{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MSAQHGLRJA5DNXKA3YU3CXPJ2Q","short_pith_number":"pith:MSAQHGLR","canonical_record":{"source":{"id":"1801.08186","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-24T20:54:26Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"537cd808547f8eb3b96e02c2e74c83a76092eed44ee97c23519324014d2e94aa","abstract_canon_sha256":"7746791f3397c351bfc3a125987c5fbb58c01f0d8ac2f8925872c829dd98cb57"},"schema_version":"1.0"},"canonical_sha256":"6481039971483a36dd40de29b15de9d43fb0a58cf376892a073c40e583c05365","source":{"kind":"arxiv","id":"1801.08186","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.08186","created_at":"2026-05-18T00:20:15Z"},{"alias_kind":"arxiv_version","alias_value":"1801.08186v3","created_at":"2026-05-18T00:20:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.08186","created_at":"2026-05-18T00:20:15Z"},{"alias_kind":"pith_short_12","alias_value":"MSAQHGLRJA5D","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MSAQHGLRJA5DNXKA","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MSAQHGLR","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MSAQHGLRJA5DNXKA3YU3CXPJ2Q","target":"record","payload":{"canonical_record":{"source":{"id":"1801.08186","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-24T20:54:26Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"537cd808547f8eb3b96e02c2e74c83a76092eed44ee97c23519324014d2e94aa","abstract_canon_sha256":"7746791f3397c351bfc3a125987c5fbb58c01f0d8ac2f8925872c829dd98cb57"},"schema_version":"1.0"},"canonical_sha256":"6481039971483a36dd40de29b15de9d43fb0a58cf376892a073c40e583c05365","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:15.953815Z","signature_b64":"/ZO/Uw4CDCmponycZG/uwVDkGCGz8Y4tzLKdsn4xiY0MopaJSuEeRX6/xZ1JklslURmcv/5exiGqggGE0uNgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6481039971483a36dd40de29b15de9d43fb0a58cf376892a073c40e583c05365","last_reissued_at":"2026-05-18T00:20:15.953081Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:15.953081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.08186","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:20:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p4QBL1pR4g95M5kpiFklnYaatBU+4iqym3WT2nk9aiR3m1gFrV2Af3UVvkR8cDjm4by8+ZHpg21V4G/qWyviBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:31:30.586874Z"},"content_sha256":"1730a902ca2d5965dba0eeb4c407b8549cc495c25edec4c15766b705fd2d26f1","schema_version":"1.0","event_id":"sha256:1730a902ca2d5965dba0eeb4c407b8549cc495c25edec4c15766b705fd2d26f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MSAQHGLRJA5DNXKA3YU3CXPJ2Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jimei Yang, Licheng Yu, Mohit Bansal, Tamara L.Berg, Xiaohui Shen, Xin Lu, Zhe Lin","submitted_at":"2018-01-24T20:54:26Z","abstract_excerpt":"In this paper, we address referring expression comprehension: localizing an image region described by a natural language expression. While most recent work treats expressions as a single unit, we propose to decompose them into three modular components related to subject appearance, location, and relationship to other objects. This allows us to flexibly adapt to expressions containing different types of information in an end-to-end framework. In our model, which we call the Modular Attention Network (MAttNet), two types of attention are utilized: language-based attention that learns the module "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.08186","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:20:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wipZYPahrmOasnsSnCGIubLrxEFajoh8yMJxkW5iCkngkvdEk6sr//RDr42+LZIEat2oJXo1z4KtKfzkY3ukAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:31:30.587224Z"},"content_sha256":"a77642afb7edd1d5e2573746ae2c51eb6fac3dd0e7a96fe6e9d5eb6c66f0daf9","schema_version":"1.0","event_id":"sha256:a77642afb7edd1d5e2573746ae2c51eb6fac3dd0e7a96fe6e9d5eb6c66f0daf9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MSAQHGLRJA5DNXKA3YU3CXPJ2Q/bundle.json","state_url":"https://pith.science/pith/MSAQHGLRJA5DNXKA3YU3CXPJ2Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MSAQHGLRJA5DNXKA3YU3CXPJ2Q/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":"2026-06-03T07:31:30Z","links":{"resolver":"https://pith.science/pith/MSAQHGLRJA5DNXKA3YU3CXPJ2Q","bundle":"https://pith.science/pith/MSAQHGLRJA5DNXKA3YU3CXPJ2Q/bundle.json","state":"https://pith.science/pith/MSAQHGLRJA5DNXKA3YU3CXPJ2Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MSAQHGLRJA5DNXKA3YU3CXPJ2Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MSAQHGLRJA5DNXKA3YU3CXPJ2Q","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":"7746791f3397c351bfc3a125987c5fbb58c01f0d8ac2f8925872c829dd98cb57","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-24T20:54:26Z","title_canon_sha256":"537cd808547f8eb3b96e02c2e74c83a76092eed44ee97c23519324014d2e94aa"},"schema_version":"1.0","source":{"id":"1801.08186","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.08186","created_at":"2026-05-18T00:20:15Z"},{"alias_kind":"arxiv_version","alias_value":"1801.08186v3","created_at":"2026-05-18T00:20:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.08186","created_at":"2026-05-18T00:20:15Z"},{"alias_kind":"pith_short_12","alias_value":"MSAQHGLRJA5D","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MSAQHGLRJA5DNXKA","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MSAQHGLR","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:a77642afb7edd1d5e2573746ae2c51eb6fac3dd0e7a96fe6e9d5eb6c66f0daf9","target":"graph","created_at":"2026-05-18T00:20:15Z","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"},"paper":{"abstract_excerpt":"In this paper, we address referring expression comprehension: localizing an image region described by a natural language expression. While most recent work treats expressions as a single unit, we propose to decompose them into three modular components related to subject appearance, location, and relationship to other objects. This allows us to flexibly adapt to expressions containing different types of information in an end-to-end framework. In our model, which we call the Modular Attention Network (MAttNet), two types of attention are utilized: language-based attention that learns the module ","authors_text":"Jimei Yang, Licheng Yu, Mohit Bansal, Tamara L.Berg, Xiaohui Shen, Xin Lu, Zhe Lin","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-24T20:54:26Z","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.08186","kind":"arxiv","version":3},"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":"sha256:1730a902ca2d5965dba0eeb4c407b8549cc495c25edec4c15766b705fd2d26f1","target":"record","created_at":"2026-05-18T00:20:15Z","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":"7746791f3397c351bfc3a125987c5fbb58c01f0d8ac2f8925872c829dd98cb57","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-24T20:54:26Z","title_canon_sha256":"537cd808547f8eb3b96e02c2e74c83a76092eed44ee97c23519324014d2e94aa"},"schema_version":"1.0","source":{"id":"1801.08186","kind":"arxiv","version":3}},"canonical_sha256":"6481039971483a36dd40de29b15de9d43fb0a58cf376892a073c40e583c05365","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6481039971483a36dd40de29b15de9d43fb0a58cf376892a073c40e583c05365","first_computed_at":"2026-05-18T00:20:15.953081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:15.953081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/ZO/Uw4CDCmponycZG/uwVDkGCGz8Y4tzLKdsn4xiY0MopaJSuEeRX6/xZ1JklslURmcv/5exiGqggGE0uNgAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:15.953815Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.08186","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1730a902ca2d5965dba0eeb4c407b8549cc495c25edec4c15766b705fd2d26f1","sha256:a77642afb7edd1d5e2573746ae2c51eb6fac3dd0e7a96fe6e9d5eb6c66f0daf9"],"state_sha256":"2c99570e28e727aeecc04aeaeaf0748f76ad3a3a75c7bbd726c057944f587a47"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qu5k16a6QaC3NCSZBdasUGNPK6aTi3jU4W6XyyWA1udB63F8L1mgZocUjRaXsdcSqFJ45KstMVwNmj2CoQPUCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T07:31:30.589208Z","bundle_sha256":"c8bfaacaf386c598f81d4b09b369bff7e7ecbd98b03a3726fbbd04712636d509"}}