{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5IE7CSCEKAZ5ZZSQXKRNPDD4S2","short_pith_number":"pith:5IE7CSCE","schema_version":"1.0","canonical_sha256":"ea09f148445033dce650baa2d78c7c969cc88ab93e24f500f240f6a27aebaeaf","source":{"kind":"arxiv","id":"2112.07910","version":2},"attestation_state":"computed","paper":{"title":"Decoupling Zero-Shot Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dengxin Dai, Gui-Song Xia, Jian Ding, Nan Xue","submitted_at":"2021-12-15T06:21:47Z","abstract_excerpt":"Zero-shot semantic segmentation (ZS3) aims to segment the novel categories that have not been seen in the training. Existing works formulate ZS3 as a pixel-level zeroshot classification problem, and transfer semantic knowledge from seen classes to unseen ones with the help of language models pre-trained only with texts. While simple, the pixel-level ZS3 formulation shows the limited capability to integrate vision-language models that are often pre-trained with image-text pairs and currently demonstrate great potential for vision tasks. Inspired by the observation that humans often perform segm"},"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":"2112.07910","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-15T06:21:47Z","cross_cats_sorted":[],"title_canon_sha256":"e8ceac566953625f19e2e739a772a03508ffc9891eaaf353e3b10cd0b89f8723","abstract_canon_sha256":"31abded616c2e566ce43898aff723ec33be0890b53db86dbcfdcabe73dbe8e3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:15:00.340667Z","signature_b64":"XR2fNKQS6nxglLEkkN3m2mSAPwPVZyKhgUP6LKQNGqr4K5Mkj8bRuE1ck0pJs/NurmzcX8Osp4y/cjG3jtQWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea09f148445033dce650baa2d78c7c969cc88ab93e24f500f240f6a27aebaeaf","last_reissued_at":"2026-07-05T04:15:00.340205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:15:00.340205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupling Zero-Shot Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dengxin Dai, Gui-Song Xia, Jian Ding, Nan Xue","submitted_at":"2021-12-15T06:21:47Z","abstract_excerpt":"Zero-shot semantic segmentation (ZS3) aims to segment the novel categories that have not been seen in the training. Existing works formulate ZS3 as a pixel-level zeroshot classification problem, and transfer semantic knowledge from seen classes to unseen ones with the help of language models pre-trained only with texts. While simple, the pixel-level ZS3 formulation shows the limited capability to integrate vision-language models that are often pre-trained with image-text pairs and currently demonstrate great potential for vision tasks. Inspired by the observation that humans often perform segm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07910","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/2112.07910/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":"2112.07910","created_at":"2026-07-05T04:15:00.340261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.07910v2","created_at":"2026-07-05T04:15:00.340261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07910","created_at":"2026-07-05T04:15:00.340261+00:00"},{"alias_kind":"pith_short_12","alias_value":"5IE7CSCEKAZ5","created_at":"2026-07-05T04:15:00.340261+00:00"},{"alias_kind":"pith_short_16","alias_value":"5IE7CSCEKAZ5ZZSQ","created_at":"2026-07-05T04:15:00.340261+00:00"},{"alias_kind":"pith_short_8","alias_value":"5IE7CSCE","created_at":"2026-07-05T04:15:00.340261+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.08644","citing_title":"AME: Aligned Manifold Entropy for Robust Vision-Language Distillation","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5IE7CSCEKAZ5ZZSQXKRNPDD4S2","json":"https://pith.science/pith/5IE7CSCEKAZ5ZZSQXKRNPDD4S2.json","graph_json":"https://pith.science/api/pith-number/5IE7CSCEKAZ5ZZSQXKRNPDD4S2/graph.json","events_json":"https://pith.science/api/pith-number/5IE7CSCEKAZ5ZZSQXKRNPDD4S2/events.json","paper":"https://pith.science/paper/5IE7CSCE"},"agent_actions":{"view_html":"https://pith.science/pith/5IE7CSCEKAZ5ZZSQXKRNPDD4S2","download_json":"https://pith.science/pith/5IE7CSCEKAZ5ZZSQXKRNPDD4S2.json","view_paper":"https://pith.science/paper/5IE7CSCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.07910&json=true","fetch_graph":"https://pith.science/api/pith-number/5IE7CSCEKAZ5ZZSQXKRNPDD4S2/graph.json","fetch_events":"https://pith.science/api/pith-number/5IE7CSCEKAZ5ZZSQXKRNPDD4S2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5IE7CSCEKAZ5ZZSQXKRNPDD4S2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5IE7CSCEKAZ5ZZSQXKRNPDD4S2/action/storage_attestation","attest_author":"https://pith.science/pith/5IE7CSCEKAZ5ZZSQXKRNPDD4S2/action/author_attestation","sign_citation":"https://pith.science/pith/5IE7CSCEKAZ5ZZSQXKRNPDD4S2/action/citation_signature","submit_replication":"https://pith.science/pith/5IE7CSCEKAZ5ZZSQXKRNPDD4S2/action/replication_record"}},"created_at":"2026-07-05T04:15:00.340261+00:00","updated_at":"2026-07-05T04:15:00.340261+00:00"}