{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YQWLBDHQWOMYS6J2P4FDYRQYI2","short_pith_number":"pith:YQWLBDHQ","canonical_record":{"source":{"id":"2406.04842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T11:15:03Z","cross_cats_sorted":[],"title_canon_sha256":"2e8f38d15a5331ca3b07750c0fb7e0afdb527d88f3a8ec15ee035d37d5ddff7f","abstract_canon_sha256":"c685eaac647b79795d2b8c6c3c9bd60353dacb186be4a8f30f663647d6dd6ad5"},"schema_version":"1.0"},"canonical_sha256":"c42cb08cf0b39989793a7f0a3c461846aea774147d1c259310bd1be85327fcb2","source":{"kind":"arxiv","id":"2406.04842","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04842","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04842v1","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04842","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_12","alias_value":"YQWLBDHQWOMY","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"YQWLBDHQWOMYS6J2","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"YQWLBDHQ","created_at":"2026-07-05T08:28:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YQWLBDHQWOMYS6J2P4FDYRQYI2","target":"record","payload":{"canonical_record":{"source":{"id":"2406.04842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T11:15:03Z","cross_cats_sorted":[],"title_canon_sha256":"2e8f38d15a5331ca3b07750c0fb7e0afdb527d88f3a8ec15ee035d37d5ddff7f","abstract_canon_sha256":"c685eaac647b79795d2b8c6c3c9bd60353dacb186be4a8f30f663647d6dd6ad5"},"schema_version":"1.0"},"canonical_sha256":"c42cb08cf0b39989793a7f0a3c461846aea774147d1c259310bd1be85327fcb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:49.869037Z","signature_b64":"59BlLFrdskoP1nC8nRUTf9NOpaBKReSbeegTxEUufY5aeMw59/UVaFPLXikIOxkZ7LENtD1vF9oqboUToH7VBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c42cb08cf0b39989793a7f0a3c461846aea774147d1c259310bd1be85327fcb2","last_reissued_at":"2026-07-05T08:28:49.868626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:49.868626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.04842","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":"2026-07-05T08:28:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qyr2gUkihE5y+MgIXGTPh9XPYzQQ8GvXx+QY8eNIJfvhmLjRo0zBS9MFmfmv+47ubsB4WMBGga7kobMABJdLDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T00:18:00.674466Z"},"content_sha256":"efec0d9b7f758185f244b7a53566f62389fada2389a6fcd58403bbbc17d57d12","schema_version":"1.0","event_id":"sha256:efec0d9b7f758185f244b7a53566f62389fada2389a6fcd58403bbbc17d57d12"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YQWLBDHQWOMYS6J2P4FDYRQYI2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"3rd Place Solution for MeViS Track in CVPR 2024 PVUW workshop: Motion Expression guided Video Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feiyu Pan, Hao Fang, Xiankai Lu","submitted_at":"2024-06-07T11:15:03Z","abstract_excerpt":"Referring video object segmentation (RVOS) relies on natural language expressions to segment target objects in video, emphasizing modeling dense text-video relations. The current RVOS methods typically use independently pre-trained vision and language models as backbones, resulting in a significant domain gap between video and text. In cross-modal feature interaction, text features are only used as query initialization and do not fully utilize important information in the text. In this work, we propose using frozen pre-trained vision-language models (VLM) as backbones, with a specific emphasis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04842","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/2406.04842/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":"2026-07-05T08:28:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v9oBhzMTSxGFDM+gLHFftJ5pv4Yws3LCLV/QPgTpskqPl2yQsXH8nLcV6T8GLW1Hw1IYEdSmhHVD9fdx9hdZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T00:18:00.674953Z"},"content_sha256":"58a3a11821a099754cb95e29b8a82ec4fa22bf282abbc6f16f738bf2761c13ac","schema_version":"1.0","event_id":"sha256:58a3a11821a099754cb95e29b8a82ec4fa22bf282abbc6f16f738bf2761c13ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YQWLBDHQWOMYS6J2P4FDYRQYI2/bundle.json","state_url":"https://pith.science/pith/YQWLBDHQWOMYS6J2P4FDYRQYI2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YQWLBDHQWOMYS6J2P4FDYRQYI2/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":"2026-08-01T00:18:00Z","links":{"resolver":"https://pith.science/pith/YQWLBDHQWOMYS6J2P4FDYRQYI2","bundle":"https://pith.science/pith/YQWLBDHQWOMYS6J2P4FDYRQYI2/bundle.json","state":"https://pith.science/pith/YQWLBDHQWOMYS6J2P4FDYRQYI2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YQWLBDHQWOMYS6J2P4FDYRQYI2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YQWLBDHQWOMYS6J2P4FDYRQYI2","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":"c685eaac647b79795d2b8c6c3c9bd60353dacb186be4a8f30f663647d6dd6ad5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T11:15:03Z","title_canon_sha256":"2e8f38d15a5331ca3b07750c0fb7e0afdb527d88f3a8ec15ee035d37d5ddff7f"},"schema_version":"1.0","source":{"id":"2406.04842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04842","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04842v1","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04842","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_12","alias_value":"YQWLBDHQWOMY","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"YQWLBDHQWOMYS6J2","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"YQWLBDHQ","created_at":"2026-07-05T08:28:49Z"}],"graph_snapshots":[{"event_id":"sha256:58a3a11821a099754cb95e29b8a82ec4fa22bf282abbc6f16f738bf2761c13ac","target":"graph","created_at":"2026-07-05T08:28:49Z","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/2406.04842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring video object segmentation (RVOS) relies on natural language expressions to segment target objects in video, emphasizing modeling dense text-video relations. The current RVOS methods typically use independently pre-trained vision and language models as backbones, resulting in a significant domain gap between video and text. In cross-modal feature interaction, text features are only used as query initialization and do not fully utilize important information in the text. In this work, we propose using frozen pre-trained vision-language models (VLM) as backbones, with a specific emphasis","authors_text":"Feiyu Pan, Hao Fang, Xiankai Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T11:15:03Z","title":"3rd Place Solution for MeViS Track in CVPR 2024 PVUW workshop: Motion Expression guided Video Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04842","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:efec0d9b7f758185f244b7a53566f62389fada2389a6fcd58403bbbc17d57d12","target":"record","created_at":"2026-07-05T08:28:49Z","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":"c685eaac647b79795d2b8c6c3c9bd60353dacb186be4a8f30f663647d6dd6ad5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T11:15:03Z","title_canon_sha256":"2e8f38d15a5331ca3b07750c0fb7e0afdb527d88f3a8ec15ee035d37d5ddff7f"},"schema_version":"1.0","source":{"id":"2406.04842","kind":"arxiv","version":1}},"canonical_sha256":"c42cb08cf0b39989793a7f0a3c461846aea774147d1c259310bd1be85327fcb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c42cb08cf0b39989793a7f0a3c461846aea774147d1c259310bd1be85327fcb2","first_computed_at":"2026-07-05T08:28:49.868626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:49.868626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"59BlLFrdskoP1nC8nRUTf9NOpaBKReSbeegTxEUufY5aeMw59/UVaFPLXikIOxkZ7LENtD1vF9oqboUToH7VBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:49.869037Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efec0d9b7f758185f244b7a53566f62389fada2389a6fcd58403bbbc17d57d12","sha256:58a3a11821a099754cb95e29b8a82ec4fa22bf282abbc6f16f738bf2761c13ac"],"state_sha256":"13e91edda08dae9868e94a3e3907d10ad5e9a56e09c8cc7ae9665c7ee7fafb6c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WCPO/OrvRQ1b0ucbXQLLKQmXagHw5I2SXu4sW3S6rG7/sxd0y+FHGp0TQ3BRzu1oqh6tmRNDCP+aGScLvvNtCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T00:18:00.680121Z","bundle_sha256":"b677841cfc142f5cb32f1cb92e46087fa0ec194f50d14b5f618d6230f3269412"}}