{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RTS7P2PISXO44LLGLPYK4L4ULW","short_pith_number":"pith:RTS7P2PI","canonical_record":{"source":{"id":"2411.17606","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T17:18:20Z","cross_cats_sorted":[],"title_canon_sha256":"bb9214a2d0e6d1282c5d36936bd7116e0d7b1a693b7e650e6413e4db254117a2","abstract_canon_sha256":"0b2758e2a7bb5db940c9762997aac11178310cddd16010f9a13c7e18b9056c13"},"schema_version":"1.0"},"canonical_sha256":"8ce5f7e9e895ddce2d665bf0ae2f945d8eb8c506cea1befc973125934a8b4c74","source":{"kind":"arxiv","id":"2411.17606","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17606","created_at":"2026-07-05T09:42:33Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17606v2","created_at":"2026-07-05T09:42:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17606","created_at":"2026-07-05T09:42:33Z"},{"alias_kind":"pith_short_12","alias_value":"RTS7P2PISXO4","created_at":"2026-07-05T09:42:33Z"},{"alias_kind":"pith_short_16","alias_value":"RTS7P2PISXO44LLG","created_at":"2026-07-05T09:42:33Z"},{"alias_kind":"pith_short_8","alias_value":"RTS7P2PI","created_at":"2026-07-05T09:42:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RTS7P2PISXO44LLGLPYK4L4ULW","target":"record","payload":{"canonical_record":{"source":{"id":"2411.17606","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T17:18:20Z","cross_cats_sorted":[],"title_canon_sha256":"bb9214a2d0e6d1282c5d36936bd7116e0d7b1a693b7e650e6413e4db254117a2","abstract_canon_sha256":"0b2758e2a7bb5db940c9762997aac11178310cddd16010f9a13c7e18b9056c13"},"schema_version":"1.0"},"canonical_sha256":"8ce5f7e9e895ddce2d665bf0ae2f945d8eb8c506cea1befc973125934a8b4c74","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:33.778570Z","signature_b64":"HysvLwHoOBUwPdPW8dDMRH52TcDPWR1aTju0f4TezpXgzrIegGTS07zuJfeT1+05ZgPvTY+3vOthGEfW89CFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ce5f7e9e895ddce2d665bf0ae2f945d8eb8c506cea1befc973125934a8b4c74","last_reissued_at":"2026-07-05T09:42:33.778029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:33.778029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.17606","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":"2026-07-05T09:42:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8kLuE2LP03Kr/39F4m7EHGicAthBm5pB1+MsojUkp46iD+4pR78p+aaIGE8BqxNEz3bRc2UNXpUkyC1nASwJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:52:23.032157Z"},"content_sha256":"58d85ab626f858e83da1e7aa33af54e4e51ac510f6a92264176dfb69f61d0b7e","schema_version":"1.0","event_id":"sha256:58d85ab626f858e83da1e7aa33af54e4e51ac510f6a92264176dfb69f61d0b7e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RTS7P2PISXO44LLGLPYK4L4ULW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Wei, Haoxian Tan, Jie Hu, Yong Liu, Yujie Zhong, Yujiu Yang, Zheng Zhao","submitted_at":"2024-11-26T17:18:20Z","abstract_excerpt":"This paper aims to address universal segmentation for image and video perception with the strong reasoning ability empowered by Visual Large Language Models (VLLMs). Despite significant progress in current unified segmentation methods, limitations in adaptation to both image and video scenarios, as well as the complex reasoning segmentation, make it difficult for them to handle various challenging instructions and achieve an accurate understanding of fine-grained vision-language correlations. We propose HyperSeg, the first VLLM-based universal segmentation model for pixel-level image and video"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17606","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/2411.17606/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":"2026-07-05T09:42:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SEejIMEM69i0pUzaKPCAWWSh02QfAKc27ZlF5btXtwGrStojutwQEubNziBzr46W+J63uZE5yAr3pu7nePGKAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:52:23.032929Z"},"content_sha256":"4481b0bd8d8bcfee96add5e27e4e7e0067654377384319f8c2b5d73be69feef9","schema_version":"1.0","event_id":"sha256:4481b0bd8d8bcfee96add5e27e4e7e0067654377384319f8c2b5d73be69feef9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RTS7P2PISXO44LLGLPYK4L4ULW/bundle.json","state_url":"https://pith.science/pith/RTS7P2PISXO44LLGLPYK4L4ULW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RTS7P2PISXO44LLGLPYK4L4ULW/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":"2026-08-06T18:52:23Z","links":{"resolver":"https://pith.science/pith/RTS7P2PISXO44LLGLPYK4L4ULW","bundle":"https://pith.science/pith/RTS7P2PISXO44LLGLPYK4L4ULW/bundle.json","state":"https://pith.science/pith/RTS7P2PISXO44LLGLPYK4L4ULW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RTS7P2PISXO44LLGLPYK4L4ULW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RTS7P2PISXO44LLGLPYK4L4ULW","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":"0b2758e2a7bb5db940c9762997aac11178310cddd16010f9a13c7e18b9056c13","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T17:18:20Z","title_canon_sha256":"bb9214a2d0e6d1282c5d36936bd7116e0d7b1a693b7e650e6413e4db254117a2"},"schema_version":"1.0","source":{"id":"2411.17606","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17606","created_at":"2026-07-05T09:42:33Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17606v2","created_at":"2026-07-05T09:42:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17606","created_at":"2026-07-05T09:42:33Z"},{"alias_kind":"pith_short_12","alias_value":"RTS7P2PISXO4","created_at":"2026-07-05T09:42:33Z"},{"alias_kind":"pith_short_16","alias_value":"RTS7P2PISXO44LLG","created_at":"2026-07-05T09:42:33Z"},{"alias_kind":"pith_short_8","alias_value":"RTS7P2PI","created_at":"2026-07-05T09:42:33Z"}],"graph_snapshots":[{"event_id":"sha256:4481b0bd8d8bcfee96add5e27e4e7e0067654377384319f8c2b5d73be69feef9","target":"graph","created_at":"2026-07-05T09:42:33Z","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/2411.17606/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper aims to address universal segmentation for image and video perception with the strong reasoning ability empowered by Visual Large Language Models (VLLMs). Despite significant progress in current unified segmentation methods, limitations in adaptation to both image and video scenarios, as well as the complex reasoning segmentation, make it difficult for them to handle various challenging instructions and achieve an accurate understanding of fine-grained vision-language correlations. We propose HyperSeg, the first VLLM-based universal segmentation model for pixel-level image and video","authors_text":"Cong Wei, Haoxian Tan, Jie Hu, Yong Liu, Yujie Zhong, Yujiu Yang, Zheng Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T17:18:20Z","title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17606","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":"sha256:58d85ab626f858e83da1e7aa33af54e4e51ac510f6a92264176dfb69f61d0b7e","target":"record","created_at":"2026-07-05T09:42:33Z","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":"0b2758e2a7bb5db940c9762997aac11178310cddd16010f9a13c7e18b9056c13","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T17:18:20Z","title_canon_sha256":"bb9214a2d0e6d1282c5d36936bd7116e0d7b1a693b7e650e6413e4db254117a2"},"schema_version":"1.0","source":{"id":"2411.17606","kind":"arxiv","version":2}},"canonical_sha256":"8ce5f7e9e895ddce2d665bf0ae2f945d8eb8c506cea1befc973125934a8b4c74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ce5f7e9e895ddce2d665bf0ae2f945d8eb8c506cea1befc973125934a8b4c74","first_computed_at":"2026-07-05T09:42:33.778029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:33.778029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HysvLwHoOBUwPdPW8dDMRH52TcDPWR1aTju0f4TezpXgzrIegGTS07zuJfeT1+05ZgPvTY+3vOthGEfW89CFCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:33.778570Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17606","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58d85ab626f858e83da1e7aa33af54e4e51ac510f6a92264176dfb69f61d0b7e","sha256:4481b0bd8d8bcfee96add5e27e4e7e0067654377384319f8c2b5d73be69feef9"],"state_sha256":"f294def4ca3ecf2a74f4c44d4130aa097cd640528ef7cc4a8827c0b85ede2e84"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jad4bhnGyrXk4KvT4b5e/Kazfia2WjEhgLHmS2RDdKcoPBGPgsgmQDMmzq7JZP0elB1ezSQZSMBVmUWdRXIlCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:52:23.040055Z","bundle_sha256":"d30796ae2a80b47a81cdde1ba89515656e1cf1cb7ebe409684a8e8655d0c4ed8"}}