{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PAMFODQ4JAYECSEHBQZ4GPBWHL","short_pith_number":"pith:PAMFODQ4","schema_version":"1.0","canonical_sha256":"7818570e1c48304148870c33c33c363aca10940c27084a63bbba7b1734faf747","source":{"kind":"arxiv","id":"2002.02734","version":1},"attestation_state":"computed","paper":{"title":"Incorporating Visual Semantics into Sentence Representations within a Grounded Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Piwowarski, Eloi Zablocki, Laure Soulier, Patrick Bordes, Patrick Gallinari","submitted_at":"2020-02-07T12:26:41Z","abstract_excerpt":"Language grounding is an active field aiming at enriching textual representations with visual information. Generally, textual and visual elements are embedded in the same representation space, which implicitly assumes a one-to-one correspondence between modalities. This hypothesis does not hold when representing words, and becomes problematic when used to learn sentence representations --- the focus of this paper --- as a visual scene can be described by a wide variety of sentences. To overcome this limitation, we propose to transfer visual information to textual representations by learning an"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2002.02734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-07T12:26:41Z","cross_cats_sorted":[],"title_canon_sha256":"33f42f3b1b362ca3c2801c9e10b8a4ddef4567db2ae5103b8b734e12b8e873e7","abstract_canon_sha256":"0a5c82723fe2aea585352c69b3ddefc50e99ff2cd1dc4bdc0fce88145070b251"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:38:58.451212Z","signature_b64":"zuoH/QcVqw5fi1Ywuo8kATzhQGDDBtsyED3MC/yMS2U/ZShdwD6Y3wFRVXjZ2qMh/56xxMzwrIPmgGU2QlxGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7818570e1c48304148870c33c33c363aca10940c27084a63bbba7b1734faf747","last_reissued_at":"2026-07-05T00:38:58.450725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:38:58.450725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incorporating Visual Semantics into Sentence Representations within a Grounded Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Piwowarski, Eloi Zablocki, Laure Soulier, Patrick Bordes, Patrick Gallinari","submitted_at":"2020-02-07T12:26:41Z","abstract_excerpt":"Language grounding is an active field aiming at enriching textual representations with visual information. Generally, textual and visual elements are embedded in the same representation space, which implicitly assumes a one-to-one correspondence between modalities. This hypothesis does not hold when representing words, and becomes problematic when used to learn sentence representations --- the focus of this paper --- as a visual scene can be described by a wide variety of sentences. To overcome this limitation, we propose to transfer visual information to textual representations by learning an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.02734","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/2002.02734/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2002.02734","created_at":"2026-07-05T00:38:58.450785+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.02734v1","created_at":"2026-07-05T00:38:58.450785+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.02734","created_at":"2026-07-05T00:38:58.450785+00:00"},{"alias_kind":"pith_short_12","alias_value":"PAMFODQ4JAYE","created_at":"2026-07-05T00:38:58.450785+00:00"},{"alias_kind":"pith_short_16","alias_value":"PAMFODQ4JAYECSEH","created_at":"2026-07-05T00:38:58.450785+00:00"},{"alias_kind":"pith_short_8","alias_value":"PAMFODQ4","created_at":"2026-07-05T00:38:58.450785+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21096","citing_title":"DALR: Dual-level Alignment Learning for Multimodal Sentence Representation Learning","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PAMFODQ4JAYECSEHBQZ4GPBWHL","json":"https://pith.science/pith/PAMFODQ4JAYECSEHBQZ4GPBWHL.json","graph_json":"https://pith.science/api/pith-number/PAMFODQ4JAYECSEHBQZ4GPBWHL/graph.json","events_json":"https://pith.science/api/pith-number/PAMFODQ4JAYECSEHBQZ4GPBWHL/events.json","paper":"https://pith.science/paper/PAMFODQ4"},"agent_actions":{"view_html":"https://pith.science/pith/PAMFODQ4JAYECSEHBQZ4GPBWHL","download_json":"https://pith.science/pith/PAMFODQ4JAYECSEHBQZ4GPBWHL.json","view_paper":"https://pith.science/paper/PAMFODQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.02734&json=true","fetch_graph":"https://pith.science/api/pith-number/PAMFODQ4JAYECSEHBQZ4GPBWHL/graph.json","fetch_events":"https://pith.science/api/pith-number/PAMFODQ4JAYECSEHBQZ4GPBWHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PAMFODQ4JAYECSEHBQZ4GPBWHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PAMFODQ4JAYECSEHBQZ4GPBWHL/action/storage_attestation","attest_author":"https://pith.science/pith/PAMFODQ4JAYECSEHBQZ4GPBWHL/action/author_attestation","sign_citation":"https://pith.science/pith/PAMFODQ4JAYECSEHBQZ4GPBWHL/action/citation_signature","submit_replication":"https://pith.science/pith/PAMFODQ4JAYECSEHBQZ4GPBWHL/action/replication_record"}},"created_at":"2026-07-05T00:38:58.450785+00:00","updated_at":"2026-07-05T00:38:58.450785+00:00"}