{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:VMHA5MYLVFYWN3YOYFBK3D6H6V","short_pith_number":"pith:VMHA5MYL","canonical_record":{"source":{"id":"1706.06706","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-20T23:55:32Z","cross_cats_sorted":[],"title_canon_sha256":"63904913197c2b9f2985da43f46863376665c3fb24fcf60f21fad1b84183c453","abstract_canon_sha256":"9a6d38a839287c21f6c4d1ff330bf98e668df07c846d3674295b7d1bf68a09ba"},"schema_version":"1.0"},"canonical_sha256":"ab0e0eb30ba97166ef0ec142ad8fc7f557ba858ee2698f94d25314c6d5deddbe","source":{"kind":"arxiv","id":"1706.06706","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.06706","created_at":"2026-05-18T00:41:57Z"},{"alias_kind":"arxiv_version","alias_value":"1706.06706v1","created_at":"2026-05-18T00:41:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.06706","created_at":"2026-05-18T00:41:57Z"},{"alias_kind":"pith_short_12","alias_value":"VMHA5MYLVFYW","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VMHA5MYLVFYWN3YO","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VMHA5MYL","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:VMHA5MYLVFYWN3YOYFBK3D6H6V","target":"record","payload":{"canonical_record":{"source":{"id":"1706.06706","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-20T23:55:32Z","cross_cats_sorted":[],"title_canon_sha256":"63904913197c2b9f2985da43f46863376665c3fb24fcf60f21fad1b84183c453","abstract_canon_sha256":"9a6d38a839287c21f6c4d1ff330bf98e668df07c846d3674295b7d1bf68a09ba"},"schema_version":"1.0"},"canonical_sha256":"ab0e0eb30ba97166ef0ec142ad8fc7f557ba858ee2698f94d25314c6d5deddbe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:57.068565Z","signature_b64":"WKj5HGtztrrMl8B5+QuyH9MR1RT4XujLz/NJgzBtf9LjnGnFXMcSBefNxP6mZiQx3nCpHwjiQHSnvlr6QZ2PDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab0e0eb30ba97166ef0ec142ad8fc7f557ba858ee2698f94d25314c6d5deddbe","last_reissued_at":"2026-05-18T00:41:57.067862Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:57.067862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.06706","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":"2026-05-18T00:41:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N08B2d55OCipLAmj+i7TNq2RNYtebK0ZAZo97AzqMCDOnZKHJuYMmK2ASLwoNaE7vPTQodqNA+TrqNSkUNueCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T08:41:31.184921Z"},"content_sha256":"067d396446f0d9344cd22c1e1b28ad0c8afd739041572952e7f4c4c3666ffa39","schema_version":"1.0","event_id":"sha256:067d396446f0d9344cd22c1e1b28ad0c8afd739041572952e7f4c4c3666ffa39"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:VMHA5MYLVFYWN3YOYFBK3D6H6V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compact Tensor Pooling for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anima Anandkumar, Tommaso Furlanello, Yang Shi","submitted_at":"2017-06-20T23:55:32Z","abstract_excerpt":"Performing high level cognitive tasks requires the integration of feature maps with drastically different structure. In Visual Question Answering (VQA) image descriptors have spatial structures, while lexical inputs inherently follow a temporal sequence. The recently proposed Multimodal Compact Bilinear pooling (MCB) forms the outer products, via count-sketch approximation, of the visual and textual representation at each spatial location. While this procedure preserves spatial information locally, outer-products are taken independently for each fiber of the activation tensor, and therefore do"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.06706","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":""},"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":"2026-05-18T00:41:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WkhQkO3cID7ji8YeLWHSIdoLg0Kz8SBAFNhLhkW2ixsaagd30USh3PBHZXkIIkPSk5p3VTpockBE7eatWOf9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T08:41:31.185278Z"},"content_sha256":"b28125e1a82c3ff6dedd6544ae8e3292366b46be64e61cc897493aff2e4e155f","schema_version":"1.0","event_id":"sha256:b28125e1a82c3ff6dedd6544ae8e3292366b46be64e61cc897493aff2e4e155f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VMHA5MYLVFYWN3YOYFBK3D6H6V/bundle.json","state_url":"https://pith.science/pith/VMHA5MYLVFYWN3YOYFBK3D6H6V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VMHA5MYLVFYWN3YOYFBK3D6H6V/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":"2026-05-31T08:41:31Z","links":{"resolver":"https://pith.science/pith/VMHA5MYLVFYWN3YOYFBK3D6H6V","bundle":"https://pith.science/pith/VMHA5MYLVFYWN3YOYFBK3D6H6V/bundle.json","state":"https://pith.science/pith/VMHA5MYLVFYWN3YOYFBK3D6H6V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VMHA5MYLVFYWN3YOYFBK3D6H6V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:VMHA5MYLVFYWN3YOYFBK3D6H6V","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":"9a6d38a839287c21f6c4d1ff330bf98e668df07c846d3674295b7d1bf68a09ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-20T23:55:32Z","title_canon_sha256":"63904913197c2b9f2985da43f46863376665c3fb24fcf60f21fad1b84183c453"},"schema_version":"1.0","source":{"id":"1706.06706","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.06706","created_at":"2026-05-18T00:41:57Z"},{"alias_kind":"arxiv_version","alias_value":"1706.06706v1","created_at":"2026-05-18T00:41:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.06706","created_at":"2026-05-18T00:41:57Z"},{"alias_kind":"pith_short_12","alias_value":"VMHA5MYLVFYW","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VMHA5MYLVFYWN3YO","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VMHA5MYL","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:b28125e1a82c3ff6dedd6544ae8e3292366b46be64e61cc897493aff2e4e155f","target":"graph","created_at":"2026-05-18T00:41:57Z","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"},"paper":{"abstract_excerpt":"Performing high level cognitive tasks requires the integration of feature maps with drastically different structure. In Visual Question Answering (VQA) image descriptors have spatial structures, while lexical inputs inherently follow a temporal sequence. The recently proposed Multimodal Compact Bilinear pooling (MCB) forms the outer products, via count-sketch approximation, of the visual and textual representation at each spatial location. While this procedure preserves spatial information locally, outer-products are taken independently for each fiber of the activation tensor, and therefore do","authors_text":"Anima Anandkumar, Tommaso Furlanello, Yang Shi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-20T23:55:32Z","title":"Compact Tensor Pooling for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.06706","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":"sha256:067d396446f0d9344cd22c1e1b28ad0c8afd739041572952e7f4c4c3666ffa39","target":"record","created_at":"2026-05-18T00:41:57Z","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":"9a6d38a839287c21f6c4d1ff330bf98e668df07c846d3674295b7d1bf68a09ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-20T23:55:32Z","title_canon_sha256":"63904913197c2b9f2985da43f46863376665c3fb24fcf60f21fad1b84183c453"},"schema_version":"1.0","source":{"id":"1706.06706","kind":"arxiv","version":1}},"canonical_sha256":"ab0e0eb30ba97166ef0ec142ad8fc7f557ba858ee2698f94d25314c6d5deddbe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab0e0eb30ba97166ef0ec142ad8fc7f557ba858ee2698f94d25314c6d5deddbe","first_computed_at":"2026-05-18T00:41:57.067862Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:41:57.067862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WKj5HGtztrrMl8B5+QuyH9MR1RT4XujLz/NJgzBtf9LjnGnFXMcSBefNxP6mZiQx3nCpHwjiQHSnvlr6QZ2PDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:41:57.068565Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.06706","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:067d396446f0d9344cd22c1e1b28ad0c8afd739041572952e7f4c4c3666ffa39","sha256:b28125e1a82c3ff6dedd6544ae8e3292366b46be64e61cc897493aff2e4e155f"],"state_sha256":"634467ef062a1fd9a4ee2b4c7f8af495e8aff81e759edd612f9d3c53fe877ae5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x0OHkJqwjOqECXAdq4X1/HHEIJRCr5hg9J0IMBQfmizfh4Kht14SqOWgvBpjGPbVJlZaW9av2j1BPAdjoC9jDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T08:41:31.187696Z","bundle_sha256":"49faa2bd856c65f72eb09af450e9ad4eb60466e3a134df9c0274c1cdcdabb535"}}