{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:K47PZOVVPL5D6NWFKROGOO2BAU","short_pith_number":"pith:K47PZOVV","canonical_record":{"source":{"id":"2306.03899","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-06T17:57:49Z","cross_cats_sorted":[],"title_canon_sha256":"765ce1ecb69d836bd214750c103d12f74ab244c2007af836d9a8139489867e10","abstract_canon_sha256":"7be7795c949911bb04d13b6b09d1d2cc061e03a5bc4b697ff17becbe83b88214"},"schema_version":"1.0"},"canonical_sha256":"573efcbab57afa3f36c5545c673b41052ec8b64e819d116fa9d7183913203ee4","source":{"kind":"arxiv","id":"2306.03899","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.03899","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"arxiv_version","alias_value":"2306.03899v2","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03899","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"pith_short_12","alias_value":"K47PZOVVPL5D","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"pith_short_16","alias_value":"K47PZOVVPL5D6NWF","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"pith_short_8","alias_value":"K47PZOVV","created_at":"2026-07-05T07:06:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:K47PZOVVPL5D6NWFKROGOO2BAU","target":"record","payload":{"canonical_record":{"source":{"id":"2306.03899","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-06T17:57:49Z","cross_cats_sorted":[],"title_canon_sha256":"765ce1ecb69d836bd214750c103d12f74ab244c2007af836d9a8139489867e10","abstract_canon_sha256":"7be7795c949911bb04d13b6b09d1d2cc061e03a5bc4b697ff17becbe83b88214"},"schema_version":"1.0"},"canonical_sha256":"573efcbab57afa3f36c5545c673b41052ec8b64e819d116fa9d7183913203ee4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:29.482690Z","signature_b64":"BRrmP5XPYtsTjWI8Icy5RiMFX9gCdj9e9bWVgwvrEfnYmJoGoHLp10VX1Uj2bZY97lX6DjkfswVyqrMTnN6ICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"573efcbab57afa3f36c5545c673b41052ec8b64e819d116fa9d7183913203ee4","last_reissued_at":"2026-07-05T07:06:29.482207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:29.482207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.03899","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":"2026-07-05T07:06:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iPguRJ9Wv/XKVTphwPaoRVvMcKpuXrruSRCWSYdK7GcckCcwfjQ+aVVpH7bCCvK5HVQ1BCm277Yi/kNghJdQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T17:19:05.817433Z"},"content_sha256":"bd2b300866ed1122b06d63b0bb5d09b6deac24769c42fb1116324714a78d2340","schema_version":"1.0","event_id":"sha256:bd2b300866ed1122b06d63b0bb5d09b6deac24769c42fb1116324714a78d2340"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:K47PZOVVPL5D6NWFKROGOO2BAU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Label-free Scene Understanding by Vision Foundation Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lingdong Kong, Nenglun Chen, Runnan Chen, Tongliang Liu, Wenping Wang, Xinge Zhu, Youquan Liu, Yuexin Ma","submitted_at":"2023-06-06T17:57:49Z","abstract_excerpt":"Vision foundation models such as Contrastive Vision-Language Pre-training (CLIP) and Segment Anything (SAM) have demonstrated impressive zero-shot performance on image classification and segmentation tasks. However, the incorporation of CLIP and SAM for label-free scene understanding has yet to be explored. In this paper, we investigate the potential of vision foundation models in enabling networks to comprehend 2D and 3D worlds without labelled data. The primary challenge lies in effectively supervising networks under extremely noisy pseudo labels, which are generated by CLIP and further exac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03899","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/2306.03899/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":"2026-07-05T07:06:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hn0Tyu9tlNwgSYR9IS+9iSBdbB2Unv9PnMYJoa2Cd8dLwTxTWxeUoaXXQEH/OqJsBmkVAKhpJJf+IR1/e3lBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T17:19:05.817808Z"},"content_sha256":"3904c943d158895f7863db2cd1f7017678fcb1671fd850fed8b45ebcdc4f9f0a","schema_version":"1.0","event_id":"sha256:3904c943d158895f7863db2cd1f7017678fcb1671fd850fed8b45ebcdc4f9f0a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K47PZOVVPL5D6NWFKROGOO2BAU/bundle.json","state_url":"https://pith.science/pith/K47PZOVVPL5D6NWFKROGOO2BAU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K47PZOVVPL5D6NWFKROGOO2BAU/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":"2026-07-08T17:19:05Z","links":{"resolver":"https://pith.science/pith/K47PZOVVPL5D6NWFKROGOO2BAU","bundle":"https://pith.science/pith/K47PZOVVPL5D6NWFKROGOO2BAU/bundle.json","state":"https://pith.science/pith/K47PZOVVPL5D6NWFKROGOO2BAU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K47PZOVVPL5D6NWFKROGOO2BAU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:K47PZOVVPL5D6NWFKROGOO2BAU","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":"7be7795c949911bb04d13b6b09d1d2cc061e03a5bc4b697ff17becbe83b88214","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-06T17:57:49Z","title_canon_sha256":"765ce1ecb69d836bd214750c103d12f74ab244c2007af836d9a8139489867e10"},"schema_version":"1.0","source":{"id":"2306.03899","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.03899","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"arxiv_version","alias_value":"2306.03899v2","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03899","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"pith_short_12","alias_value":"K47PZOVVPL5D","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"pith_short_16","alias_value":"K47PZOVVPL5D6NWF","created_at":"2026-07-05T07:06:29Z"},{"alias_kind":"pith_short_8","alias_value":"K47PZOVV","created_at":"2026-07-05T07:06:29Z"}],"graph_snapshots":[{"event_id":"sha256:3904c943d158895f7863db2cd1f7017678fcb1671fd850fed8b45ebcdc4f9f0a","target":"graph","created_at":"2026-07-05T07:06:29Z","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/2306.03899/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision foundation models such as Contrastive Vision-Language Pre-training (CLIP) and Segment Anything (SAM) have demonstrated impressive zero-shot performance on image classification and segmentation tasks. However, the incorporation of CLIP and SAM for label-free scene understanding has yet to be explored. In this paper, we investigate the potential of vision foundation models in enabling networks to comprehend 2D and 3D worlds without labelled data. The primary challenge lies in effectively supervising networks under extremely noisy pseudo labels, which are generated by CLIP and further exac","authors_text":"Lingdong Kong, Nenglun Chen, Runnan Chen, Tongliang Liu, Wenping Wang, Xinge Zhu, Youquan Liu, Yuexin Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-06T17:57:49Z","title":"Towards Label-free Scene Understanding by Vision Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03899","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:bd2b300866ed1122b06d63b0bb5d09b6deac24769c42fb1116324714a78d2340","target":"record","created_at":"2026-07-05T07:06:29Z","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":"7be7795c949911bb04d13b6b09d1d2cc061e03a5bc4b697ff17becbe83b88214","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-06T17:57:49Z","title_canon_sha256":"765ce1ecb69d836bd214750c103d12f74ab244c2007af836d9a8139489867e10"},"schema_version":"1.0","source":{"id":"2306.03899","kind":"arxiv","version":2}},"canonical_sha256":"573efcbab57afa3f36c5545c673b41052ec8b64e819d116fa9d7183913203ee4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"573efcbab57afa3f36c5545c673b41052ec8b64e819d116fa9d7183913203ee4","first_computed_at":"2026-07-05T07:06:29.482207Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:29.482207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BRrmP5XPYtsTjWI8Icy5RiMFX9gCdj9e9bWVgwvrEfnYmJoGoHLp10VX1Uj2bZY97lX6DjkfswVyqrMTnN6ICg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:29.482690Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.03899","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd2b300866ed1122b06d63b0bb5d09b6deac24769c42fb1116324714a78d2340","sha256:3904c943d158895f7863db2cd1f7017678fcb1671fd850fed8b45ebcdc4f9f0a"],"state_sha256":"eda81b22af9ff24186bbc3acbff712e4b1f49f2966a9b5b7602bfb44d71cb43b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aL+hZIzQdASehc0yjCEheWVNI9oI9jDCmY3xk4/9xI09HCt8qdAoOBcA8JsGmeFiB4qBF0ykADo3ZGrT9SXEDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T17:19:05.819908Z","bundle_sha256":"4d20bcc7474345b05c9bf221694b7e9b67f1c59251cfd74e4430ab2aeebf6caf"}}