{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3ZDYHGGWCDONIK4WI3OVZ765KR","short_pith_number":"pith:3ZDYHGGW","schema_version":"1.0","canonical_sha256":"de478398d610dcd42b9646dd5cffdd547fedb8f697f5e732207a44f6f214eab1","source":{"kind":"arxiv","id":"2007.00145","version":1},"attestation_state":"computed","paper":{"title":"Modality-Agnostic Attention Fusion for visual search with text feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Eric Dodds, Jack Culpepper, Kofi Boakye, Simao Herdade, Yang Zhang","submitted_at":"2020-06-30T22:55:02Z","abstract_excerpt":"Image retrieval with natural language feedback offers the promise of catalog search based on fine-grained visual features that go beyond objects and binary attributes, facilitating real-world applications such as e-commerce. Our Modality-Agnostic Attention Fusion (MAAF) model combines image and text features and outperforms existing approaches on two visual search with modifying phrase datasets, Fashion IQ and CSS, and performs competitively on a dataset with only single-word modifications, Fashion200k. We also introduce two new challenging benchmarks adapted from Birds-to-Words and Spot-the-D"},"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":"2007.00145","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-30T22:55:02Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"34dd571ccbcc56d61f0fd0f2b81dd2f16a38249b959d29923b06c98cbb7c097d","abstract_canon_sha256":"9f254162b188a51b17ea506faab28c5ec28b25b813f4f11454a146374f3e2885"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:15:28.744537Z","signature_b64":"BoBS4hg5ZgctAms2x8h+K/vFG1K2BEZ42P0O+cDvKTcThUuM8/zh6NnALKI5Y9+XkGtMuCcJN4+eRB5evjghDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de478398d610dcd42b9646dd5cffdd547fedb8f697f5e732207a44f6f214eab1","last_reissued_at":"2026-07-05T01:15:28.744041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:15:28.744041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modality-Agnostic Attention Fusion for visual search with text feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Eric Dodds, Jack Culpepper, Kofi Boakye, Simao Herdade, Yang Zhang","submitted_at":"2020-06-30T22:55:02Z","abstract_excerpt":"Image retrieval with natural language feedback offers the promise of catalog search based on fine-grained visual features that go beyond objects and binary attributes, facilitating real-world applications such as e-commerce. Our Modality-Agnostic Attention Fusion (MAAF) model combines image and text features and outperforms existing approaches on two visual search with modifying phrase datasets, Fashion IQ and CSS, and performs competitively on a dataset with only single-word modifications, Fashion200k. We also introduce two new challenging benchmarks adapted from Birds-to-Words and Spot-the-D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.00145","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/2007.00145/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":"2007.00145","created_at":"2026-07-05T01:15:28.744104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.00145v1","created_at":"2026-07-05T01:15:28.744104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.00145","created_at":"2026-07-05T01:15:28.744104+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZDYHGGWCDON","created_at":"2026-07-05T01:15:28.744104+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZDYHGGWCDONIK4W","created_at":"2026-07-05T01:15:28.744104+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZDYHGGW","created_at":"2026-07-05T01:15:28.744104+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18992","citing_title":"Show, Don't Ask: Generative Visual Disambiguation for Composed Image Retrieval with Turn-Valid Coverage","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07032","citing_title":"Never Seen Before: Benchmarking Genuine Zero-Shot Composed Image Retrieval with Consistent Video-Sourced Datasets","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00374","citing_title":"Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24634","citing_title":"Resolving Ambiguity in Composed Image Retrieval via Calibrated Interaction","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ZDYHGGWCDONIK4WI3OVZ765KR","json":"https://pith.science/pith/3ZDYHGGWCDONIK4WI3OVZ765KR.json","graph_json":"https://pith.science/api/pith-number/3ZDYHGGWCDONIK4WI3OVZ765KR/graph.json","events_json":"https://pith.science/api/pith-number/3ZDYHGGWCDONIK4WI3OVZ765KR/events.json","paper":"https://pith.science/paper/3ZDYHGGW"},"agent_actions":{"view_html":"https://pith.science/pith/3ZDYHGGWCDONIK4WI3OVZ765KR","download_json":"https://pith.science/pith/3ZDYHGGWCDONIK4WI3OVZ765KR.json","view_paper":"https://pith.science/paper/3ZDYHGGW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.00145&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZDYHGGWCDONIK4WI3OVZ765KR/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZDYHGGWCDONIK4WI3OVZ765KR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZDYHGGWCDONIK4WI3OVZ765KR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZDYHGGWCDONIK4WI3OVZ765KR/action/storage_attestation","attest_author":"https://pith.science/pith/3ZDYHGGWCDONIK4WI3OVZ765KR/action/author_attestation","sign_citation":"https://pith.science/pith/3ZDYHGGWCDONIK4WI3OVZ765KR/action/citation_signature","submit_replication":"https://pith.science/pith/3ZDYHGGWCDONIK4WI3OVZ765KR/action/replication_record"}},"created_at":"2026-07-05T01:15:28.744104+00:00","updated_at":"2026-07-05T01:15:28.744104+00:00"}