{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:27YHUDDWREUNF4TTOUA4L2BKHL","short_pith_number":"pith:27YHUDDW","schema_version":"1.0","canonical_sha256":"d7f07a0c768928d2f2737501c5e82a3ad62bbf7e947bc302cc15e2033e347a6a","source":{"kind":"arxiv","id":"1804.05018","version":1},"attestation_state":"computed","paper":{"title":"Comparatives, Quantifiers, Proportions: A Multi-Task Model for the Learning of Quantities from Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Ionut-Teodor Sorodoc, Raffaella Bernardi, Sandro Pezzelle","submitted_at":"2018-04-13T16:36:52Z","abstract_excerpt":"The present work investigates whether different quantification mechanisms (set comparison, vague quantification, and proportional estimation) can be jointly learned from visual scenes by a multi-task computational model. The motivation is that, in humans, these processes underlie the same cognitive, non-symbolic ability, which allows an automatic estimation and comparison of set magnitudes. We show that when information about lower-complexity tasks is available, the higher-level proportional task becomes more accurate than when performed in isolation. Moreover, the multi-task model is able to "},"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":"1804.05018","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-13T16:36:52Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"aecb83bea8d7434d73b08d0478483818d55874119f60670f8eade7cbdcb7cd8d","abstract_canon_sha256":"20fe65da070a396c7bb7938b4f447d008dde108555f89a6a0921b55f2623e6a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:32.490887Z","signature_b64":"pZ2JUIBj1CeO+BIc9TLu+c4s9HeRNbhRLmj3wYJjGQMSjjqyCqgjUgl63yRtGKvrAr5ZGWQWrxSKtjLyp1CIBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7f07a0c768928d2f2737501c5e82a3ad62bbf7e947bc302cc15e2033e347a6a","last_reissued_at":"2026-05-18T00:18:32.490422Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:32.490422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparatives, Quantifiers, Proportions: A Multi-Task Model for the Learning of Quantities from Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Ionut-Teodor Sorodoc, Raffaella Bernardi, Sandro Pezzelle","submitted_at":"2018-04-13T16:36:52Z","abstract_excerpt":"The present work investigates whether different quantification mechanisms (set comparison, vague quantification, and proportional estimation) can be jointly learned from visual scenes by a multi-task computational model. The motivation is that, in humans, these processes underlie the same cognitive, non-symbolic ability, which allows an automatic estimation and comparison of set magnitudes. We show that when information about lower-complexity tasks is available, the higher-level proportional task becomes more accurate than when performed in isolation. Moreover, the multi-task model is able to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05018","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1804.05018","created_at":"2026-05-18T00:18:32.490497+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.05018v1","created_at":"2026-05-18T00:18:32.490497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05018","created_at":"2026-05-18T00:18:32.490497+00:00"},{"alias_kind":"pith_short_12","alias_value":"27YHUDDWREUN","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"27YHUDDWREUNF4TT","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"27YHUDDW","created_at":"2026-05-18T12:31:59.375834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/27YHUDDWREUNF4TTOUA4L2BKHL","json":"https://pith.science/pith/27YHUDDWREUNF4TTOUA4L2BKHL.json","graph_json":"https://pith.science/api/pith-number/27YHUDDWREUNF4TTOUA4L2BKHL/graph.json","events_json":"https://pith.science/api/pith-number/27YHUDDWREUNF4TTOUA4L2BKHL/events.json","paper":"https://pith.science/paper/27YHUDDW"},"agent_actions":{"view_html":"https://pith.science/pith/27YHUDDWREUNF4TTOUA4L2BKHL","download_json":"https://pith.science/pith/27YHUDDWREUNF4TTOUA4L2BKHL.json","view_paper":"https://pith.science/paper/27YHUDDW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.05018&json=true","fetch_graph":"https://pith.science/api/pith-number/27YHUDDWREUNF4TTOUA4L2BKHL/graph.json","fetch_events":"https://pith.science/api/pith-number/27YHUDDWREUNF4TTOUA4L2BKHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/27YHUDDWREUNF4TTOUA4L2BKHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/27YHUDDWREUNF4TTOUA4L2BKHL/action/storage_attestation","attest_author":"https://pith.science/pith/27YHUDDWREUNF4TTOUA4L2BKHL/action/author_attestation","sign_citation":"https://pith.science/pith/27YHUDDWREUNF4TTOUA4L2BKHL/action/citation_signature","submit_replication":"https://pith.science/pith/27YHUDDWREUNF4TTOUA4L2BKHL/action/replication_record"}},"created_at":"2026-05-18T00:18:32.490497+00:00","updated_at":"2026-05-18T00:18:32.490497+00:00"}