{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:HMVMRQ2RC2B4OKB5VV6AOELULX","short_pith_number":"pith:HMVMRQ2R","canonical_record":{"source":{"id":"2111.10747","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-21T05:54:17Z","cross_cats_sorted":[],"title_canon_sha256":"ed5d8b8e0e163458c090b6f6cfa31f9ffc4944f89c35febe10b3b5b6ab62adbb","abstract_canon_sha256":"fa6f95876e4628964a6cbee0a296ee0e25eb504c5d635a4197293eedf123e345"},"schema_version":"1.0"},"canonical_sha256":"3b2ac8c3511683c7283dad7c0711745dee5b661ae61c9a8cef745f8f7a743739","source":{"kind":"arxiv","id":"2111.10747","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.10747","created_at":"2026-07-05T03:34:57Z"},{"alias_kind":"arxiv_version","alias_value":"2111.10747v2","created_at":"2026-07-05T03:34:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10747","created_at":"2026-07-05T03:34:57Z"},{"alias_kind":"pith_short_12","alias_value":"HMVMRQ2RC2B4","created_at":"2026-07-05T03:34:57Z"},{"alias_kind":"pith_short_16","alias_value":"HMVMRQ2RC2B4OKB5","created_at":"2026-07-05T03:34:57Z"},{"alias_kind":"pith_short_8","alias_value":"HMVMRQ2R","created_at":"2026-07-05T03:34:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:HMVMRQ2RC2B4OKB5VV6AOELULX","target":"record","payload":{"canonical_record":{"source":{"id":"2111.10747","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-21T05:54:17Z","cross_cats_sorted":[],"title_canon_sha256":"ed5d8b8e0e163458c090b6f6cfa31f9ffc4944f89c35febe10b3b5b6ab62adbb","abstract_canon_sha256":"fa6f95876e4628964a6cbee0a296ee0e25eb504c5d635a4197293eedf123e345"},"schema_version":"1.0"},"canonical_sha256":"3b2ac8c3511683c7283dad7c0711745dee5b661ae61c9a8cef745f8f7a743739","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:57.496513Z","signature_b64":"7YWtipwnip2USN39eLMO+6kHaJjk/qQ3kT4mKyKZawhrVos2JZd4XSCgFONhcmsq7xNKVj1vzrd2SQBjPbg3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b2ac8c3511683c7283dad7c0711745dee5b661ae61c9a8cef745f8f7a743739","last_reissued_at":"2026-07-05T03:34:57.496081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:57.496081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.10747","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":"2026-07-05T03:34:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6/qDIpHZYpDfB0dMXP6GCk6PkHPxJe/XIwiG9ajC+wl8oAEdbmKP3iIhmT8biQVP5dZ1oOdvSPWpi54/JF1vBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:47:36.102283Z"},"content_sha256":"15db4224fe5a49ed0cb428912ff499f745286af2509671284da762bb64e3a082","schema_version":"1.0","event_id":"sha256:15db4224fe5a49ed0cb428912ff499f745286af2509671284da762bb64e3a082"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:HMVMRQ2RC2B4OKB5VV6AOELULX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianbiao Mei, Mengmeng Wang, Yong Liu, Zizhang Li","submitted_at":"2021-11-21T05:54:17Z","abstract_excerpt":"Referring image segmentation is a typical multi-modal task, which aims at generating a binary mask for referent described in given language expressions. Prior arts adopt a bimodal solution, taking images and languages as two modalities within an encoder-fusion-decoder pipeline. However, this pipeline is sub-optimal for the target task for two reasons. First, they only fuse high-level features produced by uni-modal encoders separately, which hinders sufficient cross-modal learning. Second, the uni-modal encoders are pre-trained independently, which brings inconsistency between pre-trained uni-m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10747","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/2111.10747/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":"2026-07-05T03:34:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m8TY25w5sq78h3/I8zjViwv4fih6yJYmhOB5SdXYr3squrow0Yx06hl1dxsqSntyFt9UJW+ePEJRswVqxmPqDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:47:36.103237Z"},"content_sha256":"751d5b4d57a5bd9f2385fe1627c4137de6b7f0156a09b5a9926d767ce4dde8b2","schema_version":"1.0","event_id":"sha256:751d5b4d57a5bd9f2385fe1627c4137de6b7f0156a09b5a9926d767ce4dde8b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HMVMRQ2RC2B4OKB5VV6AOELULX/bundle.json","state_url":"https://pith.science/pith/HMVMRQ2RC2B4OKB5VV6AOELULX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HMVMRQ2RC2B4OKB5VV6AOELULX/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":"2026-08-09T11:47:36Z","links":{"resolver":"https://pith.science/pith/HMVMRQ2RC2B4OKB5VV6AOELULX","bundle":"https://pith.science/pith/HMVMRQ2RC2B4OKB5VV6AOELULX/bundle.json","state":"https://pith.science/pith/HMVMRQ2RC2B4OKB5VV6AOELULX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HMVMRQ2RC2B4OKB5VV6AOELULX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HMVMRQ2RC2B4OKB5VV6AOELULX","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":"fa6f95876e4628964a6cbee0a296ee0e25eb504c5d635a4197293eedf123e345","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-21T05:54:17Z","title_canon_sha256":"ed5d8b8e0e163458c090b6f6cfa31f9ffc4944f89c35febe10b3b5b6ab62adbb"},"schema_version":"1.0","source":{"id":"2111.10747","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.10747","created_at":"2026-07-05T03:34:57Z"},{"alias_kind":"arxiv_version","alias_value":"2111.10747v2","created_at":"2026-07-05T03:34:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10747","created_at":"2026-07-05T03:34:57Z"},{"alias_kind":"pith_short_12","alias_value":"HMVMRQ2RC2B4","created_at":"2026-07-05T03:34:57Z"},{"alias_kind":"pith_short_16","alias_value":"HMVMRQ2RC2B4OKB5","created_at":"2026-07-05T03:34:57Z"},{"alias_kind":"pith_short_8","alias_value":"HMVMRQ2R","created_at":"2026-07-05T03:34:57Z"}],"graph_snapshots":[{"event_id":"sha256:751d5b4d57a5bd9f2385fe1627c4137de6b7f0156a09b5a9926d767ce4dde8b2","target":"graph","created_at":"2026-07-05T03:34:57Z","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/2111.10747/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring image segmentation is a typical multi-modal task, which aims at generating a binary mask for referent described in given language expressions. Prior arts adopt a bimodal solution, taking images and languages as two modalities within an encoder-fusion-decoder pipeline. However, this pipeline is sub-optimal for the target task for two reasons. First, they only fuse high-level features produced by uni-modal encoders separately, which hinders sufficient cross-modal learning. Second, the uni-modal encoders are pre-trained independently, which brings inconsistency between pre-trained uni-m","authors_text":"Jianbiao Mei, Mengmeng Wang, Yong Liu, Zizhang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-21T05:54:17Z","title":"MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10747","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":"sha256:15db4224fe5a49ed0cb428912ff499f745286af2509671284da762bb64e3a082","target":"record","created_at":"2026-07-05T03:34:57Z","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":"fa6f95876e4628964a6cbee0a296ee0e25eb504c5d635a4197293eedf123e345","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-21T05:54:17Z","title_canon_sha256":"ed5d8b8e0e163458c090b6f6cfa31f9ffc4944f89c35febe10b3b5b6ab62adbb"},"schema_version":"1.0","source":{"id":"2111.10747","kind":"arxiv","version":2}},"canonical_sha256":"3b2ac8c3511683c7283dad7c0711745dee5b661ae61c9a8cef745f8f7a743739","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b2ac8c3511683c7283dad7c0711745dee5b661ae61c9a8cef745f8f7a743739","first_computed_at":"2026-07-05T03:34:57.496081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:34:57.496081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7YWtipwnip2USN39eLMO+6kHaJjk/qQ3kT4mKyKZawhrVos2JZd4XSCgFONhcmsq7xNKVj1vzrd2SQBjPbg3Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:34:57.496513Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.10747","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15db4224fe5a49ed0cb428912ff499f745286af2509671284da762bb64e3a082","sha256:751d5b4d57a5bd9f2385fe1627c4137de6b7f0156a09b5a9926d767ce4dde8b2"],"state_sha256":"e3b039401256c61efda316e848282ecadfd2fbb43e6ed0c4775f878c8f87ee2d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BVz8vQx9uU8ov16rhwPPqSUzNl2u5wTLpY+9zpq3yGQ0iPQjeORSHOtid5vU2NT9MAyPXKhKv+KM+K4zlorkAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:47:36.110686Z","bundle_sha256":"30626ebd97eeaf13dbe91655623a945b068b4527b319041687d81839d83a751d"}}