{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:3RXEMZZSFIUHZ3A4N57J2MDNC6","short_pith_number":"pith:3RXEMZZS","canonical_record":{"source":{"id":"2210.15871","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-28T03:36:07Z","cross_cats_sorted":[],"title_canon_sha256":"5b84febc7d592a0571b285a451eac104e105f0021bf653fabd5d90b1e143c57e","abstract_canon_sha256":"7b64437995d2f516727a2fce771903a807861b12a1ffda370918075ce3702f1d"},"schema_version":"1.0"},"canonical_sha256":"dc6e4667322a287cec1c6f7e9d306d17a5e9933232af358aba25c0198b0a0bf0","source":{"kind":"arxiv","id":"2210.15871","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.15871","created_at":"2026-07-05T05:19:20Z"},{"alias_kind":"arxiv_version","alias_value":"2210.15871v1","created_at":"2026-07-05T05:19:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15871","created_at":"2026-07-05T05:19:20Z"},{"alias_kind":"pith_short_12","alias_value":"3RXEMZZSFIUH","created_at":"2026-07-05T05:19:20Z"},{"alias_kind":"pith_short_16","alias_value":"3RXEMZZSFIUHZ3A4","created_at":"2026-07-05T05:19:20Z"},{"alias_kind":"pith_short_8","alias_value":"3RXEMZZS","created_at":"2026-07-05T05:19:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:3RXEMZZSFIUHZ3A4N57J2MDNC6","target":"record","payload":{"canonical_record":{"source":{"id":"2210.15871","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-28T03:36:07Z","cross_cats_sorted":[],"title_canon_sha256":"5b84febc7d592a0571b285a451eac104e105f0021bf653fabd5d90b1e143c57e","abstract_canon_sha256":"7b64437995d2f516727a2fce771903a807861b12a1ffda370918075ce3702f1d"},"schema_version":"1.0"},"canonical_sha256":"dc6e4667322a287cec1c6f7e9d306d17a5e9933232af358aba25c0198b0a0bf0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:20.172685Z","signature_b64":"wuAphs9F9cLwzM9We1DvsEaTD9GZwcRXS8jbOJVtWqLCk3twTQwu1FI7pXGHQqXLWgZ+YDfz3zlYlhi5xRlZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc6e4667322a287cec1c6f7e9d306d17a5e9933232af358aba25c0198b0a0bf0","last_reissued_at":"2026-07-05T05:19:20.172223Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:20.172223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.15871","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":"2026-07-05T05:19:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+fn2ut7GRbuT7c/iLpjM/nkfk8hKrz3tiubiAvSjhDwpJXjFjKvoTYTk29cPGWTLR3KxWM7dqp0VTkYaRyFGCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T13:52:38.813299Z"},"content_sha256":"dcf0df726b2940338253962422c1de50b1d3c22d880b9008ca586383bf713f31","schema_version":"1.0","event_id":"sha256:dcf0df726b2940338253962422c1de50b1d3c22d880b9008ca586383bf713f31"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:3RXEMZZSFIUHZ3A4N57J2MDNC6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Liu, Henghui Ding, Suchen Wang, Xudong Jiang","submitted_at":"2022-10-28T03:36:07Z","abstract_excerpt":"We propose a Vision-Language Transformer (VLT) framework for referring segmentation to facilitate deep interactions among multi-modal information and enhance the holistic understanding to vision-language features. There are different ways to understand the dynamic emphasis of a language expression, especially when interacting with the image. However, the learned queries in existing transformer works are fixed after training, which cannot cope with the randomness and huge diversity of the language expressions. To address this issue, we propose a Query Generation Module, which dynamically produc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15871","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/2210.15871/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":"2026-07-05T05:19:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SzBMohvYZmqOuJTr6SXE2RXEmRim+vFCBFxW+kO75fry4JVfMg2KHqlAKQ8HG+o9xT0OZtY7+EfjJCPlRs32Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T13:52:38.813861Z"},"content_sha256":"adc9608fa35113ce57ead9fd18c80d42209445b9c429a383426794ee2e31f18b","schema_version":"1.0","event_id":"sha256:adc9608fa35113ce57ead9fd18c80d42209445b9c429a383426794ee2e31f18b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3RXEMZZSFIUHZ3A4N57J2MDNC6/bundle.json","state_url":"https://pith.science/pith/3RXEMZZSFIUHZ3A4N57J2MDNC6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3RXEMZZSFIUHZ3A4N57J2MDNC6/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":"2026-08-23T13:52:38Z","links":{"resolver":"https://pith.science/pith/3RXEMZZSFIUHZ3A4N57J2MDNC6","bundle":"https://pith.science/pith/3RXEMZZSFIUHZ3A4N57J2MDNC6/bundle.json","state":"https://pith.science/pith/3RXEMZZSFIUHZ3A4N57J2MDNC6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3RXEMZZSFIUHZ3A4N57J2MDNC6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3RXEMZZSFIUHZ3A4N57J2MDNC6","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":"7b64437995d2f516727a2fce771903a807861b12a1ffda370918075ce3702f1d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-28T03:36:07Z","title_canon_sha256":"5b84febc7d592a0571b285a451eac104e105f0021bf653fabd5d90b1e143c57e"},"schema_version":"1.0","source":{"id":"2210.15871","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.15871","created_at":"2026-07-05T05:19:20Z"},{"alias_kind":"arxiv_version","alias_value":"2210.15871v1","created_at":"2026-07-05T05:19:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15871","created_at":"2026-07-05T05:19:20Z"},{"alias_kind":"pith_short_12","alias_value":"3RXEMZZSFIUH","created_at":"2026-07-05T05:19:20Z"},{"alias_kind":"pith_short_16","alias_value":"3RXEMZZSFIUHZ3A4","created_at":"2026-07-05T05:19:20Z"},{"alias_kind":"pith_short_8","alias_value":"3RXEMZZS","created_at":"2026-07-05T05:19:20Z"}],"graph_snapshots":[{"event_id":"sha256:adc9608fa35113ce57ead9fd18c80d42209445b9c429a383426794ee2e31f18b","target":"graph","created_at":"2026-07-05T05:19:20Z","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/2210.15871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a Vision-Language Transformer (VLT) framework for referring segmentation to facilitate deep interactions among multi-modal information and enhance the holistic understanding to vision-language features. There are different ways to understand the dynamic emphasis of a language expression, especially when interacting with the image. However, the learned queries in existing transformer works are fixed after training, which cannot cope with the randomness and huge diversity of the language expressions. To address this issue, we propose a Query Generation Module, which dynamically produc","authors_text":"Chang Liu, Henghui Ding, Suchen Wang, Xudong Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-28T03:36:07Z","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15871","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:dcf0df726b2940338253962422c1de50b1d3c22d880b9008ca586383bf713f31","target":"record","created_at":"2026-07-05T05:19:20Z","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":"7b64437995d2f516727a2fce771903a807861b12a1ffda370918075ce3702f1d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-28T03:36:07Z","title_canon_sha256":"5b84febc7d592a0571b285a451eac104e105f0021bf653fabd5d90b1e143c57e"},"schema_version":"1.0","source":{"id":"2210.15871","kind":"arxiv","version":1}},"canonical_sha256":"dc6e4667322a287cec1c6f7e9d306d17a5e9933232af358aba25c0198b0a0bf0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc6e4667322a287cec1c6f7e9d306d17a5e9933232af358aba25c0198b0a0bf0","first_computed_at":"2026-07-05T05:19:20.172223Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:19:20.172223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wuAphs9F9cLwzM9We1DvsEaTD9GZwcRXS8jbOJVtWqLCk3twTQwu1FI7pXGHQqXLWgZ+YDfz3zlYlhi5xRlZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:19:20.172685Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.15871","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcf0df726b2940338253962422c1de50b1d3c22d880b9008ca586383bf713f31","sha256:adc9608fa35113ce57ead9fd18c80d42209445b9c429a383426794ee2e31f18b"],"state_sha256":"0c6441f86994fc7df132e5454e17768f86947bb2f86dd792fb705e5c8b8ea0ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k7m+psTgRiASkwZvoSsm0AlvYgB6vjzr6K6kqB8Q3RWGW8AnoXWRpTob08RBwboo3iOZBRqh0oDG4VsoLnFWBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T13:52:38.818984Z","bundle_sha256":"168121a3d8dac31c85c62b7df08725af81608f5c6604eaf6a6c44f6faa527900"}}