{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UGF5SUGPMNWBKBCD4Y5FZDNLWZ","short_pith_number":"pith:UGF5SUGP","canonical_record":{"source":{"id":"2504.07962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T17:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"803ac09c8162984ee09db7c1902ae840359df4f6c270a32dda27a4812332aaaa","abstract_canon_sha256":"c9dc915b24106790f3d34c6669650437a98866a31cd332b884101813f96c36ee"},"schema_version":"1.0"},"canonical_sha256":"a18bd950cf636c150443e63a5c8dabb66c78a7a3999d628da1e82b183e21f938","source":{"kind":"arxiv","id":"2504.07962","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07962","created_at":"2026-07-05T10:47:22Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07962v1","created_at":"2026-07-05T10:47:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07962","created_at":"2026-07-05T10:47:22Z"},{"alias_kind":"pith_short_12","alias_value":"UGF5SUGPMNWB","created_at":"2026-07-05T10:47:22Z"},{"alias_kind":"pith_short_16","alias_value":"UGF5SUGPMNWBKBCD","created_at":"2026-07-05T10:47:22Z"},{"alias_kind":"pith_short_8","alias_value":"UGF5SUGP","created_at":"2026-07-05T10:47:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UGF5SUGPMNWBKBCD4Y5FZDNLWZ","target":"record","payload":{"canonical_record":{"source":{"id":"2504.07962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T17:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"803ac09c8162984ee09db7c1902ae840359df4f6c270a32dda27a4812332aaaa","abstract_canon_sha256":"c9dc915b24106790f3d34c6669650437a98866a31cd332b884101813f96c36ee"},"schema_version":"1.0"},"canonical_sha256":"a18bd950cf636c150443e63a5c8dabb66c78a7a3999d628da1e82b183e21f938","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:22.641628Z","signature_b64":"eivODNItXE5b8xlD+Nw2wznoX8uDR5AztXYFl8xGRfTzq8/FgdOsdYZuvjZAYJe26zAWGxfkL83MG3Npul+VAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a18bd950cf636c150443e63a5c8dabb66c78a7a3999d628da1e82b183e21f938","last_reissued_at":"2026-07-05T10:47:22.641191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:22.641191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.07962","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":"2026-07-05T10:47:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vGdNZHdPHvTysZ4r7NAjIuoFSTrwjT75CVzfutO+Pi6fIjbiOYYXl+5hVrJqn8UtGcstshiE/R++9uNsJJZPDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:32:15.599949Z"},"content_sha256":"ac8e297602423eb77f862b45a4aeeb7f9a3cb3d54f65ffc130edbfa379f8cf44","schema_version":"1.0","event_id":"sha256:ac8e297602423eb77f862b45a4aeeb7f9a3cb3d54f65ffc130edbfa379f8cf44"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UGF5SUGPMNWBKBCD4Y5FZDNLWZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lang Lin, Xueyang Yu, Yu-Xiong Wang, Ziqi Pang","submitted_at":"2025-04-10T17:59:55Z","abstract_excerpt":"This paper proposes a novel framework utilizing multi-modal large language models (MLLMs) for referring video object segmentation (RefVOS). Previous MLLM-based methods commonly struggle with the dilemma between \"Ref\" and \"VOS\": they either specialize in understanding a few key frames (global reasoning) or tracking objects on continuous frames (local reasoning), and rely on external VOS or frame selectors to mitigate the other end of the challenge. However, our framework GLUS shows that global and local consistency can be unified into a single video segmentation MLLM: a set of sparse \"context f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07962","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/2504.07962/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":"2026-07-05T10:47:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F+4y9cPm9Umrthh0TLYlwju5SSCUHtrLuJ2REyK09DOKb8Q4TfI+8aARkG+lHpIAWdd1de1g1pMf6UW98WlbCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:32:15.600350Z"},"content_sha256":"942aa27bc624f374122be226bdb9ae83d3eda928dae8564a568c7b91bd9cc68f","schema_version":"1.0","event_id":"sha256:942aa27bc624f374122be226bdb9ae83d3eda928dae8564a568c7b91bd9cc68f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UGF5SUGPMNWBKBCD4Y5FZDNLWZ/bundle.json","state_url":"https://pith.science/pith/UGF5SUGPMNWBKBCD4Y5FZDNLWZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UGF5SUGPMNWBKBCD4Y5FZDNLWZ/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":"2026-08-06T03:32:15Z","links":{"resolver":"https://pith.science/pith/UGF5SUGPMNWBKBCD4Y5FZDNLWZ","bundle":"https://pith.science/pith/UGF5SUGPMNWBKBCD4Y5FZDNLWZ/bundle.json","state":"https://pith.science/pith/UGF5SUGPMNWBKBCD4Y5FZDNLWZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UGF5SUGPMNWBKBCD4Y5FZDNLWZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UGF5SUGPMNWBKBCD4Y5FZDNLWZ","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":"c9dc915b24106790f3d34c6669650437a98866a31cd332b884101813f96c36ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T17:59:55Z","title_canon_sha256":"803ac09c8162984ee09db7c1902ae840359df4f6c270a32dda27a4812332aaaa"},"schema_version":"1.0","source":{"id":"2504.07962","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07962","created_at":"2026-07-05T10:47:22Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07962v1","created_at":"2026-07-05T10:47:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07962","created_at":"2026-07-05T10:47:22Z"},{"alias_kind":"pith_short_12","alias_value":"UGF5SUGPMNWB","created_at":"2026-07-05T10:47:22Z"},{"alias_kind":"pith_short_16","alias_value":"UGF5SUGPMNWBKBCD","created_at":"2026-07-05T10:47:22Z"},{"alias_kind":"pith_short_8","alias_value":"UGF5SUGP","created_at":"2026-07-05T10:47:22Z"}],"graph_snapshots":[{"event_id":"sha256:942aa27bc624f374122be226bdb9ae83d3eda928dae8564a568c7b91bd9cc68f","target":"graph","created_at":"2026-07-05T10:47:22Z","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/2504.07962/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a novel framework utilizing multi-modal large language models (MLLMs) for referring video object segmentation (RefVOS). Previous MLLM-based methods commonly struggle with the dilemma between \"Ref\" and \"VOS\": they either specialize in understanding a few key frames (global reasoning) or tracking objects on continuous frames (local reasoning), and rely on external VOS or frame selectors to mitigate the other end of the challenge. However, our framework GLUS shows that global and local consistency can be unified into a single video segmentation MLLM: a set of sparse \"context f","authors_text":"Lang Lin, Xueyang Yu, Yu-Xiong Wang, Ziqi Pang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T17:59:55Z","title":"GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07962","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:ac8e297602423eb77f862b45a4aeeb7f9a3cb3d54f65ffc130edbfa379f8cf44","target":"record","created_at":"2026-07-05T10:47:22Z","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":"c9dc915b24106790f3d34c6669650437a98866a31cd332b884101813f96c36ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T17:59:55Z","title_canon_sha256":"803ac09c8162984ee09db7c1902ae840359df4f6c270a32dda27a4812332aaaa"},"schema_version":"1.0","source":{"id":"2504.07962","kind":"arxiv","version":1}},"canonical_sha256":"a18bd950cf636c150443e63a5c8dabb66c78a7a3999d628da1e82b183e21f938","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a18bd950cf636c150443e63a5c8dabb66c78a7a3999d628da1e82b183e21f938","first_computed_at":"2026-07-05T10:47:22.641191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:22.641191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eivODNItXE5b8xlD+Nw2wznoX8uDR5AztXYFl8xGRfTzq8/FgdOsdYZuvjZAYJe26zAWGxfkL83MG3Npul+VAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:22.641628Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07962","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac8e297602423eb77f862b45a4aeeb7f9a3cb3d54f65ffc130edbfa379f8cf44","sha256:942aa27bc624f374122be226bdb9ae83d3eda928dae8564a568c7b91bd9cc68f"],"state_sha256":"133b406eb2c3a964c8e65de370c66719dc82d2df5ea3186e58bca6e064730cb3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pWw/+H6Uv94QF2z/Y9bs2OGhlKjIGbGyzeJMIfD5TsOAVOcqolzxuQmtpmNBMppR6Y71sFRb+0SvAe6b2rC1AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:32:15.604749Z","bundle_sha256":"1af7026ad147ebf4a1041e8bb70ee5e1599837669e12d10d1c1bcdfbc8197feb"}}