{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JFTBHPR4S6LDTCXAYFQG3ZWSHJ","short_pith_number":"pith:JFTBHPR4","schema_version":"1.0","canonical_sha256":"496613be3c9796398ae0c1606de6d23a67c5eb15302948e1baae9205da0f537b","source":{"kind":"arxiv","id":"2312.16272","version":2},"attestation_state":"computed","paper":{"title":"SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Pan, Hao Tang, Huaxia Li, Jiaming Liu, Jinpeng Yu, Rui Wang, Xu Tang, Yao Hu, Yiren Song, Yuxuan Zhang, Zhongliang Jing","submitted_at":"2023-12-26T14:39:11Z","abstract_excerpt":"Recent advancements in subject-driven image generation have led to zero-shot generation, yet precise selection and focus on crucial subject representations remain challenging. Addressing this, we introduce the SSR-Encoder, a novel architecture designed for selectively capturing any subject from single or multiple reference images. It responds to various query modalities including text and masks, without necessitating test-time fine-tuning. The SSR-Encoder combines a Token-to-Patch Aligner that aligns query inputs with image patches and a Detail-Preserving Subject Encoder for extracting and pre"},"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":"2312.16272","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-26T14:39:11Z","cross_cats_sorted":[],"title_canon_sha256":"a84fc801ed168d6d94642fe5e6c386529bd83d1226c3ad75447e510a0dc1cdf1","abstract_canon_sha256":"d80fcfc003c9e2707c932365c901acec9a829c75681dfd1ad6d1fee8f22ff94b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:02.303591Z","signature_b64":"EkwCzyMkJRQngLTmK6y1u3qq16PBh4eTyFg9qF3Ae37Fea7igCdo1dSyqIyzWJnzM7N1OabXUFSevmtiWTeLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"496613be3c9796398ae0c1606de6d23a67c5eb15302948e1baae9205da0f537b","last_reissued_at":"2026-07-05T07:56:02.303103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:02.303103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Pan, Hao Tang, Huaxia Li, Jiaming Liu, Jinpeng Yu, Rui Wang, Xu Tang, Yao Hu, Yiren Song, Yuxuan Zhang, Zhongliang Jing","submitted_at":"2023-12-26T14:39:11Z","abstract_excerpt":"Recent advancements in subject-driven image generation have led to zero-shot generation, yet precise selection and focus on crucial subject representations remain challenging. Addressing this, we introduce the SSR-Encoder, a novel architecture designed for selectively capturing any subject from single or multiple reference images. It responds to various query modalities including text and masks, without necessitating test-time fine-tuning. The SSR-Encoder combines a Token-to-Patch Aligner that aligns query inputs with image patches and a Detail-Preserving Subject Encoder for extracting and pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16272","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/2312.16272/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":"2312.16272","created_at":"2026-07-05T07:56:02.303159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.16272v2","created_at":"2026-07-05T07:56:02.303159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16272","created_at":"2026-07-05T07:56:02.303159+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFTBHPR4S6LD","created_at":"2026-07-05T07:56:02.303159+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFTBHPR4S6LDTCXA","created_at":"2026-07-05T07:56:02.303159+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFTBHPR4","created_at":"2026-07-05T07:56:02.303159+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.04300","citing_title":"T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFTBHPR4S6LDTCXAYFQG3ZWSHJ","json":"https://pith.science/pith/JFTBHPR4S6LDTCXAYFQG3ZWSHJ.json","graph_json":"https://pith.science/api/pith-number/JFTBHPR4S6LDTCXAYFQG3ZWSHJ/graph.json","events_json":"https://pith.science/api/pith-number/JFTBHPR4S6LDTCXAYFQG3ZWSHJ/events.json","paper":"https://pith.science/paper/JFTBHPR4"},"agent_actions":{"view_html":"https://pith.science/pith/JFTBHPR4S6LDTCXAYFQG3ZWSHJ","download_json":"https://pith.science/pith/JFTBHPR4S6LDTCXAYFQG3ZWSHJ.json","view_paper":"https://pith.science/paper/JFTBHPR4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.16272&json=true","fetch_graph":"https://pith.science/api/pith-number/JFTBHPR4S6LDTCXAYFQG3ZWSHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/JFTBHPR4S6LDTCXAYFQG3ZWSHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFTBHPR4S6LDTCXAYFQG3ZWSHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFTBHPR4S6LDTCXAYFQG3ZWSHJ/action/storage_attestation","attest_author":"https://pith.science/pith/JFTBHPR4S6LDTCXAYFQG3ZWSHJ/action/author_attestation","sign_citation":"https://pith.science/pith/JFTBHPR4S6LDTCXAYFQG3ZWSHJ/action/citation_signature","submit_replication":"https://pith.science/pith/JFTBHPR4S6LDTCXAYFQG3ZWSHJ/action/replication_record"}},"created_at":"2026-07-05T07:56:02.303159+00:00","updated_at":"2026-07-05T07:56:02.303159+00:00"}