{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_69703cc3932d0f9e536f273f2927b911bfc93bd4cf0f83a8b472232895684792","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_69703cc3932d0f9e536f273f2927b911bfc93bd4cf0f83a8b472232895684792","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"c2fe7cb52a2d11f4ea0ca55e561bbb55fc06034e931196cf85cfd112c83eadf9","published":"Fri, 24 Jul 2026 00:00:00 -0400","receipt_hash":"c2fe7cb52a2d11f4ea0ca55e561bbb55fc06034e931196cf85cfd112c83eadf9","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"c2fe7cb52a2d11f4ea0ca55e561bbb55fc06034e931196cf85cfd112c83eadf9","observed_at":"2026-07-24T04:43:08.456021Z","parent_run_hash":"b018378f86139a28e6209ec008b31c1282cd1b5c1632dbd43b054c17aa88ab96","published":"Fri, 24 Jul 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2607.20556v1 Announce Type: new \nAbstract: In large-scale text analysis tasks, pre-trained language models are often used to embed text corpora for downstream analysis. However, such models may struggle to capture domain-specific semantics and adapting them typically requires large amounts of labeled data and technical expertise to implement training pipelines. Recent approaches have demonstrated how visual interactions in document projections can capture human feedback as training signals for model tuning. However, these methods operate on document-level feedback, which requires users to open and assess individual documents in order to provide effective feedback. In this paper, we propose KeySI, an interaction framework that enables feature-level feedback through keyword-based concept specification. Users specify feedback by organizing extracted keywords into groups representing concepts, which KeySI translates into document-level supervision for subsequent tuning. By operating ","title":"KeySI: An Interaction Framework for Tuning Text Embeddings Based on Human Feedback","url":"https://arxiv.org/abs/2607.20556","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.20556v1 Announce Type: new \nAbstract: In large-scale text analysis tasks, pre-trained language models are often used to embed text corpora for downstream analysis. However, such models may struggle to capture domain-specific semantics and adapting them typically requires large amounts of labeled data and technical expertise to implement training pipelines. Recent approaches have demonstrated how visual interactions in document projections can capture human feedback as training signals for model tuning. However, these methods operate on document-level feedback, which requires users to open and assess individual documents in order to provide effective feedback. In this paper, we propose KeySI, an interaction framework that enables feature-level feedback through keyword-based concept specification. Users specify feedback by organizing extracted keywords into groups representing concepts, which KeySI translates into document-level supervision for subsequent tuning. By operating ","title":"KeySI: An Interaction Framework for Tuning Text Embeddings Based on Human Feedback","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-24T04:43:08Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.20556"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:97e9b87957aedd219d3275bf56a5ad9c4c89dc2b91a0c55804cceb6a0f62c9ee5f83faebb4fa85e499da3f848823e040a5ac0c3ba3af864b5c8b4c6da3544804","signer":"crovia.substrate","subject":{"observed_at":"2026-07-24T04:43:08Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.20556"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"4836ea70025c55475fad8d2258643207fcfa4046236978e707d2b9d469d0d9da","leaf_index":347001,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"70e12aac4430051053e8f646e1bc9d5e2f9938fddb8fc1477b6d864de9c770d7","side":"left"},{"sibling":"2bb18f876cc46036c55708a417ce2a8d02863cd79b545a048937d3bdb30628e1","side":"right"},{"sibling":"ea31924b82e651c1a175190b362d41baede4a4ac80769825bf330053c555672b","side":"right"},{"sibling":"aa8da06ec7ecd388c9a492c99beb97e98e564bf4403d3a320e36c2aa1a0c85cc","side":"left"},{"sibling":"95da4ad14827dc8554eb82f12569537c1ac46e8a84fbd2e08d4f0ecf82fb98db","side":"left"},{"sibling":"2d8571a85ef8db282687baf52c678be7c1e616f7a8b798c9f0b7c1f94ce5acd7","side":"left"},{"sibling":"6149df3d1da13abe8a81da069f7bd406a0badf8b62cfc2d62ba645f403037400","side":"left"},{"sibling":"ffd3a55995db3d94b2e5c6432ae18b8c5c13fa05a460ebe646d97e4cfd4c196c","side":"right"},{"sibling":"c212fcc83c532c0321804b72fe72b546946bb055d3d482aab19c43f5bebfbf3f","side":"left"},{"sibling":"da189c159d0789c2229cf3731890cc753832dab1aa83e4bbf0fac01955c22cd8","side":"left"},{"sibling":"3a02ed8ea41a09957282e4e27db74ed88cd675156461abb02acb28e2cd257e63","side":"right"},{"sibling":"d3139af8c5ce235438e1c69e4b7afa44ba09129fd86674968434f23e546f423e","side":"left"},{"sibling":"cb89775a838ee16d10fc8da3213420c2012b4d96e8d55cd49939b0887a4b92d3","side":"right"},{"sibling":"252d30ea8052c3bb6b40bc5cc29fc9b9725343d212f84c08fbbae4215a125b00","side":"right"},{"sibling":"f3e45bceed774d2402fa45d41ff5190f295823bd2f216eb90157884150034693","side":"left"},{"sibling":"3cfa2102c0224815c6f3bf73e6710e24103f43f7bf5da1ca2abad1416d9c0890","side":"right"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"e871fd7edf9b2ad89bce1609a028f5225eea4d14372169bac242420830f86530","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":347413,"merkle_root":"9efe042c5dd6583dfd3b6a58fbfc289807f60bcf2bd2927f10488a54a8ba11fc","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260724T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-24T05:38:42Z","sig_algorithm":"ed25519","signature":"8633c55f558d42994850505218b2862c6134bad2b1c80d4b80736c2fd3ea7a19690ca3498727a8adbdc47791176128a8d64bef0883b888db809f0477355bd00c","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_69703cc3932d0f9e536f273f2927b911bfc93bd4cf0f83a8b472232895684792"}}