{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZAO6QCLLAV72XTWLGCDX6TW3XR","short_pith_number":"pith:ZAO6QCLL","canonical_record":{"source":{"id":"2201.00487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-03T05:54:00Z","cross_cats_sorted":[],"title_canon_sha256":"2bc59cff8ff3cfd5c3581cf26553cded3744eb8d7c81501de09821db9f8f49d6","abstract_canon_sha256":"dcf30ea808ab98cb9d695bc3e384e72d01f00e57fab51a38e175a99ccd140c2e"},"schema_version":"1.0"},"canonical_sha256":"c81de8096b057fabcecb30877f4edbbc405d6388b1ca32e6919b53bb84625c3a","source":{"kind":"arxiv","id":"2201.00487","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.00487","created_at":"2026-07-05T04:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2201.00487v2","created_at":"2026-07-05T04:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.00487","created_at":"2026-07-05T04:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZAO6QCLLAV72","created_at":"2026-07-05T04:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZAO6QCLLAV72XTWL","created_at":"2026-07-05T04:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZAO6QCLL","created_at":"2026-07-05T04:04:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZAO6QCLLAV72XTWLGCDX6TW3XR","target":"record","payload":{"canonical_record":{"source":{"id":"2201.00487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-03T05:54:00Z","cross_cats_sorted":[],"title_canon_sha256":"2bc59cff8ff3cfd5c3581cf26553cded3744eb8d7c81501de09821db9f8f49d6","abstract_canon_sha256":"dcf30ea808ab98cb9d695bc3e384e72d01f00e57fab51a38e175a99ccd140c2e"},"schema_version":"1.0"},"canonical_sha256":"c81de8096b057fabcecb30877f4edbbc405d6388b1ca32e6919b53bb84625c3a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:44.666957Z","signature_b64":"XNaHxDasiPgI+quraEnlze4ZRC7L6LR4UvCGelBYdnpsQ1RtLF1T7sJs97hU9/lsv6ggy1nhqCHHtCMO2XwnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c81de8096b057fabcecb30877f4edbbc405d6388b1ca32e6919b53bb84625c3a","last_reissued_at":"2026-07-05T04:04:44.666428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:44.666428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.00487","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":"2026-07-05T04:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bxtvIa72z1rTFB7WveMFpjJYDPUSsVgC2m3BBi1vpiav6MTi+IueZOkuj2w4OD4Mbd3FKNv3uSUqIlz6HB9vBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:51:59.859699Z"},"content_sha256":"1bf53502bd46883de654e9fbc495b34b30ca657a06eb571b8fa1007ee6cc502c","schema_version":"1.0","event_id":"sha256:1bf53502bd46883de654e9fbc495b34b30ca657a06eb571b8fa1007ee6cc502c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZAO6QCLLAV72XTWLGCDX6TW3XR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language as Queries for Referring Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiannan Wu, Peize Sun, Ping Luo, Yi Jiang, Zehuan Yuan","submitted_at":"2022-01-03T05:54:00Z","abstract_excerpt":"Referring video object segmentation (R-VOS) is an emerging cross-modal task that aims to segment the target object referred by a language expression in all video frames. In this work, we propose a simple and unified framework built upon Transformer, termed ReferFormer. It views the language as queries and directly attends to the most relevant regions in the video frames. Concretely, we introduce a small set of object queries conditioned on the language as the input to the Transformer. In this manner, all the queries are obligated to find the referred objects only. They are eventually transform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.00487","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/2201.00487/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":"2026-07-05T04:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mAOKdsul+PGMn1ZwEVPhIyGUOd6peNhnNARnAMZysnAwdHmQ+8M5F9LKk8sbFHKePFBuED2ZzGjjN0mg+o8tBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:51:59.860212Z"},"content_sha256":"0cdd1342e45a8e461b1bf7873304894a432c53d9aaa61066b79ccffe1c1429dd","schema_version":"1.0","event_id":"sha256:0cdd1342e45a8e461b1bf7873304894a432c53d9aaa61066b79ccffe1c1429dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZAO6QCLLAV72XTWLGCDX6TW3XR/bundle.json","state_url":"https://pith.science/pith/ZAO6QCLLAV72XTWLGCDX6TW3XR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZAO6QCLLAV72XTWLGCDX6TW3XR/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":"2026-08-06T21:51:59Z","links":{"resolver":"https://pith.science/pith/ZAO6QCLLAV72XTWLGCDX6TW3XR","bundle":"https://pith.science/pith/ZAO6QCLLAV72XTWLGCDX6TW3XR/bundle.json","state":"https://pith.science/pith/ZAO6QCLLAV72XTWLGCDX6TW3XR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZAO6QCLLAV72XTWLGCDX6TW3XR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZAO6QCLLAV72XTWLGCDX6TW3XR","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":"dcf30ea808ab98cb9d695bc3e384e72d01f00e57fab51a38e175a99ccd140c2e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-03T05:54:00Z","title_canon_sha256":"2bc59cff8ff3cfd5c3581cf26553cded3744eb8d7c81501de09821db9f8f49d6"},"schema_version":"1.0","source":{"id":"2201.00487","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.00487","created_at":"2026-07-05T04:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2201.00487v2","created_at":"2026-07-05T04:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.00487","created_at":"2026-07-05T04:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZAO6QCLLAV72","created_at":"2026-07-05T04:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZAO6QCLLAV72XTWL","created_at":"2026-07-05T04:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZAO6QCLL","created_at":"2026-07-05T04:04:44Z"}],"graph_snapshots":[{"event_id":"sha256:0cdd1342e45a8e461b1bf7873304894a432c53d9aaa61066b79ccffe1c1429dd","target":"graph","created_at":"2026-07-05T04:04:44Z","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/2201.00487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring video object segmentation (R-VOS) is an emerging cross-modal task that aims to segment the target object referred by a language expression in all video frames. In this work, we propose a simple and unified framework built upon Transformer, termed ReferFormer. It views the language as queries and directly attends to the most relevant regions in the video frames. Concretely, we introduce a small set of object queries conditioned on the language as the input to the Transformer. In this manner, all the queries are obligated to find the referred objects only. They are eventually transform","authors_text":"Jiannan Wu, Peize Sun, Ping Luo, Yi Jiang, Zehuan Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-03T05:54:00Z","title":"Language as Queries for Referring Video Object Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.00487","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":"sha256:1bf53502bd46883de654e9fbc495b34b30ca657a06eb571b8fa1007ee6cc502c","target":"record","created_at":"2026-07-05T04:04:44Z","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":"dcf30ea808ab98cb9d695bc3e384e72d01f00e57fab51a38e175a99ccd140c2e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-03T05:54:00Z","title_canon_sha256":"2bc59cff8ff3cfd5c3581cf26553cded3744eb8d7c81501de09821db9f8f49d6"},"schema_version":"1.0","source":{"id":"2201.00487","kind":"arxiv","version":2}},"canonical_sha256":"c81de8096b057fabcecb30877f4edbbc405d6388b1ca32e6919b53bb84625c3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c81de8096b057fabcecb30877f4edbbc405d6388b1ca32e6919b53bb84625c3a","first_computed_at":"2026-07-05T04:04:44.666428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:04:44.666428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XNaHxDasiPgI+quraEnlze4ZRC7L6LR4UvCGelBYdnpsQ1RtLF1T7sJs97hU9/lsv6ggy1nhqCHHtCMO2XwnDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:04:44.666957Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.00487","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bf53502bd46883de654e9fbc495b34b30ca657a06eb571b8fa1007ee6cc502c","sha256:0cdd1342e45a8e461b1bf7873304894a432c53d9aaa61066b79ccffe1c1429dd"],"state_sha256":"ac7f9b37acb23ad63458ab7baba47bcb05724f23feae6b4d031059d8ebac1d7b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CG/I4SOR8fMazVSVOGdZx/NsOUbtTo6jjbx8WfS80ETBkViVBIUcSSEfH6f8ZomhQcwTV78s0Wpd0pIOqWwdAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:51:59.863999Z","bundle_sha256":"17250ad47a0b03a7bed1b1e390a2200956dba181eba5f7a45b3614b06bb39e95"}}