY3PXSWK5JHKW6GESBPNE4UF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZBBY3PXSWK5JHKW6GESBPNE4UF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZBBY3PXSWK5JHKW6GESBPNE4UF","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":"5b02282bca0433f065cf77aca20da3a0d2906476914a8499106982c642a3dc47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-12T10:42:39Z","title_canon_sha256":"cdc5066b715ddfd361ec330165948d72a4105bef9265a368d9bffb8f25df7817"},"schema_version":"1.0","source":{"id":"2301.04926","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.04926","created_at":"2026-07-05T05:58:40Z"},{"alias_kind":"arxiv_version","alias_value":"2301.04926v2","created_at":"2026-07-05T05:58:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04926","created_at":"2026-07-05T05:58:40Z"},{"alias_kind":"pith_short_12","alias_value":"ZBBY3PXSWK5J","created_at":"2026-07-05T05:58:40Z"},{"alias_kind":"pith_short_16","alias_value":"ZBBY3PXSWK5JHKW6","created_at":"2026-07-05T05:58:40Z"},{"alias_kind":"pith_short_8","alias_value":"ZBBY3PXS","created_at":"2026-07-05T05:58:40Z"}],"graph_snapshots":[{"event_id":"sha256:d6f076239be4e4aa2beca416aec6ebcac2bc72560d1e25eebeb266b0ab91a5b9","target":"graph","created_at":"2026-07-05T05:58:40Z","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/2301.04926/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP to help the learning in 3D scene understanding has yet to be explored. In this paper, we make the first attempt to investigate how CLIP knowledge benefits 3D scene understanding. We propose CLIP2Scene, a simple yet effective framework that transfers CLIP knowledge from 2D image-text pre-trained models to a 3D point cloud network. We show that the pre-trained 3D network yields impressive performance on various downstream tasks, ","authors_text":"Lingdong Kong, Runnan Chen, Wenping Wang, Xinge Zhu, Yikang Li, Youquan Liu, Yuenan Hou, Yuexin Ma, Yu Qiao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-12T10:42:39Z","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04926","kind":"arxiv","version":2},"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":"sha256:364e66a2c2c5b461a83c65308402c09785097820c617e70021c7c862f207a728","target":"record","created_at":"2026-07-05T05:58:40Z","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":"5b02282bca0433f065cf77aca20da3a0d2906476914a8499106982c642a3dc47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-12T10:42:39Z","title_canon_sha256":"cdc5066b715ddfd361ec330165948d72a4105bef9265a368d9bffb8f25df7817"},"schema_version":"1.0","source":{"id":"2301.04926","kind":"arxiv","version":2}},"canonical_sha256":"c8438dbef2b2ba93aade312417b49ca157e3e85e304abe349b2a3ad27f37af00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8438dbef2b2ba93aade312417b49ca157e3e85e304abe349b2a3ad27f37af00","first_computed_at":"2026-07-05T05:58:40.443556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:58:40.443556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mWssrgy4rw5EqdjwIhQeXp3NqPe1pZzWd02Xx9NrTnrSEDwm28Wcvb/f0ANXMp1EEbIuEKG/JSAelJBhrZ1dDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:58:40.443989Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.04926","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:364e66a2c2c5b461a83c65308402c09785097820c617e70021c7c862f207a728","sha256:d6f076239be4e4aa2beca416aec6ebcac2bc72560d1e25eebeb266b0ab91a5b9"],"state_sha256":"59747d5e3011cd4f62188e2603629b19a46d540825f2c3bec7c393d8c93ba430"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eTKivnl7QzpIGt7Y9k6BKJL+hCX+GoBKRW70U2RNOHFN5fBsl+KNgVevrqq8YkD1GxDCbRttILpODLaPdfHaCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T18:59:52.358151Z","bundle_sha256":"3300c831f7a1dd1e5f99deb8712a3b917c454c092844dad936aee7e4f9860603"}}