{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KI63SAQNOTNCYFMTOPV3QMOHT3","short_pith_number":"pith:KI63SAQN","schema_version":"1.0","canonical_sha256":"523db9020d74da2c159373ebb831c79efdd4c74a943a556b9c4bb336f65ef374","source":{"kind":"arxiv","id":"2605.20309","version":1},"attestation_state":"computed","paper":{"title":"Tiny-Engram: Trigger-Indexed Concept Tables for Generative Vision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Runyuan Cai, Xiaodong Zeng, Yiming Wang, Yu Lin","submitted_at":"2026-05-19T16:27:07Z","abstract_excerpt":"Current personalization methods for generative vision models typically encode new concepts through continuous adapters or weight updates, yet provide limited control over whether and when a concept should be retrieved. In this work, we introduce Tiny-Engram, a compact trigger-indexed concept table that gives visual memories an explicit lexical address and activation boundary inside frozen image and video generators. Tiny-Engram parameterizes each concept as a small set of memory entries indexed by registered n-gram matches, which modulate text-encoder hidden states only within the matched trig"},"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":"2605.20309","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T16:27:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"820dc95282f45a7257b2dea69d231260c6a7624c8694ffbceff49de3ced4a786","abstract_canon_sha256":"3b8a5fa6b4e57af46b0b9831651a372a087d9ce9be8ef82e68e42dfa4169ec3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T00:04:24.762348Z","signature_b64":"ZGFEkysWVV+K01oddsii95g5+eXYjf0/0jqVjgYd0IJiPjV/6ndbW39wcgQhi722BKB9ttLdfk25kEClhNbuBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"523db9020d74da2c159373ebb831c79efdd4c74a943a556b9c4bb336f65ef374","last_reissued_at":"2026-05-21T00:04:24.761838Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T00:04:24.761838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tiny-Engram: Trigger-Indexed Concept Tables for Generative Vision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Runyuan Cai, Xiaodong Zeng, Yiming Wang, Yu Lin","submitted_at":"2026-05-19T16:27:07Z","abstract_excerpt":"Current personalization methods for generative vision models typically encode new concepts through continuous adapters or weight updates, yet provide limited control over whether and when a concept should be retrieved. In this work, we introduce Tiny-Engram, a compact trigger-indexed concept table that gives visual memories an explicit lexical address and activation boundary inside frozen image and video generators. Tiny-Engram parameterizes each concept as a small set of memory entries indexed by registered n-gram matches, which modulate text-encoder hidden states only within the matched trig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20309","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/2605.20309/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":"2605.20309","created_at":"2026-05-21T00:04:24.761913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20309v1","created_at":"2026-05-21T00:04:24.761913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20309","created_at":"2026-05-21T00:04:24.761913+00:00"},{"alias_kind":"pith_short_12","alias_value":"KI63SAQNOTNC","created_at":"2026-05-21T00:04:24.761913+00:00"},{"alias_kind":"pith_short_16","alias_value":"KI63SAQNOTNCYFMT","created_at":"2026-05-21T00:04:24.761913+00:00"},{"alias_kind":"pith_short_8","alias_value":"KI63SAQN","created_at":"2026-05-21T00:04:24.761913+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/KI63SAQNOTNCYFMTOPV3QMOHT3","json":"https://pith.science/pith/KI63SAQNOTNCYFMTOPV3QMOHT3.json","graph_json":"https://pith.science/api/pith-number/KI63SAQNOTNCYFMTOPV3QMOHT3/graph.json","events_json":"https://pith.science/api/pith-number/KI63SAQNOTNCYFMTOPV3QMOHT3/events.json","paper":"https://pith.science/paper/KI63SAQN"},"agent_actions":{"view_html":"https://pith.science/pith/KI63SAQNOTNCYFMTOPV3QMOHT3","download_json":"https://pith.science/pith/KI63SAQNOTNCYFMTOPV3QMOHT3.json","view_paper":"https://pith.science/paper/KI63SAQN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20309&json=true","fetch_graph":"https://pith.science/api/pith-number/KI63SAQNOTNCYFMTOPV3QMOHT3/graph.json","fetch_events":"https://pith.science/api/pith-number/KI63SAQNOTNCYFMTOPV3QMOHT3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KI63SAQNOTNCYFMTOPV3QMOHT3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KI63SAQNOTNCYFMTOPV3QMOHT3/action/storage_attestation","attest_author":"https://pith.science/pith/KI63SAQNOTNCYFMTOPV3QMOHT3/action/author_attestation","sign_citation":"https://pith.science/pith/KI63SAQNOTNCYFMTOPV3QMOHT3/action/citation_signature","submit_replication":"https://pith.science/pith/KI63SAQNOTNCYFMTOPV3QMOHT3/action/replication_record"}},"created_at":"2026-05-21T00:04:24.761913+00:00","updated_at":"2026-05-21T00:04:24.761913+00:00"}