{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UBK7AHTCY5G27P3VUUZCKADQEJ","short_pith_number":"pith:UBK7AHTC","canonical_record":{"source":{"id":"2210.02206","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2022-10-05T12:34:06Z","cross_cats_sorted":[],"title_canon_sha256":"6e65e346a0f8ff3aafb493065eb080d310508f4cfb0b1ae07111c88c8b8fb2b6","abstract_canon_sha256":"5269f7c3d5fd895d05c8fe85410c3e330d03d8088546ce37308fafd9b227382e"},"schema_version":"1.0"},"canonical_sha256":"a055f01e62c74dafbf75a53225007022603cc4f9bbe6ae0e2ccfe8e7cd0b873a","source":{"kind":"arxiv","id":"2210.02206","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.02206","created_at":"2026-07-05T05:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2210.02206v1","created_at":"2026-07-05T05:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02206","created_at":"2026-07-05T05:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"UBK7AHTCY5G2","created_at":"2026-07-05T05:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"UBK7AHTCY5G27P3V","created_at":"2026-07-05T05:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"UBK7AHTC","created_at":"2026-07-05T05:03:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UBK7AHTCY5G27P3VUUZCKADQEJ","target":"record","payload":{"canonical_record":{"source":{"id":"2210.02206","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2022-10-05T12:34:06Z","cross_cats_sorted":[],"title_canon_sha256":"6e65e346a0f8ff3aafb493065eb080d310508f4cfb0b1ae07111c88c8b8fb2b6","abstract_canon_sha256":"5269f7c3d5fd895d05c8fe85410c3e330d03d8088546ce37308fafd9b227382e"},"schema_version":"1.0"},"canonical_sha256":"a055f01e62c74dafbf75a53225007022603cc4f9bbe6ae0e2ccfe8e7cd0b873a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:44.686792Z","signature_b64":"H1wdyI04STUmbh6heob4j97/HY+J5gznOhjXpWY6PriaqaVmWAJdjGV/0IpAPKcop3nonvQcHL1qKuj3iIaYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a055f01e62c74dafbf75a53225007022603cc4f9bbe6ae0e2ccfe8e7cd0b873a","last_reissued_at":"2026-07-05T05:03:44.686301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:44.686301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.02206","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":"2026-07-05T05:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fPw6Ah0/+lk0Ydap8hU/Ka8ZokstVPV03opsS0WQ7q45I6YVuLHsPiHdfnic3NYIR3B/2F/Fy44MjuoQdvm7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:55:08.611291Z"},"content_sha256":"f602a5347ab1092b452624e8e237469dd73e41aacda9dd9971105235b842867e","schema_version":"1.0","event_id":"sha256:f602a5347ab1092b452624e8e237469dd73e41aacda9dd9971105235b842867e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UBK7AHTCY5G27P3VUUZCKADQEJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Visual-Semantic Embedding with Adaptive Pooling and Optimization Objective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Chang Shu, Di Zhu, Jey Han Lau, Jing Xiao, Qian Zhang, Ya Xiao, Youxin Chen, Yuan Shen, Zheng Lu, Zijian Zhang","submitted_at":"2022-10-05T12:34:06Z","abstract_excerpt":"Visual-Semantic Embedding (VSE) aims to learn an embedding space where related visual and semantic instances are close to each other. Recent VSE models tend to design complex structures to pool visual and semantic features into fixed-length vectors and use hard triplet loss for optimization. However, we find that: (1) combining simple pooling methods is no worse than these sophisticated methods; and (2) only considering the most difficult-to-distinguish negative sample leads to slow convergence and poor Recall@K improvement. To this end, we propose an adaptive pooling strategy that allows the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02206","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/2210.02206/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":"2026-07-05T05:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7B53bZLTnHtKNg7rcnqZKW0PwNElSY8iXUt1ES07dyMxXYXnITApI7MEgNa8EtkNN9y4yBNtkwasQkyz0KMFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:55:08.611682Z"},"content_sha256":"56ac7cbe78d87e138118de6adf33d6ec2b7ea20acbad4d787709b9d9264f6ca1","schema_version":"1.0","event_id":"sha256:56ac7cbe78d87e138118de6adf33d6ec2b7ea20acbad4d787709b9d9264f6ca1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UBK7AHTCY5G27P3VUUZCKADQEJ/bundle.json","state_url":"https://pith.science/pith/UBK7AHTCY5G27P3VUUZCKADQEJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UBK7AHTCY5G27P3VUUZCKADQEJ/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":"2026-07-07T06:55:08Z","links":{"resolver":"https://pith.science/pith/UBK7AHTCY5G27P3VUUZCKADQEJ","bundle":"https://pith.science/pith/UBK7AHTCY5G27P3VUUZCKADQEJ/bundle.json","state":"https://pith.science/pith/UBK7AHTCY5G27P3VUUZCKADQEJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UBK7AHTCY5G27P3VUUZCKADQEJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UBK7AHTCY5G27P3VUUZCKADQEJ","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":"5269f7c3d5fd895d05c8fe85410c3e330d03d8088546ce37308fafd9b227382e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2022-10-05T12:34:06Z","title_canon_sha256":"6e65e346a0f8ff3aafb493065eb080d310508f4cfb0b1ae07111c88c8b8fb2b6"},"schema_version":"1.0","source":{"id":"2210.02206","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.02206","created_at":"2026-07-05T05:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2210.02206v1","created_at":"2026-07-05T05:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02206","created_at":"2026-07-05T05:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"UBK7AHTCY5G2","created_at":"2026-07-05T05:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"UBK7AHTCY5G27P3V","created_at":"2026-07-05T05:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"UBK7AHTC","created_at":"2026-07-05T05:03:44Z"}],"graph_snapshots":[{"event_id":"sha256:56ac7cbe78d87e138118de6adf33d6ec2b7ea20acbad4d787709b9d9264f6ca1","target":"graph","created_at":"2026-07-05T05:03:44Z","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/2210.02206/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual-Semantic Embedding (VSE) aims to learn an embedding space where related visual and semantic instances are close to each other. Recent VSE models tend to design complex structures to pool visual and semantic features into fixed-length vectors and use hard triplet loss for optimization. However, we find that: (1) combining simple pooling methods is no worse than these sophisticated methods; and (2) only considering the most difficult-to-distinguish negative sample leads to slow convergence and poor Recall@K improvement. To this end, we propose an adaptive pooling strategy that allows the ","authors_text":"Chang Shu, Di Zhu, Jey Han Lau, Jing Xiao, Qian Zhang, Ya Xiao, Youxin Chen, Yuan Shen, Zheng Lu, Zijian Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2022-10-05T12:34:06Z","title":"Improving Visual-Semantic Embedding with Adaptive Pooling and Optimization Objective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02206","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:f602a5347ab1092b452624e8e237469dd73e41aacda9dd9971105235b842867e","target":"record","created_at":"2026-07-05T05:03:44Z","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":"5269f7c3d5fd895d05c8fe85410c3e330d03d8088546ce37308fafd9b227382e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2022-10-05T12:34:06Z","title_canon_sha256":"6e65e346a0f8ff3aafb493065eb080d310508f4cfb0b1ae07111c88c8b8fb2b6"},"schema_version":"1.0","source":{"id":"2210.02206","kind":"arxiv","version":1}},"canonical_sha256":"a055f01e62c74dafbf75a53225007022603cc4f9bbe6ae0e2ccfe8e7cd0b873a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a055f01e62c74dafbf75a53225007022603cc4f9bbe6ae0e2ccfe8e7cd0b873a","first_computed_at":"2026-07-05T05:03:44.686301Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:44.686301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H1wdyI04STUmbh6heob4j97/HY+J5gznOhjXpWY6PriaqaVmWAJdjGV/0IpAPKcop3nonvQcHL1qKuj3iIaYDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:44.686792Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.02206","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f602a5347ab1092b452624e8e237469dd73e41aacda9dd9971105235b842867e","sha256:56ac7cbe78d87e138118de6adf33d6ec2b7ea20acbad4d787709b9d9264f6ca1"],"state_sha256":"af312bc959baba94bc2f4dccf3eecc7d9d3b18fc95b3e7e2796795a9d421c429"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d+d5j96mLhcTHs6b/aybhjTbIQZbvlPhgHZzMpFrNr31+8xV9N1DGeBQt6/gDUQrAzXEhUBeWT7WRNiZXJErDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:55:08.613628Z","bundle_sha256":"12b208a5865e5b5d8bb7b9af81d614a1740df060bdf13a5a55d996de49049f97"}}