{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OQ33I6YA3TKW3NXWJ3S7YU47YN","short_pith_number":"pith:OQ33I6YA","canonical_record":{"source":{"id":"2510.01427","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-10-01T20:06:48Z","cross_cats_sorted":[],"title_canon_sha256":"5c618132fee49194f1d02e7cdb73612a5185571be28a2fc8cfa074828fcaead3","abstract_canon_sha256":"c287af65fd860648933150addc5dfeee458bae7bca54b32af586b663b26f1001"},"schema_version":"1.0"},"canonical_sha256":"7437b47b00dcd56db6f64ee5fc539fc364a3e847d5d69347bfcde39279741a13","source":{"kind":"arxiv","id":"2510.01427","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.01427","created_at":"2026-06-08T01:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"2510.01427v3","created_at":"2026-06-08T01:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01427","created_at":"2026-06-08T01:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"OQ33I6YA3TKW","created_at":"2026-06-08T01:03:49Z"},{"alias_kind":"pith_short_16","alias_value":"OQ33I6YA3TKW3NXW","created_at":"2026-06-08T01:03:49Z"},{"alias_kind":"pith_short_8","alias_value":"OQ33I6YA","created_at":"2026-06-08T01:03:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OQ33I6YA3TKW3NXWJ3S7YU47YN","target":"record","payload":{"canonical_record":{"source":{"id":"2510.01427","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-10-01T20:06:48Z","cross_cats_sorted":[],"title_canon_sha256":"5c618132fee49194f1d02e7cdb73612a5185571be28a2fc8cfa074828fcaead3","abstract_canon_sha256":"c287af65fd860648933150addc5dfeee458bae7bca54b32af586b663b26f1001"},"schema_version":"1.0"},"canonical_sha256":"7437b47b00dcd56db6f64ee5fc539fc364a3e847d5d69347bfcde39279741a13","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:03:49.001924Z","signature_b64":"erLcUSQfKPV/OHIF5N5QqvSbkIHQk/VK3YQ9AYq7BcLHcQHxeQ8VAf62daw3s33BEFgJGapGezTfURPXg8azCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7437b47b00dcd56db6f64ee5fc539fc364a3e847d5d69347bfcde39279741a13","last_reissued_at":"2026-06-08T01:03:49.000866Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:03:49.000866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.01427","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-08T01:03:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nnVYpMsCIkJYjc0AK4ZESceVkGA0p+qmvWMgPDXos62KzgW8RkjqA7Kz7oDn98HrwgeA8K4kOGvzpxpMe2n9AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T04:22:22.293178Z"},"content_sha256":"7eadaf485b14158fbb3de78ac5746a51d2aea7f6d09b0b862012dd666c4d8380","schema_version":"1.0","event_id":"sha256:7eadaf485b14158fbb3de78ac5746a51d2aea7f6d09b0b862012dd666c4d8380"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OQ33I6YA3TKW3NXWJ3S7YU47YN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Small Language Model Agents Enable Efficient and High-Quality Knowledge Mining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Huan Xu, Pin Qian, Shuhuai Lin, Sipeng Zhang, Su Wang, Xinpeng Wei, Yihang Chen","submitted_at":"2025-10-01T20:06:48Z","abstract_excerpt":"At the core of Deep Research is knowledge mining, the task of extracting structured information from massive unstructured text in response to user instructions. Large language models (LLMs) excel at interpreting such instructions but are prohibitively expensive to deploy at scale, while traditional pipelines of classifiers and extractors remain efficient yet brittle and unable to generalize to new tasks. We introduce Falconer, a collaborative framework that combines the agentic reasoning of LLMs with lightweight proxy models for scalable knowledge mining. In Falconer, LLMs act as planners, dec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.01427","kind":"arxiv","version":3},"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/2510.01427/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":"2026-06-08T01:03:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eHl5TbutWcskWLLbN9m5JoOgPFZ1SEgirP+xtsEeFdKCQSFaShpX+TwaWPoDPEsYeuzhBZbROnLJbnQculrPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T04:22:22.293567Z"},"content_sha256":"c14162fc2db1d99960fc17a41a02ceda3d5fb913d98775af9a86d4911b30337b","schema_version":"1.0","event_id":"sha256:c14162fc2db1d99960fc17a41a02ceda3d5fb913d98775af9a86d4911b30337b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OQ33I6YA3TKW3NXWJ3S7YU47YN/bundle.json","state_url":"https://pith.science/pith/OQ33I6YA3TKW3NXWJ3S7YU47YN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OQ33I6YA3TKW3NXWJ3S7YU47YN/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":"2026-06-28T04:22:22Z","links":{"resolver":"https://pith.science/pith/OQ33I6YA3TKW3NXWJ3S7YU47YN","bundle":"https://pith.science/pith/OQ33I6YA3TKW3NXWJ3S7YU47YN/bundle.json","state":"https://pith.science/pith/OQ33I6YA3TKW3NXWJ3S7YU47YN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OQ33I6YA3TKW3NXWJ3S7YU47YN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OQ33I6YA3TKW3NXWJ3S7YU47YN","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":"c287af65fd860648933150addc5dfeee458bae7bca54b32af586b663b26f1001","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-10-01T20:06:48Z","title_canon_sha256":"5c618132fee49194f1d02e7cdb73612a5185571be28a2fc8cfa074828fcaead3"},"schema_version":"1.0","source":{"id":"2510.01427","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.01427","created_at":"2026-06-08T01:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"2510.01427v3","created_at":"2026-06-08T01:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01427","created_at":"2026-06-08T01:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"OQ33I6YA3TKW","created_at":"2026-06-08T01:03:49Z"},{"alias_kind":"pith_short_16","alias_value":"OQ33I6YA3TKW3NXW","created_at":"2026-06-08T01:03:49Z"},{"alias_kind":"pith_short_8","alias_value":"OQ33I6YA","created_at":"2026-06-08T01:03:49Z"}],"graph_snapshots":[{"event_id":"sha256:c14162fc2db1d99960fc17a41a02ceda3d5fb913d98775af9a86d4911b30337b","target":"graph","created_at":"2026-06-08T01:03:49Z","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/2510.01427/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"At the core of Deep Research is knowledge mining, the task of extracting structured information from massive unstructured text in response to user instructions. Large language models (LLMs) excel at interpreting such instructions but are prohibitively expensive to deploy at scale, while traditional pipelines of classifiers and extractors remain efficient yet brittle and unable to generalize to new tasks. We introduce Falconer, a collaborative framework that combines the agentic reasoning of LLMs with lightweight proxy models for scalable knowledge mining. In Falconer, LLMs act as planners, dec","authors_text":"Huan Xu, Pin Qian, Shuhuai Lin, Sipeng Zhang, Su Wang, Xinpeng Wei, Yihang Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-10-01T20:06:48Z","title":"Small Language Model Agents Enable Efficient and High-Quality Knowledge Mining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.01427","kind":"arxiv","version":3},"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":"sha256:7eadaf485b14158fbb3de78ac5746a51d2aea7f6d09b0b862012dd666c4d8380","target":"record","created_at":"2026-06-08T01:03:49Z","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":"c287af65fd860648933150addc5dfeee458bae7bca54b32af586b663b26f1001","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-10-01T20:06:48Z","title_canon_sha256":"5c618132fee49194f1d02e7cdb73612a5185571be28a2fc8cfa074828fcaead3"},"schema_version":"1.0","source":{"id":"2510.01427","kind":"arxiv","version":3}},"canonical_sha256":"7437b47b00dcd56db6f64ee5fc539fc364a3e847d5d69347bfcde39279741a13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7437b47b00dcd56db6f64ee5fc539fc364a3e847d5d69347bfcde39279741a13","first_computed_at":"2026-06-08T01:03:49.000866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:03:49.000866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"erLcUSQfKPV/OHIF5N5QqvSbkIHQk/VK3YQ9AYq7BcLHcQHxeQ8VAf62daw3s33BEFgJGapGezTfURPXg8azCg==","signature_status":"signed_v1","signed_at":"2026-06-08T01:03:49.001924Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.01427","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7eadaf485b14158fbb3de78ac5746a51d2aea7f6d09b0b862012dd666c4d8380","sha256:c14162fc2db1d99960fc17a41a02ceda3d5fb913d98775af9a86d4911b30337b"],"state_sha256":"7677cb5c065cfd4c13260c772491b028b01abbdb312c631bb69ca4fa0895442e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bXizws2KOfEgnSaMM22kKoxyNqr6Kp81v7ig83061lqHsJ9WuWFsDHR0RauBb7t7Pu7/ZcEbcZgOd9sFTJ92Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T04:22:22.295498Z","bundle_sha256":"2b47efc500b8aafa83102b6720415460e1557ebcbf98a7ea2846e2625d9b0051"}}