{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:EXJTUOQSTB2HVJMNJFL42QOMQR","short_pith_number":"pith:EXJTUOQS","canonical_record":{"source":{"id":"1704.03470","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-11T18:00:25Z","cross_cats_sorted":[],"title_canon_sha256":"4106d5ae883a751c82a6b11a24d94e76997a6d1763adb9d67327deaf960ca5c2","abstract_canon_sha256":"d34aa5bbab2a9356bd23d11bfcf0d669a940751237c1820d5b156be79c1a691a"},"schema_version":"1.0"},"canonical_sha256":"25d33a3a1298747aa58d4957cd41cc8449f0e0eaf5f67c1081ff156b0bc66a49","source":{"kind":"arxiv","id":"1704.03470","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.03470","created_at":"2026-05-18T00:17:01Z"},{"alias_kind":"arxiv_version","alias_value":"1704.03470v4","created_at":"2026-05-18T00:17:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.03470","created_at":"2026-05-18T00:17:01Z"},{"alias_kind":"pith_short_12","alias_value":"EXJTUOQSTB2H","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EXJTUOQSTB2HVJMN","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EXJTUOQS","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:EXJTUOQSTB2HVJMNJFL42QOMQR","target":"record","payload":{"canonical_record":{"source":{"id":"1704.03470","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-11T18:00:25Z","cross_cats_sorted":[],"title_canon_sha256":"4106d5ae883a751c82a6b11a24d94e76997a6d1763adb9d67327deaf960ca5c2","abstract_canon_sha256":"d34aa5bbab2a9356bd23d11bfcf0d669a940751237c1820d5b156be79c1a691a"},"schema_version":"1.0"},"canonical_sha256":"25d33a3a1298747aa58d4957cd41cc8449f0e0eaf5f67c1081ff156b0bc66a49","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:01.915447Z","signature_b64":"Z8o1var+eyWq96WPv5NrlwZzi1N/9LQEA0h6NYCGVduvetrjKP/mRpMlSVlpcNFJRtTRG6oJNnyZ/wtndNTLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25d33a3a1298747aa58d4957cd41cc8449f0e0eaf5f67c1081ff156b0bc66a49","last_reissued_at":"2026-05-18T00:17:01.914826Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:01.914826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.03470","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:17:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"THh2GgWWBel7Vppu58nLlK+ptTs0w4jRMwiZ4AhG17AmHlU9YCOZ7QfSQcw/lT0ieCf6ELX+pr1B5LljnaR+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T15:07:29.741660Z"},"content_sha256":"f633410d1678b4f046996ca8e988bd7425f61294817cb336570315c78ae15e82","schema_version":"1.0","event_id":"sha256:f633410d1678b4f046996ca8e988bd7425f61294817cb336570315c78ae15e82"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:EXJTUOQSTB2HVJMNJFL42QOMQR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Two-Branch Neural Networks for Image-Text Matching Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Huang, Liwei Wang, Svetlana Lazebnik, Yin Li","submitted_at":"2017-04-11T18:00:25Z","abstract_excerpt":"Image-language matching tasks have recently attracted a lot of attention in the computer vision field. These tasks include image-sentence matching, i.e., given an image query, retrieving relevant sentences and vice versa, and region-phrase matching or visual grounding, i.e., matching a phrase to relevant regions. This paper investigates two-branch neural networks for learning the similarity between these two data modalities. We propose two network structures that produce different output representations. The first one, referred to as an embedding network, learns an explicit shared latent embed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.03470","kind":"arxiv","version":4},"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":"2026-05-18T00:17:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LDsHJOuAAIeiDzGw/Zsk3jJdFCW24f1D+kyR7JgFuRQvCzLD2l7aRgXFcvGVo48gWnwphx4y9zgRBtgfyAA4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T15:07:29.742927Z"},"content_sha256":"d2b43ec7131bd8edfe4eadf509e8bc8c03d1a98efc2b0d1c36cbecb1fa8bbb2b","schema_version":"1.0","event_id":"sha256:d2b43ec7131bd8edfe4eadf509e8bc8c03d1a98efc2b0d1c36cbecb1fa8bbb2b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EXJTUOQSTB2HVJMNJFL42QOMQR/bundle.json","state_url":"https://pith.science/pith/EXJTUOQSTB2HVJMNJFL42QOMQR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EXJTUOQSTB2HVJMNJFL42QOMQR/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":"2026-08-16T15:07:29Z","links":{"resolver":"https://pith.science/pith/EXJTUOQSTB2HVJMNJFL42QOMQR","bundle":"https://pith.science/pith/EXJTUOQSTB2HVJMNJFL42QOMQR/bundle.json","state":"https://pith.science/pith/EXJTUOQSTB2HVJMNJFL42QOMQR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EXJTUOQSTB2HVJMNJFL42QOMQR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:EXJTUOQSTB2HVJMNJFL42QOMQR","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":"d34aa5bbab2a9356bd23d11bfcf0d669a940751237c1820d5b156be79c1a691a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-11T18:00:25Z","title_canon_sha256":"4106d5ae883a751c82a6b11a24d94e76997a6d1763adb9d67327deaf960ca5c2"},"schema_version":"1.0","source":{"id":"1704.03470","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.03470","created_at":"2026-05-18T00:17:01Z"},{"alias_kind":"arxiv_version","alias_value":"1704.03470v4","created_at":"2026-05-18T00:17:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.03470","created_at":"2026-05-18T00:17:01Z"},{"alias_kind":"pith_short_12","alias_value":"EXJTUOQSTB2H","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EXJTUOQSTB2HVJMN","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EXJTUOQS","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:d2b43ec7131bd8edfe4eadf509e8bc8c03d1a98efc2b0d1c36cbecb1fa8bbb2b","target":"graph","created_at":"2026-05-18T00:17:01Z","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":"Image-language matching tasks have recently attracted a lot of attention in the computer vision field. These tasks include image-sentence matching, i.e., given an image query, retrieving relevant sentences and vice versa, and region-phrase matching or visual grounding, i.e., matching a phrase to relevant regions. This paper investigates two-branch neural networks for learning the similarity between these two data modalities. We propose two network structures that produce different output representations. The first one, referred to as an embedding network, learns an explicit shared latent embed","authors_text":"Jing Huang, Liwei Wang, Svetlana Lazebnik, Yin Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-11T18:00:25Z","title":"Learning Two-Branch Neural Networks for Image-Text Matching Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.03470","kind":"arxiv","version":4},"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:f633410d1678b4f046996ca8e988bd7425f61294817cb336570315c78ae15e82","target":"record","created_at":"2026-05-18T00:17:01Z","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":"d34aa5bbab2a9356bd23d11bfcf0d669a940751237c1820d5b156be79c1a691a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-11T18:00:25Z","title_canon_sha256":"4106d5ae883a751c82a6b11a24d94e76997a6d1763adb9d67327deaf960ca5c2"},"schema_version":"1.0","source":{"id":"1704.03470","kind":"arxiv","version":4}},"canonical_sha256":"25d33a3a1298747aa58d4957cd41cc8449f0e0eaf5f67c1081ff156b0bc66a49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25d33a3a1298747aa58d4957cd41cc8449f0e0eaf5f67c1081ff156b0bc66a49","first_computed_at":"2026-05-18T00:17:01.914826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:01.914826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z8o1var+eyWq96WPv5NrlwZzi1N/9LQEA0h6NYCGVduvetrjKP/mRpMlSVlpcNFJRtTRG6oJNnyZ/wtndNTLCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:01.915447Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.03470","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f633410d1678b4f046996ca8e988bd7425f61294817cb336570315c78ae15e82","sha256:d2b43ec7131bd8edfe4eadf509e8bc8c03d1a98efc2b0d1c36cbecb1fa8bbb2b"],"state_sha256":"aa68331c7061317ca449e4c9edfec8c061bbbde1b9ebc117bc3567ffc9802e84"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wlXwV629v9CVNnhm71UTHfFPznWNm+2q2HRPAOw+O7u+C1pMA0BM4Apf0pW3o0yu+6yALh/0Ox/qSGS3GbBOBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T15:07:29.750602Z","bundle_sha256":"013253bf09e2d6baaf3a7d3740a24b690e356fb6e8fec4cbd9b25c140e7cab9d"}}