{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:XCFOPYKEFUKRKC4FDS5XB2KOVK","short_pith_number":"pith:XCFOPYKE","canonical_record":{"source":{"id":"1705.08386","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-23T16:06:32Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"972383e54da6a7448030f772c868102f475211fa30220cc8a1ef4c7c34ce197c","abstract_canon_sha256":"eadb0d12754f953c6bc507172f4ed82eacb8f493d8dfa16cd8567af384a3ba52"},"schema_version":"1.0"},"canonical_sha256":"b88ae7e1442d15150b851cbb70e94eaa932cb58255d73fb1593e1ff54cd5b752","source":{"kind":"arxiv","id":"1705.08386","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08386","created_at":"2026-05-18T00:43:15Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08386v2","created_at":"2026-05-18T00:43:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08386","created_at":"2026-05-18T00:43:15Z"},{"alias_kind":"pith_short_12","alias_value":"XCFOPYKEFUKR","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XCFOPYKEFUKRKC4F","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XCFOPYKE","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:XCFOPYKEFUKRKC4FDS5XB2KOVK","target":"record","payload":{"canonical_record":{"source":{"id":"1705.08386","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-23T16:06:32Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"972383e54da6a7448030f772c868102f475211fa30220cc8a1ef4c7c34ce197c","abstract_canon_sha256":"eadb0d12754f953c6bc507172f4ed82eacb8f493d8dfa16cd8567af384a3ba52"},"schema_version":"1.0"},"canonical_sha256":"b88ae7e1442d15150b851cbb70e94eaa932cb58255d73fb1593e1ff54cd5b752","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:15.415059Z","signature_b64":"J/bBU5MWrNNsGfhEanYuhrUEkkqwuEKm6iXeOAZIqFZ2eyjlAdxSYCR4Q9NOZhjT/fciSmsQoYqfQZWXzejlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b88ae7e1442d15150b851cbb70e94eaa932cb58255d73fb1593e1ff54cd5b752","last_reissued_at":"2026-05-18T00:43:15.414562Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:15.414562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.08386","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":"2026-05-18T00:43:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3KlB1ycakD62hT3kmXxbomiCeB+Ouuwe8D/vE3xsiaP4nMVyf+dcJZMcbBSlpVe6zuKIbAEa/iYBBfoHTKMKAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T14:03:01.016108Z"},"content_sha256":"53ebc29ebc9e669db951a4f5618706d37276aa28cbf3f15658ac0e8adb86d7e4","schema_version":"1.0","event_id":"sha256:53ebc29ebc9e669db951a4f5618706d37276aa28cbf3f15658ac0e8adb86d7e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:XCFOPYKEFUKRKC4FDS5XB2KOVK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Better Text Understanding Through Image-To-Text Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Damien Vincent, Karol Kurach, Michal Jastrzebski, Olivier Bousquet, Olivier Teytaud, Philip Haeusser, Sylvain Gelly","submitted_at":"2017-05-23T16:06:32Z","abstract_excerpt":"Generic text embeddings are successfully used in a variety of tasks. However, they are often learnt by capturing the co-occurrence structure from pure text corpora, resulting in limitations of their ability to generalize. In this paper, we explore models that incorporate visual information into the text representation. Based on comprehensive ablation studies, we propose a conceptually simple, yet well performing architecture. It outperforms previous multimodal approaches on a set of well established benchmarks. We also improve the state-of-the-art results for image-related text datasets, using"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08386","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":"2026-05-18T00:43:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Piif1XwpWlbI0p+eciS7ORy60n1Q++e0mnVaJ3y1kuHXzRgZuVJQjyHgtFziDF4F/yM/DK8rR36DcJfe6Y0MBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T14:03:01.016469Z"},"content_sha256":"47c51cf00cc10e59013a6e43759e9bdcf37d00b88a325d1204f9623a7f755852","schema_version":"1.0","event_id":"sha256:47c51cf00cc10e59013a6e43759e9bdcf37d00b88a325d1204f9623a7f755852"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XCFOPYKEFUKRKC4FDS5XB2KOVK/bundle.json","state_url":"https://pith.science/pith/XCFOPYKEFUKRKC4FDS5XB2KOVK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XCFOPYKEFUKRKC4FDS5XB2KOVK/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":"2026-06-01T14:03:01Z","links":{"resolver":"https://pith.science/pith/XCFOPYKEFUKRKC4FDS5XB2KOVK","bundle":"https://pith.science/pith/XCFOPYKEFUKRKC4FDS5XB2KOVK/bundle.json","state":"https://pith.science/pith/XCFOPYKEFUKRKC4FDS5XB2KOVK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XCFOPYKEFUKRKC4FDS5XB2KOVK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:XCFOPYKEFUKRKC4FDS5XB2KOVK","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":"eadb0d12754f953c6bc507172f4ed82eacb8f493d8dfa16cd8567af384a3ba52","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-23T16:06:32Z","title_canon_sha256":"972383e54da6a7448030f772c868102f475211fa30220cc8a1ef4c7c34ce197c"},"schema_version":"1.0","source":{"id":"1705.08386","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08386","created_at":"2026-05-18T00:43:15Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08386v2","created_at":"2026-05-18T00:43:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08386","created_at":"2026-05-18T00:43:15Z"},{"alias_kind":"pith_short_12","alias_value":"XCFOPYKEFUKR","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XCFOPYKEFUKRKC4F","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XCFOPYKE","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:47c51cf00cc10e59013a6e43759e9bdcf37d00b88a325d1204f9623a7f755852","target":"graph","created_at":"2026-05-18T00:43:15Z","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":"Generic text embeddings are successfully used in a variety of tasks. However, they are often learnt by capturing the co-occurrence structure from pure text corpora, resulting in limitations of their ability to generalize. In this paper, we explore models that incorporate visual information into the text representation. Based on comprehensive ablation studies, we propose a conceptually simple, yet well performing architecture. It outperforms previous multimodal approaches on a set of well established benchmarks. We also improve the state-of-the-art results for image-related text datasets, using","authors_text":"Damien Vincent, Karol Kurach, Michal Jastrzebski, Olivier Bousquet, Olivier Teytaud, Philip Haeusser, Sylvain Gelly","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-23T16:06:32Z","title":"Better Text Understanding Through Image-To-Text Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08386","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":"sha256:53ebc29ebc9e669db951a4f5618706d37276aa28cbf3f15658ac0e8adb86d7e4","target":"record","created_at":"2026-05-18T00:43:15Z","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":"eadb0d12754f953c6bc507172f4ed82eacb8f493d8dfa16cd8567af384a3ba52","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-23T16:06:32Z","title_canon_sha256":"972383e54da6a7448030f772c868102f475211fa30220cc8a1ef4c7c34ce197c"},"schema_version":"1.0","source":{"id":"1705.08386","kind":"arxiv","version":2}},"canonical_sha256":"b88ae7e1442d15150b851cbb70e94eaa932cb58255d73fb1593e1ff54cd5b752","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b88ae7e1442d15150b851cbb70e94eaa932cb58255d73fb1593e1ff54cd5b752","first_computed_at":"2026-05-18T00:43:15.414562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:15.414562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J/bBU5MWrNNsGfhEanYuhrUEkkqwuEKm6iXeOAZIqFZ2eyjlAdxSYCR4Q9NOZhjT/fciSmsQoYqfQZWXzejlDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:15.415059Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.08386","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53ebc29ebc9e669db951a4f5618706d37276aa28cbf3f15658ac0e8adb86d7e4","sha256:47c51cf00cc10e59013a6e43759e9bdcf37d00b88a325d1204f9623a7f755852"],"state_sha256":"97afdc0ec2934f2c0e5cbf18b5e1fd5048b31dab640729c0193f3d7258af6eec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kp7iClEbMP/ylHKHMUHnxkbtt2g8cqqxRtcvLmPmciigZjHvkSM3b3QmCEUvPicabQmwWLilD1aKT95VSNsdDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T14:03:01.018433Z","bundle_sha256":"75d9a565254be1c16bfed27477d8d8d6f8893510c2882e87f3f26d43e6112ca4"}}