{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PVKHF4WLSS5PDN3GHNJTQFL2B6","short_pith_number":"pith:PVKHF4WL","schema_version":"1.0","canonical_sha256":"7d5472f2cb94baf1b7663b5338157a0fa0f313a6233088235944eddaea8ccd26","source":{"kind":"arxiv","id":"2104.09757","version":2},"attestation_state":"computed","paper":{"title":"Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Divyansh Jha, Ivan Skorokhodov, Kai Yi, Mohamed Elhoseiny","submitted_at":"2021-04-20T04:34:28Z","abstract_excerpt":"We propose a novel loss for generative models, dubbed as GRaWD (Generative Random Walk Deviation), to improve learning representations of unexplored visual spaces. Quality learning representation of unseen classes (or styles) is critical to facilitate novel image generation and better generative understanding of unseen visual classes, i.e., zero-shot learning (ZSL). By generating representations of unseen classes based on their semantic descriptions, e.g., attributes or text, generative ZSL attempts to differentiate unseen from seen categories. The proposed GRaWD loss is defined by constructin"},"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":"2104.09757","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-20T04:34:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1208b3c656e67f2ca39092039b0cc43972e202f44482abb88c2b790b186769a2","abstract_canon_sha256":"cf6e2ae0829b30bea9da74a2eda31c5f9fcbb9261dc9315af9d13c768f03495a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:17:02.633771Z","signature_b64":"asSAFIuy4UGvY2wQmCkXDUF+rwmfOG/P/Kq8ON6MNutvWQD/TMPkSLQDQ2i8WQ4pw9tU7ykiTCdhg57UR+TlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d5472f2cb94baf1b7663b5338157a0fa0f313a6233088235944eddaea8ccd26","last_reissued_at":"2026-07-05T03:17:02.633373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:17:02.633373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Divyansh Jha, Ivan Skorokhodov, Kai Yi, Mohamed Elhoseiny","submitted_at":"2021-04-20T04:34:28Z","abstract_excerpt":"We propose a novel loss for generative models, dubbed as GRaWD (Generative Random Walk Deviation), to improve learning representations of unexplored visual spaces. Quality learning representation of unseen classes (or styles) is critical to facilitate novel image generation and better generative understanding of unseen visual classes, i.e., zero-shot learning (ZSL). By generating representations of unseen classes based on their semantic descriptions, e.g., attributes or text, generative ZSL attempts to differentiate unseen from seen categories. The proposed GRaWD loss is defined by constructin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09757","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.09757/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":"2104.09757","created_at":"2026-07-05T03:17:02.633435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.09757v2","created_at":"2026-07-05T03:17:02.633435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09757","created_at":"2026-07-05T03:17:02.633435+00:00"},{"alias_kind":"pith_short_12","alias_value":"PVKHF4WLSS5P","created_at":"2026-07-05T03:17:02.633435+00:00"},{"alias_kind":"pith_short_16","alias_value":"PVKHF4WLSS5PDN3G","created_at":"2026-07-05T03:17:02.633435+00:00"},{"alias_kind":"pith_short_8","alias_value":"PVKHF4WL","created_at":"2026-07-05T03:17:02.633435+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/PVKHF4WLSS5PDN3GHNJTQFL2B6","json":"https://pith.science/pith/PVKHF4WLSS5PDN3GHNJTQFL2B6.json","graph_json":"https://pith.science/api/pith-number/PVKHF4WLSS5PDN3GHNJTQFL2B6/graph.json","events_json":"https://pith.science/api/pith-number/PVKHF4WLSS5PDN3GHNJTQFL2B6/events.json","paper":"https://pith.science/paper/PVKHF4WL"},"agent_actions":{"view_html":"https://pith.science/pith/PVKHF4WLSS5PDN3GHNJTQFL2B6","download_json":"https://pith.science/pith/PVKHF4WLSS5PDN3GHNJTQFL2B6.json","view_paper":"https://pith.science/paper/PVKHF4WL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.09757&json=true","fetch_graph":"https://pith.science/api/pith-number/PVKHF4WLSS5PDN3GHNJTQFL2B6/graph.json","fetch_events":"https://pith.science/api/pith-number/PVKHF4WLSS5PDN3GHNJTQFL2B6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PVKHF4WLSS5PDN3GHNJTQFL2B6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PVKHF4WLSS5PDN3GHNJTQFL2B6/action/storage_attestation","attest_author":"https://pith.science/pith/PVKHF4WLSS5PDN3GHNJTQFL2B6/action/author_attestation","sign_citation":"https://pith.science/pith/PVKHF4WLSS5PDN3GHNJTQFL2B6/action/citation_signature","submit_replication":"https://pith.science/pith/PVKHF4WLSS5PDN3GHNJTQFL2B6/action/replication_record"}},"created_at":"2026-07-05T03:17:02.633435+00:00","updated_at":"2026-07-05T03:17:02.633435+00:00"}