{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:YKDPZH3ES5WHR2XCSCSFTDFFSJ","short_pith_number":"pith:YKDPZH3E","canonical_record":{"source":{"id":"1704.00260","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-02T08:01:30Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"c39260a660f9f25d9d52d9f0deb54b1eab5fe17eaf797fcedd12b27362cbe119","abstract_canon_sha256":"3c2d40458fb65665c0e1a997ce878cf3de11f0e634eb5c4575c47ad80b7ee723"},"schema_version":"1.0"},"canonical_sha256":"c286fc9f64976c78eae290a4598ca592558fac85b18ccc3641bcbe8f3d4591a3","source":{"kind":"arxiv","id":"1704.00260","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.00260","created_at":"2026-05-18T00:32:50Z"},{"alias_kind":"arxiv_version","alias_value":"1704.00260v2","created_at":"2026-05-18T00:32:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.00260","created_at":"2026-05-18T00:32:50Z"},{"alias_kind":"pith_short_12","alias_value":"YKDPZH3ES5WH","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"YKDPZH3ES5WHR2XC","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"YKDPZH3E","created_at":"2026-05-18T12:31:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:YKDPZH3ES5WHR2XCSCSFTDFFSJ","target":"record","payload":{"canonical_record":{"source":{"id":"1704.00260","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-02T08:01:30Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"c39260a660f9f25d9d52d9f0deb54b1eab5fe17eaf797fcedd12b27362cbe119","abstract_canon_sha256":"3c2d40458fb65665c0e1a997ce878cf3de11f0e634eb5c4575c47ad80b7ee723"},"schema_version":"1.0"},"canonical_sha256":"c286fc9f64976c78eae290a4598ca592558fac85b18ccc3641bcbe8f3d4591a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:50.924902Z","signature_b64":"6Oeu+hckP2nhY87LE7gWl5BO8r+rZ1VfLfh/qYqWER5NMnLvVkL17Oz/1FfrvhEbrxYaaRffq2/4t58pl2qaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c286fc9f64976c78eae290a4598ca592558fac85b18ccc3641bcbe8f3d4591a3","last_reissued_at":"2026-05-18T00:32:50.924256Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:50.924256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.00260","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:32:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZSppalrVMXgsuLT6/RaCZO4coTekWL9Jma/gjc+RUwJVaeBxmXSkDhn178efgUMvOmELnfsGpBRWBLO4sTKpCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T04:27:29.687703Z"},"content_sha256":"0b065ac971bba8d52227cdca69a6ed7df461513b6e70795eb3c508ed97e207f3","schema_version":"1.0","event_id":"sha256:0b065ac971bba8d52227cdca69a6ed7df461513b6e70795eb3c508ed97e207f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:YKDPZH3ES5WHR2XCSCSFTDFFSJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.CV","authors_text":"Derek Hoiem, Kevin Shih, Saurabh Singh, Tanmay Gupta","submitted_at":"2017-04-02T08:01:30Z","abstract_excerpt":"An important goal of computer vision is to build systems that learn visual representations over time that can be applied to many tasks. In this paper, we investigate a vision-language embedding as a core representation and show that it leads to better cross-task transfer than standard multi-task learning. In particular, the task of visual recognition is aligned to the task of visual question answering by forcing each to use the same word-region embeddings. We show this leads to greater inductive transfer from recognition to VQA than standard multitask learning. Visual recognition also improves"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.00260","kind":"arxiv","version":2},"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":"2026-05-18T00:32:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tNCHWSLTLTpknGKm8AbLR86jtxOQD35Lcp6L8knJP8RoFwx2eHwETAiEbTcE3Q6hybFN8TNqdgH/i4dM6cn3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T04:27:29.688407Z"},"content_sha256":"af738a33bc5bdded1609a77879f5b84bb1ac50b847344214286572b823e38d5b","schema_version":"1.0","event_id":"sha256:af738a33bc5bdded1609a77879f5b84bb1ac50b847344214286572b823e38d5b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YKDPZH3ES5WHR2XCSCSFTDFFSJ/bundle.json","state_url":"https://pith.science/pith/YKDPZH3ES5WHR2XCSCSFTDFFSJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YKDPZH3ES5WHR2XCSCSFTDFFSJ/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":"2026-05-26T04:27:29Z","links":{"resolver":"https://pith.science/pith/YKDPZH3ES5WHR2XCSCSFTDFFSJ","bundle":"https://pith.science/pith/YKDPZH3ES5WHR2XCSCSFTDFFSJ/bundle.json","state":"https://pith.science/pith/YKDPZH3ES5WHR2XCSCSFTDFFSJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YKDPZH3ES5WHR2XCSCSFTDFFSJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:YKDPZH3ES5WHR2XCSCSFTDFFSJ","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":"3c2d40458fb65665c0e1a997ce878cf3de11f0e634eb5c4575c47ad80b7ee723","cross_cats_sorted":["cs.AI","cs.LG","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-02T08:01:30Z","title_canon_sha256":"c39260a660f9f25d9d52d9f0deb54b1eab5fe17eaf797fcedd12b27362cbe119"},"schema_version":"1.0","source":{"id":"1704.00260","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.00260","created_at":"2026-05-18T00:32:50Z"},{"alias_kind":"arxiv_version","alias_value":"1704.00260v2","created_at":"2026-05-18T00:32:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.00260","created_at":"2026-05-18T00:32:50Z"},{"alias_kind":"pith_short_12","alias_value":"YKDPZH3ES5WH","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"YKDPZH3ES5WHR2XC","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"YKDPZH3E","created_at":"2026-05-18T12:31:56Z"}],"graph_snapshots":[{"event_id":"sha256:af738a33bc5bdded1609a77879f5b84bb1ac50b847344214286572b823e38d5b","target":"graph","created_at":"2026-05-18T00:32:50Z","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":"An important goal of computer vision is to build systems that learn visual representations over time that can be applied to many tasks. In this paper, we investigate a vision-language embedding as a core representation and show that it leads to better cross-task transfer than standard multi-task learning. In particular, the task of visual recognition is aligned to the task of visual question answering by forcing each to use the same word-region embeddings. We show this leads to greater inductive transfer from recognition to VQA than standard multitask learning. Visual recognition also improves","authors_text":"Derek Hoiem, Kevin Shih, Saurabh Singh, Tanmay Gupta","cross_cats":["cs.AI","cs.LG","cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-02T08:01:30Z","title":"Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.00260","kind":"arxiv","version":2},"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":"sha256:0b065ac971bba8d52227cdca69a6ed7df461513b6e70795eb3c508ed97e207f3","target":"record","created_at":"2026-05-18T00:32:50Z","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":"3c2d40458fb65665c0e1a997ce878cf3de11f0e634eb5c4575c47ad80b7ee723","cross_cats_sorted":["cs.AI","cs.LG","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-02T08:01:30Z","title_canon_sha256":"c39260a660f9f25d9d52d9f0deb54b1eab5fe17eaf797fcedd12b27362cbe119"},"schema_version":"1.0","source":{"id":"1704.00260","kind":"arxiv","version":2}},"canonical_sha256":"c286fc9f64976c78eae290a4598ca592558fac85b18ccc3641bcbe8f3d4591a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c286fc9f64976c78eae290a4598ca592558fac85b18ccc3641bcbe8f3d4591a3","first_computed_at":"2026-05-18T00:32:50.924256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:32:50.924256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6Oeu+hckP2nhY87LE7gWl5BO8r+rZ1VfLfh/qYqWER5NMnLvVkL17Oz/1FfrvhEbrxYaaRffq2/4t58pl2qaBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:32:50.924902Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.00260","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b065ac971bba8d52227cdca69a6ed7df461513b6e70795eb3c508ed97e207f3","sha256:af738a33bc5bdded1609a77879f5b84bb1ac50b847344214286572b823e38d5b"],"state_sha256":"c70d01f320ea2d5d597a304b033c1fe595234d4f7f293b917ada3fa238354f62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MJCnbkG+GOzqpPkuqJei4Qxef1kSS8B7NEZDT8FdGn3NC9mL8N7HPJlNd7FgxcOuKvZtW+nzo23WwdTZv9bMDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T04:27:29.692077Z","bundle_sha256":"ad028bb7290f09b877a0bebd45943c4c16c94658ad677d7a91b7b46a2e79f1ad"}}