{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WC6O7FEXY4EC3SURIRNML75JON","short_pith_number":"pith:WC6O7FEX","canonical_record":{"source":{"id":"2112.02244","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-04T04:53:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e9b675e8fa127f3a1ff1adc2568ea58de7cc43abe3da094c003dfe0c4c8fa0bc","abstract_canon_sha256":"b99a83b561d0698af4e41c992b63370790f06e95ce801f24094ed0a47f10c44b"},"schema_version":"1.0"},"canonical_sha256":"b0bcef9497c7082dca91445ac5ffa973609b48c041c57fba31d0bb3ac3d0cbc7","source":{"kind":"arxiv","id":"2112.02244","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.02244","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"arxiv_version","alias_value":"2112.02244v2","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02244","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"pith_short_12","alias_value":"WC6O7FEXY4EC","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"pith_short_16","alias_value":"WC6O7FEXY4EC3SUR","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"pith_short_8","alias_value":"WC6O7FEX","created_at":"2026-07-05T04:12:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WC6O7FEXY4EC3SURIRNML75JON","target":"record","payload":{"canonical_record":{"source":{"id":"2112.02244","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-04T04:53:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e9b675e8fa127f3a1ff1adc2568ea58de7cc43abe3da094c003dfe0c4c8fa0bc","abstract_canon_sha256":"b99a83b561d0698af4e41c992b63370790f06e95ce801f24094ed0a47f10c44b"},"schema_version":"1.0"},"canonical_sha256":"b0bcef9497c7082dca91445ac5ffa973609b48c041c57fba31d0bb3ac3d0cbc7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:05.249946Z","signature_b64":"b6n4CNr8FxxHM156927PZ7bcp5GFlqhYwhJt2k7FrhWaeG6toXK6sZj+c3uQVTM9cGpuEuRhbu2po6srvwi/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0bcef9497c7082dca91445ac5ffa973609b48c041c57fba31d0bb3ac3d0cbc7","last_reissued_at":"2026-07-05T04:12:05.249451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:05.249451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.02244","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":"2026-07-05T04:12:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JY5lwjRjtjS+7V3Hp7ru6YyV3elUKqg4/4xegbfQRHsEbHybIYfZ5NWIkdMAMGoSh/42kTa8Kkm22dI47R1+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T19:49:09.263318Z"},"content_sha256":"c38af8790a04d5873560e05437cba9573587b7117ee0c25cc9f3730e1e670c6d","schema_version":"1.0","event_id":"sha256:c38af8790a04d5873560e05437cba9573587b7117ee0c25cc9f3730e1e670c6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WC6O7FEXY4EC3SURIRNML75JON","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hengshuang Zhao, Jiaqi Wang, Kai Chen, Philip H.S. Torr, Yansong Tang, Zhao Yang","submitted_at":"2021-12-04T04:53:35Z","abstract_excerpt":"Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image. One of the key challenges behind this task is leveraging the referring expression for highlighting relevant positions in the image. A paradigm for tackling this problem is to leverage a powerful vision-language (\"cross-modal\") decoder to fuse features independently extracted from a vision encoder and a language encoder. Recent methods have made remarkable advancements in this paradigm by exploiting Transformers as cross-modal decoders"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02244","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/2112.02244/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":"2026-07-05T04:12:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DTv4ryiYjBz9TQ7w/E0rmwloGUWYpSiwEyBVgW4rOXwU96xECdH4QJSWVTnezn/EewjbyhB1QOygtuTQlPrNBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T19:49:09.263933Z"},"content_sha256":"2f4267aa0377304aafce81d022869c0e2e9f294bdfa31306d18fb21ded20a3a1","schema_version":"1.0","event_id":"sha256:2f4267aa0377304aafce81d022869c0e2e9f294bdfa31306d18fb21ded20a3a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WC6O7FEXY4EC3SURIRNML75JON/bundle.json","state_url":"https://pith.science/pith/WC6O7FEXY4EC3SURIRNML75JON/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WC6O7FEXY4EC3SURIRNML75JON/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":"2026-08-17T19:49:09Z","links":{"resolver":"https://pith.science/pith/WC6O7FEXY4EC3SURIRNML75JON","bundle":"https://pith.science/pith/WC6O7FEXY4EC3SURIRNML75JON/bundle.json","state":"https://pith.science/pith/WC6O7FEXY4EC3SURIRNML75JON/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WC6O7FEXY4EC3SURIRNML75JON/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WC6O7FEXY4EC3SURIRNML75JON","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":"b99a83b561d0698af4e41c992b63370790f06e95ce801f24094ed0a47f10c44b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-04T04:53:35Z","title_canon_sha256":"e9b675e8fa127f3a1ff1adc2568ea58de7cc43abe3da094c003dfe0c4c8fa0bc"},"schema_version":"1.0","source":{"id":"2112.02244","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.02244","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"arxiv_version","alias_value":"2112.02244v2","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02244","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"pith_short_12","alias_value":"WC6O7FEXY4EC","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"pith_short_16","alias_value":"WC6O7FEXY4EC3SUR","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"pith_short_8","alias_value":"WC6O7FEX","created_at":"2026-07-05T04:12:05Z"}],"graph_snapshots":[{"event_id":"sha256:2f4267aa0377304aafce81d022869c0e2e9f294bdfa31306d18fb21ded20a3a1","target":"graph","created_at":"2026-07-05T04:12:05Z","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/2112.02244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image. One of the key challenges behind this task is leveraging the referring expression for highlighting relevant positions in the image. A paradigm for tackling this problem is to leverage a powerful vision-language (\"cross-modal\") decoder to fuse features independently extracted from a vision encoder and a language encoder. Recent methods have made remarkable advancements in this paradigm by exploiting Transformers as cross-modal decoders","authors_text":"Hengshuang Zhao, Jiaqi Wang, Kai Chen, Philip H.S. Torr, Yansong Tang, Zhao Yang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-04T04:53:35Z","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02244","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:c38af8790a04d5873560e05437cba9573587b7117ee0c25cc9f3730e1e670c6d","target":"record","created_at":"2026-07-05T04:12:05Z","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":"b99a83b561d0698af4e41c992b63370790f06e95ce801f24094ed0a47f10c44b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-04T04:53:35Z","title_canon_sha256":"e9b675e8fa127f3a1ff1adc2568ea58de7cc43abe3da094c003dfe0c4c8fa0bc"},"schema_version":"1.0","source":{"id":"2112.02244","kind":"arxiv","version":2}},"canonical_sha256":"b0bcef9497c7082dca91445ac5ffa973609b48c041c57fba31d0bb3ac3d0cbc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0bcef9497c7082dca91445ac5ffa973609b48c041c57fba31d0bb3ac3d0cbc7","first_computed_at":"2026-07-05T04:12:05.249451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:05.249451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b6n4CNr8FxxHM156927PZ7bcp5GFlqhYwhJt2k7FrhWaeG6toXK6sZj+c3uQVTM9cGpuEuRhbu2po6srvwi/Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:05.249946Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.02244","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c38af8790a04d5873560e05437cba9573587b7117ee0c25cc9f3730e1e670c6d","sha256:2f4267aa0377304aafce81d022869c0e2e9f294bdfa31306d18fb21ded20a3a1"],"state_sha256":"5c329ee3af2108d80143ebf505bbff6a1bc195ef58a0f0fe40214ad3e311decd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PDaQ68Aipr8fhn1LmpR6lgn8ikvyUliGFNvvR1hJcqXkHDwOmADm8Jn7WNTBAJlCfE4auwcUn2E8+O7V+SB0CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T19:49:09.269791Z","bundle_sha256":"05c3e4419475eca7bc01901c579d2079a944f2fcd54ee9b7ad9b3385bda77573"}}