{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ESGTVTID5CMW4OW2JX7CB4PWX7","short_pith_number":"pith:ESGTVTID","canonical_record":{"source":{"id":"2011.04305","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-09T10:22:35Z","cross_cats_sorted":[],"title_canon_sha256":"7eb349d6f36dcb0f672087b0936e50891d5062da1071c705dec5953411457883","abstract_canon_sha256":"1af91674fa08f141f059c77dbc6a3da38b19b1c03dee5f7490819ae784d942b4"},"schema_version":"1.0"},"canonical_sha256":"248d3acd03e8996e3ada4dfe20f1f6bfcff2197141327e551a79f5bd912ce39f","source":{"kind":"arxiv","id":"2011.04305","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.04305","created_at":"2026-07-05T02:55:08Z"},{"alias_kind":"arxiv_version","alias_value":"2011.04305v5","created_at":"2026-07-05T02:55:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04305","created_at":"2026-07-05T02:55:08Z"},{"alias_kind":"pith_short_12","alias_value":"ESGTVTID5CMW","created_at":"2026-07-05T02:55:08Z"},{"alias_kind":"pith_short_16","alias_value":"ESGTVTID5CMW4OW2","created_at":"2026-07-05T02:55:08Z"},{"alias_kind":"pith_short_8","alias_value":"ESGTVTID","created_at":"2026-07-05T02:55:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ESGTVTID5CMW4OW2JX7CB4PWX7","target":"record","payload":{"canonical_record":{"source":{"id":"2011.04305","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-09T10:22:35Z","cross_cats_sorted":[],"title_canon_sha256":"7eb349d6f36dcb0f672087b0936e50891d5062da1071c705dec5953411457883","abstract_canon_sha256":"1af91674fa08f141f059c77dbc6a3da38b19b1c03dee5f7490819ae784d942b4"},"schema_version":"1.0"},"canonical_sha256":"248d3acd03e8996e3ada4dfe20f1f6bfcff2197141327e551a79f5bd912ce39f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:55:08.537034Z","signature_b64":"f1h+laOHZUBsm8/mQxSEhOrPAt27amckf51uqiI9NPVZSvChtLdF6oLh1RQvdqq8+La+ot6ZvQHgUlJwWmasDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"248d3acd03e8996e3ada4dfe20f1f6bfcff2197141327e551a79f5bd912ce39f","last_reissued_at":"2026-07-05T02:55:08.536649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:55:08.536649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.04305","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:55:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XcL5WQfR9dE49Dy6o9E2J9NSy5zv/X7wtw6LO0rehUCkQc1OOi/2z9NyFoS1tbWoDrbJkWje7LBg/sdaYVtzCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:47:57.787046Z"},"content_sha256":"6f55fc58c799d585236f039103f0f5f0177673ef138ce133cc8c6837ee211304","schema_version":"1.0","event_id":"sha256:6f55fc58c799d585236f039103f0f5f0177673ef138ce133cc8c6837ee211304"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ESGTVTID5CMW4OW2JX7CB4PWX7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning the Best Pooling Strategy for Visual Semantic Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changhu Wang, Hao Wu, Hexiang Hu, Jiacheng Chen, Yuning Jiang","submitted_at":"2020-11-09T10:22:35Z","abstract_excerpt":"Visual Semantic Embedding (VSE) is a dominant approach for vision-language retrieval, which aims at learning a deep embedding space such that visual data are embedded close to their semantic text labels or descriptions. Recent VSE models use complex methods to better contextualize and aggregate multi-modal features into holistic embeddings. However, we discover that surprisingly simple (but carefully selected) global pooling functions (e.g., max pooling) outperform those complex models, across different feature extractors. Despite its simplicity and effectiveness, seeking the best pooling func"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04305","kind":"arxiv","version":5},"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/2011.04305/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":"2026-07-05T02:55:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KOErxtXN+aabaMk10FjwuC/TkIAalfi+1qollO1NPqhctX0tAmZVJv08xyoluwN6EE3jsLHLjsu630b3nHqcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:47:57.788066Z"},"content_sha256":"d24c90e7d5f8d9f62e7c321c55e48da43ecfee0310faeb182af0ea0b66e79e8a","schema_version":"1.0","event_id":"sha256:d24c90e7d5f8d9f62e7c321c55e48da43ecfee0310faeb182af0ea0b66e79e8a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ESGTVTID5CMW4OW2JX7CB4PWX7/bundle.json","state_url":"https://pith.science/pith/ESGTVTID5CMW4OW2JX7CB4PWX7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ESGTVTID5CMW4OW2JX7CB4PWX7/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":"2026-08-05T00:47:57Z","links":{"resolver":"https://pith.science/pith/ESGTVTID5CMW4OW2JX7CB4PWX7","bundle":"https://pith.science/pith/ESGTVTID5CMW4OW2JX7CB4PWX7/bundle.json","state":"https://pith.science/pith/ESGTVTID5CMW4OW2JX7CB4PWX7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ESGTVTID5CMW4OW2JX7CB4PWX7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ESGTVTID5CMW4OW2JX7CB4PWX7","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":"1af91674fa08f141f059c77dbc6a3da38b19b1c03dee5f7490819ae784d942b4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-09T10:22:35Z","title_canon_sha256":"7eb349d6f36dcb0f672087b0936e50891d5062da1071c705dec5953411457883"},"schema_version":"1.0","source":{"id":"2011.04305","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.04305","created_at":"2026-07-05T02:55:08Z"},{"alias_kind":"arxiv_version","alias_value":"2011.04305v5","created_at":"2026-07-05T02:55:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04305","created_at":"2026-07-05T02:55:08Z"},{"alias_kind":"pith_short_12","alias_value":"ESGTVTID5CMW","created_at":"2026-07-05T02:55:08Z"},{"alias_kind":"pith_short_16","alias_value":"ESGTVTID5CMW4OW2","created_at":"2026-07-05T02:55:08Z"},{"alias_kind":"pith_short_8","alias_value":"ESGTVTID","created_at":"2026-07-05T02:55:08Z"}],"graph_snapshots":[{"event_id":"sha256:d24c90e7d5f8d9f62e7c321c55e48da43ecfee0310faeb182af0ea0b66e79e8a","target":"graph","created_at":"2026-07-05T02:55:08Z","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/2011.04305/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Semantic Embedding (VSE) is a dominant approach for vision-language retrieval, which aims at learning a deep embedding space such that visual data are embedded close to their semantic text labels or descriptions. Recent VSE models use complex methods to better contextualize and aggregate multi-modal features into holistic embeddings. However, we discover that surprisingly simple (but carefully selected) global pooling functions (e.g., max pooling) outperform those complex models, across different feature extractors. Despite its simplicity and effectiveness, seeking the best pooling func","authors_text":"Changhu Wang, Hao Wu, Hexiang Hu, Jiacheng Chen, Yuning Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-09T10:22:35Z","title":"Learning the Best Pooling Strategy for Visual Semantic Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04305","kind":"arxiv","version":5},"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":"sha256:6f55fc58c799d585236f039103f0f5f0177673ef138ce133cc8c6837ee211304","target":"record","created_at":"2026-07-05T02:55:08Z","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":"1af91674fa08f141f059c77dbc6a3da38b19b1c03dee5f7490819ae784d942b4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-09T10:22:35Z","title_canon_sha256":"7eb349d6f36dcb0f672087b0936e50891d5062da1071c705dec5953411457883"},"schema_version":"1.0","source":{"id":"2011.04305","kind":"arxiv","version":5}},"canonical_sha256":"248d3acd03e8996e3ada4dfe20f1f6bfcff2197141327e551a79f5bd912ce39f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"248d3acd03e8996e3ada4dfe20f1f6bfcff2197141327e551a79f5bd912ce39f","first_computed_at":"2026-07-05T02:55:08.536649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:55:08.536649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f1h+laOHZUBsm8/mQxSEhOrPAt27amckf51uqiI9NPVZSvChtLdF6oLh1RQvdqq8+La+ot6ZvQHgUlJwWmasDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:55:08.537034Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.04305","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f55fc58c799d585236f039103f0f5f0177673ef138ce133cc8c6837ee211304","sha256:d24c90e7d5f8d9f62e7c321c55e48da43ecfee0310faeb182af0ea0b66e79e8a"],"state_sha256":"213c76664bd90fd7193bcca6e31c70d1e854347d27cc0264a32377ab6496d69d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Wrj8bfc/qi6/grHxCWzFmUVYdzG60ohx766YR0ur82kW81a+XOewc/+RNVkjOw4n8vMW6AtxISrX4BrZCNABg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T00:47:57.795026Z","bundle_sha256":"daef571c39671ed4d25d7020a48f794315e04ac005271b993a1a3124c08e7023"}}