{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2B3Y6TNNSY5JJ4BUZZSWWHMXSI","short_pith_number":"pith:2B3Y6TNN","schema_version":"1.0","canonical_sha256":"d0778f4dad963a94f034ce656b1d97921e397e86740cdf63168ffaac338cb335","source":{"kind":"arxiv","id":"1909.04101","version":3},"attestation_state":"computed","paper":{"title":"Neural Naturalist: Generating Fine-Grained Image Comparisons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Christine Kaeser-Chen, Maxwell Forbes, Piyush Sharma, Serge Belongie","submitted_at":"2019-09-09T18:54:40Z","abstract_excerpt":"We introduce the new Birds-to-Words dataset of 41k sentences describing fine-grained differences between photographs of birds. The language collected is highly detailed, while remaining understandable to the everyday observer (e.g., \"heart-shaped face,\" \"squat body\"). Paragraph-length descriptions naturally adapt to varying levels of taxonomic and visual distance---drawn from a novel stratified sampling approach---with the appropriate level of detail. We propose a new model called Neural Naturalist that uses a joint image encoding and comparative module to generate comparative language, and ev"},"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":"1909.04101","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-09T18:54:40Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0dc747bd5f90176b02c7103355bffbb2ce26f56e938969f335af2c3439e840bf","abstract_canon_sha256":"75d72f3134459b82d257edd5663d80b8e46f799119eb20d06639ac74180438ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:10.409248Z","signature_b64":"hSyJmmyxcDZRClScfeDrXPhbERuQzApy907yOyeOWgTSHEr3Oxkr99DPi0WhrFYVUaQjGKwWjRkMH/7PcpqlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0778f4dad963a94f034ce656b1d97921e397e86740cdf63168ffaac338cb335","last_reissued_at":"2026-07-05T00:19:10.408806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:10.408806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Naturalist: Generating Fine-Grained Image Comparisons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Christine Kaeser-Chen, Maxwell Forbes, Piyush Sharma, Serge Belongie","submitted_at":"2019-09-09T18:54:40Z","abstract_excerpt":"We introduce the new Birds-to-Words dataset of 41k sentences describing fine-grained differences between photographs of birds. The language collected is highly detailed, while remaining understandable to the everyday observer (e.g., \"heart-shaped face,\" \"squat body\"). Paragraph-length descriptions naturally adapt to varying levels of taxonomic and visual distance---drawn from a novel stratified sampling approach---with the appropriate level of detail. We propose a new model called Neural Naturalist that uses a joint image encoding and comparative module to generate comparative language, and ev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.04101","kind":"arxiv","version":3},"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/1909.04101/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":"1909.04101","created_at":"2026-07-05T00:19:10.408862+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.04101v3","created_at":"2026-07-05T00:19:10.408862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.04101","created_at":"2026-07-05T00:19:10.408862+00:00"},{"alias_kind":"pith_short_12","alias_value":"2B3Y6TNNSY5J","created_at":"2026-07-05T00:19:10.408862+00:00"},{"alias_kind":"pith_short_16","alias_value":"2B3Y6TNNSY5JJ4BU","created_at":"2026-07-05T00:19:10.408862+00:00"},{"alias_kind":"pith_short_8","alias_value":"2B3Y6TNN","created_at":"2026-07-05T00:19:10.408862+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.00356","citing_title":"Analyze-Prompt-Reason: A Collaborative Agent-Based Framework for Multi-Image Vision-Language Reasoning","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2B3Y6TNNSY5JJ4BUZZSWWHMXSI","json":"https://pith.science/pith/2B3Y6TNNSY5JJ4BUZZSWWHMXSI.json","graph_json":"https://pith.science/api/pith-number/2B3Y6TNNSY5JJ4BUZZSWWHMXSI/graph.json","events_json":"https://pith.science/api/pith-number/2B3Y6TNNSY5JJ4BUZZSWWHMXSI/events.json","paper":"https://pith.science/paper/2B3Y6TNN"},"agent_actions":{"view_html":"https://pith.science/pith/2B3Y6TNNSY5JJ4BUZZSWWHMXSI","download_json":"https://pith.science/pith/2B3Y6TNNSY5JJ4BUZZSWWHMXSI.json","view_paper":"https://pith.science/paper/2B3Y6TNN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.04101&json=true","fetch_graph":"https://pith.science/api/pith-number/2B3Y6TNNSY5JJ4BUZZSWWHMXSI/graph.json","fetch_events":"https://pith.science/api/pith-number/2B3Y6TNNSY5JJ4BUZZSWWHMXSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2B3Y6TNNSY5JJ4BUZZSWWHMXSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2B3Y6TNNSY5JJ4BUZZSWWHMXSI/action/storage_attestation","attest_author":"https://pith.science/pith/2B3Y6TNNSY5JJ4BUZZSWWHMXSI/action/author_attestation","sign_citation":"https://pith.science/pith/2B3Y6TNNSY5JJ4BUZZSWWHMXSI/action/citation_signature","submit_replication":"https://pith.science/pith/2B3Y6TNNSY5JJ4BUZZSWWHMXSI/action/replication_record"}},"created_at":"2026-07-05T00:19:10.408862+00:00","updated_at":"2026-07-05T00:19:10.408862+00:00"}