{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YPMNBMVRHUPBLQH6CM5IRITOSZ","short_pith_number":"pith:YPMNBMVR","canonical_record":{"source":{"id":"2505.17670","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T09:36:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0eda11b15aee35a9d22b0d1a856508cc591aa47765bfbc69238c700641540917","abstract_canon_sha256":"f7dfe7b9bbaf5a195f035a3b55ae240881cc396c12ac3a2ccca569f43d3f5c00"},"schema_version":"1.0"},"canonical_sha256":"c3d8d0b2b13d1e15c0fe133a88a26e96476edc8bc987ff91ffdfcb580c32bf7f","source":{"kind":"arxiv","id":"2505.17670","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17670","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17670v2","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17670","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_12","alias_value":"YPMNBMVRHUPB","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_16","alias_value":"YPMNBMVRHUPBLQH6","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_8","alias_value":"YPMNBMVR","created_at":"2026-07-05T11:33:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YPMNBMVRHUPBLQH6CM5IRITOSZ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.17670","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T09:36:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0eda11b15aee35a9d22b0d1a856508cc591aa47765bfbc69238c700641540917","abstract_canon_sha256":"f7dfe7b9bbaf5a195f035a3b55ae240881cc396c12ac3a2ccca569f43d3f5c00"},"schema_version":"1.0"},"canonical_sha256":"c3d8d0b2b13d1e15c0fe133a88a26e96476edc8bc987ff91ffdfcb580c32bf7f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:23.989748Z","signature_b64":"KIpDdcE1SdlQ568SKeIbNyoDgwiK8RYtaZa6JR+0o5EvT80I0FDzIKRTKmEZYQKaO0zaXGrr2Ifd+igsDlNBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3d8d0b2b13d1e15c0fe133a88a26e96476edc8bc987ff91ffdfcb580c32bf7f","last_reissued_at":"2026-07-05T11:33:23.989189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:23.989189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.17670","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PXunpq5zBoaF7JT4iHapblK33/4VPGE44fg7C6G+j76zprEM3+d4+f3yXVZPJincP9BQkUehgSZeerY1h8KYDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T21:28:58.714708Z"},"content_sha256":"84b8f6d19bcdd70e42d1e45f678b74eed54cd4b58c655ce552d8ebd0a9ab8171","schema_version":"1.0","event_id":"sha256:84b8f6d19bcdd70e42d1e45f678b74eed54cd4b58c655ce552d8ebd0a9ab8171"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YPMNBMVRHUPBLQH6CM5IRITOSZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards General Continuous Memory for Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Biwei Huang, Kun Zhou, Wenyi Wu, Yifei Shao, Zhiting Hu, Zixuan Song","submitted_at":"2025-05-23T09:36:53Z","abstract_excerpt":"Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual real-world knowledge. To support such capabilities, an external memory system that can efficiently provide relevant multimodal information is essential. Existing approaches generally concatenate image and text tokens into a long sequence as memory, which, however, may drastically increase context length and even degrade performance. In contrast, we propose using cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17670","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/2505.17670/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D+cesgwZ3iNaHD64sgwuDB0AZGJECA6T/xj3S1s7wLMDAkqSylFL8pqFPOGzfEu8fIn0LUU6eQr1OFtMx9dFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T21:28:58.715080Z"},"content_sha256":"c7a69ee8fd92948ecb41509c5dd8469e18b25e1e4408cd8c46fd0d63b12301fb","schema_version":"1.0","event_id":"sha256:c7a69ee8fd92948ecb41509c5dd8469e18b25e1e4408cd8c46fd0d63b12301fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YPMNBMVRHUPBLQH6CM5IRITOSZ/bundle.json","state_url":"https://pith.science/pith/YPMNBMVRHUPBLQH6CM5IRITOSZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YPMNBMVRHUPBLQH6CM5IRITOSZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T21:28:58Z","links":{"resolver":"https://pith.science/pith/YPMNBMVRHUPBLQH6CM5IRITOSZ","bundle":"https://pith.science/pith/YPMNBMVRHUPBLQH6CM5IRITOSZ/bundle.json","state":"https://pith.science/pith/YPMNBMVRHUPBLQH6CM5IRITOSZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YPMNBMVRHUPBLQH6CM5IRITOSZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YPMNBMVRHUPBLQH6CM5IRITOSZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f7dfe7b9bbaf5a195f035a3b55ae240881cc396c12ac3a2ccca569f43d3f5c00","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T09:36:53Z","title_canon_sha256":"0eda11b15aee35a9d22b0d1a856508cc591aa47765bfbc69238c700641540917"},"schema_version":"1.0","source":{"id":"2505.17670","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17670","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17670v2","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17670","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_12","alias_value":"YPMNBMVRHUPB","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_16","alias_value":"YPMNBMVRHUPBLQH6","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_8","alias_value":"YPMNBMVR","created_at":"2026-07-05T11:33:23Z"}],"graph_snapshots":[{"event_id":"sha256:c7a69ee8fd92948ecb41509c5dd8469e18b25e1e4408cd8c46fd0d63b12301fb","target":"graph","created_at":"2026-07-05T11:33:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.17670/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual real-world knowledge. To support such capabilities, an external memory system that can efficiently provide relevant multimodal information is essential. Existing approaches generally concatenate image and text tokens into a long sequence as memory, which, however, may drastically increase context length and even degrade performance. In contrast, we propose using cont","authors_text":"Biwei Huang, Kun Zhou, Wenyi Wu, Yifei Shao, Zhiting Hu, Zixuan Song","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T09:36:53Z","title":"Towards General Continuous Memory for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17670","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:84b8f6d19bcdd70e42d1e45f678b74eed54cd4b58c655ce552d8ebd0a9ab8171","target":"record","created_at":"2026-07-05T11:33:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f7dfe7b9bbaf5a195f035a3b55ae240881cc396c12ac3a2ccca569f43d3f5c00","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T09:36:53Z","title_canon_sha256":"0eda11b15aee35a9d22b0d1a856508cc591aa47765bfbc69238c700641540917"},"schema_version":"1.0","source":{"id":"2505.17670","kind":"arxiv","version":2}},"canonical_sha256":"c3d8d0b2b13d1e15c0fe133a88a26e96476edc8bc987ff91ffdfcb580c32bf7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3d8d0b2b13d1e15c0fe133a88a26e96476edc8bc987ff91ffdfcb580c32bf7f","first_computed_at":"2026-07-05T11:33:23.989189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:23.989189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KIpDdcE1SdlQ568SKeIbNyoDgwiK8RYtaZa6JR+0o5EvT80I0FDzIKRTKmEZYQKaO0zaXGrr2Ifd+igsDlNBAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:23.989748Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17670","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84b8f6d19bcdd70e42d1e45f678b74eed54cd4b58c655ce552d8ebd0a9ab8171","sha256:c7a69ee8fd92948ecb41509c5dd8469e18b25e1e4408cd8c46fd0d63b12301fb"],"state_sha256":"8afd3da92fb0bda08996313930b39e5e39c04ab8a404bbfd4994ddb0962fd440"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y7q/YkwRoQCBjftVDfpYke4ELxwShvmmYjX2KTgNTF+Dvv2zPRFg2tIVuxKfh97tQCygk4Gy/0w7XDHkPE2qCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T21:28:58.717331Z","bundle_sha256":"028c3eb60df5c11fc91fb30c125083eed262e01e96f287e9f5181a40133eb709"}}