{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GN6BZLTMNN3N7IXTAITV3XJV3U","short_pith_number":"pith:GN6BZLTM","schema_version":"1.0","canonical_sha256":"337c1cae6c6b76dfa2f302275ddd35dd145ac4510d7d192ebf6dbf0318d0c865","source":{"kind":"arxiv","id":"2602.00415","version":2},"attestation_state":"computed","paper":{"title":"PolarMem: A Training-Free Polarized Latent Graph Memory for Verifiable Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jingwei Song, Jinhan Li, Liang Lin, Tingyu Wu, Yingwei Zhang, Zhengwei Xie, Zhisheng Chen, Zijie Zhou, Zikai Xiao, Ziyan Weng","submitted_at":"2026-01-31T00:13:56Z","abstract_excerpt":"Memory is not merely a storage mechanism for intelligent systems, but a structure for organizing evidence and constraining belief. This is especially important for multimodal reasoning, where retrieved evidence must be both query-relevant and visually consistent. However, current memory systems for vision-language models (VLMs) remain largely positive-associative: they retrieve what is similar or previously observed, but lack an explicit way to remember what has been verified as absent or logically excluded. To this end, we propose \\textbf{PolarMem}, a training-free polarized latent graph memo"},"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":"2602.00415","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-01-31T00:13:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5cef82ed1262afe73461b6b576420df85f6abb45295ebee9802ac51f56136629","abstract_canon_sha256":"70b850b443feeb6776794876326df7d6e9310ea96bd47889b500ab16ea1d8fe5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:41.682938Z","signature_b64":"gwnGxXSageR7LTnfF3lqZNe5algsM05ZAZctjfxEI+DyJAf8Em3ZiQUbx76ZsQl5vy4Zvjzgx0fn/wyzconUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"337c1cae6c6b76dfa2f302275ddd35dd145ac4510d7d192ebf6dbf0318d0c865","last_reissued_at":"2026-06-02T01:03:41.682358Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:41.682358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PolarMem: A Training-Free Polarized Latent Graph Memory for Verifiable Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jingwei Song, Jinhan Li, Liang Lin, Tingyu Wu, Yingwei Zhang, Zhengwei Xie, Zhisheng Chen, Zijie Zhou, Zikai Xiao, Ziyan Weng","submitted_at":"2026-01-31T00:13:56Z","abstract_excerpt":"Memory is not merely a storage mechanism for intelligent systems, but a structure for organizing evidence and constraining belief. This is especially important for multimodal reasoning, where retrieved evidence must be both query-relevant and visually consistent. However, current memory systems for vision-language models (VLMs) remain largely positive-associative: they retrieve what is similar or previously observed, but lack an explicit way to remember what has been verified as absent or logically excluded. To this end, we propose \\textbf{PolarMem}, a training-free polarized latent graph memo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.00415","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/2602.00415/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":"2602.00415","created_at":"2026-06-02T01:03:41.682422+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.00415v2","created_at":"2026-06-02T01:03:41.682422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.00415","created_at":"2026-06-02T01:03:41.682422+00:00"},{"alias_kind":"pith_short_12","alias_value":"GN6BZLTMNN3N","created_at":"2026-06-02T01:03:41.682422+00:00"},{"alias_kind":"pith_short_16","alias_value":"GN6BZLTMNN3N7IXT","created_at":"2026-06-02T01:03:41.682422+00:00"},{"alias_kind":"pith_short_8","alias_value":"GN6BZLTM","created_at":"2026-06-02T01:03:41.682422+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/GN6BZLTMNN3N7IXTAITV3XJV3U","json":"https://pith.science/pith/GN6BZLTMNN3N7IXTAITV3XJV3U.json","graph_json":"https://pith.science/api/pith-number/GN6BZLTMNN3N7IXTAITV3XJV3U/graph.json","events_json":"https://pith.science/api/pith-number/GN6BZLTMNN3N7IXTAITV3XJV3U/events.json","paper":"https://pith.science/paper/GN6BZLTM"},"agent_actions":{"view_html":"https://pith.science/pith/GN6BZLTMNN3N7IXTAITV3XJV3U","download_json":"https://pith.science/pith/GN6BZLTMNN3N7IXTAITV3XJV3U.json","view_paper":"https://pith.science/paper/GN6BZLTM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.00415&json=true","fetch_graph":"https://pith.science/api/pith-number/GN6BZLTMNN3N7IXTAITV3XJV3U/graph.json","fetch_events":"https://pith.science/api/pith-number/GN6BZLTMNN3N7IXTAITV3XJV3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GN6BZLTMNN3N7IXTAITV3XJV3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GN6BZLTMNN3N7IXTAITV3XJV3U/action/storage_attestation","attest_author":"https://pith.science/pith/GN6BZLTMNN3N7IXTAITV3XJV3U/action/author_attestation","sign_citation":"https://pith.science/pith/GN6BZLTMNN3N7IXTAITV3XJV3U/action/citation_signature","submit_replication":"https://pith.science/pith/GN6BZLTMNN3N7IXTAITV3XJV3U/action/replication_record"}},"created_at":"2026-06-02T01:03:41.682422+00:00","updated_at":"2026-06-02T01:03:41.682422+00:00"}