{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4ZYJBAYQGMQMBLPYZ5XTLCKVVN","short_pith_number":"pith:4ZYJBAYQ","canonical_record":{"source":{"id":"2505.21427","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T16:57:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ac4eecddb28bcd47d6a834a98b7fbee10428d65f42ec1a34794abd3201a28e78","abstract_canon_sha256":"64e47fe4efd944307505f14f8428df6fe64928dc9111073d9dc925e4b0c10c1e"},"schema_version":"1.0"},"canonical_sha256":"e6709083103320c0adf8cf6f358955ab505f03868a5fecd833c0a66d0bb2fd11","source":{"kind":"arxiv","id":"2505.21427","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21427","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21427v2","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21427","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"4ZYJBAYQGMQM","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"4ZYJBAYQGMQMBLPY","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"4ZYJBAYQ","created_at":"2026-07-05T11:15:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4ZYJBAYQGMQMBLPYZ5XTLCKVVN","target":"record","payload":{"canonical_record":{"source":{"id":"2505.21427","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T16:57:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ac4eecddb28bcd47d6a834a98b7fbee10428d65f42ec1a34794abd3201a28e78","abstract_canon_sha256":"64e47fe4efd944307505f14f8428df6fe64928dc9111073d9dc925e4b0c10c1e"},"schema_version":"1.0"},"canonical_sha256":"e6709083103320c0adf8cf6f358955ab505f03868a5fecd833c0a66d0bb2fd11","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:47.203651Z","signature_b64":"yefGs0VSXooEcHVpE7e7VL97vaJ3xzQmbBRrAFjSkQZ6oAOfbwAH0gdElwOs7nmOjfdcDNFpMiOmdJzwXVzSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6709083103320c0adf8cf6f358955ab505f03868a5fecd833c0a66d0bb2fd11","last_reissued_at":"2026-07-05T11:15:47.203192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:47.203192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.21427","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":"2026-07-05T11:15:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zXMXDH4mhTPw/9YhfP/JI6Bz+ynWav2t9/OzsbHwoQaefDZFsVKF6w4Ivcf5kEx500khP8zh9GcUXguZo6GSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:58:57.738706Z"},"content_sha256":"d46e7c2c47383eb8a279b5d451bfa48e592605c112096ac6b7dd47b474fae984","schema_version":"1.0","event_id":"sha256:d46e7c2c47383eb8a279b5d451bfa48e592605c112096ac6b7dd47b474fae984"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4ZYJBAYQGMQMBLPYZ5XTLCKVVN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Induction: Predicting Startup Success via Explainable Memory-Augmented In-Context Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Fuat Alican, Joseph Ternasky, Xianling Mu, Yigit Ihlamur","submitted_at":"2025-05-27T16:57:07Z","abstract_excerpt":"Early-stage startup investment is a high-risk endeavor characterized by scarce data and uncertain outcomes. Traditional machine learning approaches often require large, labeled datasets and extensive fine-tuning, yet remain opaque and difficult for domain experts to interpret or improve. In this paper, we propose a transparent and data-efficient investment decision framework powered by memory-augmented large language models (LLMs) using in-context learning (ICL). Central to our method is a natural language policy embedded directly into the LLM prompt, enabling the model to apply explicit reaso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21427","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/2505.21427/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":"2026-07-05T11:15:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q3WifC8fpA50rUFXC2++DTxBZGVur/HF7/eL/EnBaAdilVRlHAL5oUnM3j/brCeN/V+jlAyJ5FOBGwMZXHeWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:58:57.739205Z"},"content_sha256":"820d3ca53d40112775971ac9eb9cfde101c6257d1f46c7fab84da717dc516734","schema_version":"1.0","event_id":"sha256:820d3ca53d40112775971ac9eb9cfde101c6257d1f46c7fab84da717dc516734"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4ZYJBAYQGMQMBLPYZ5XTLCKVVN/bundle.json","state_url":"https://pith.science/pith/4ZYJBAYQGMQMBLPYZ5XTLCKVVN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4ZYJBAYQGMQMBLPYZ5XTLCKVVN/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":"2026-08-09T23:58:57Z","links":{"resolver":"https://pith.science/pith/4ZYJBAYQGMQMBLPYZ5XTLCKVVN","bundle":"https://pith.science/pith/4ZYJBAYQGMQMBLPYZ5XTLCKVVN/bundle.json","state":"https://pith.science/pith/4ZYJBAYQGMQMBLPYZ5XTLCKVVN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4ZYJBAYQGMQMBLPYZ5XTLCKVVN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4ZYJBAYQGMQMBLPYZ5XTLCKVVN","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":"64e47fe4efd944307505f14f8428df6fe64928dc9111073d9dc925e4b0c10c1e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T16:57:07Z","title_canon_sha256":"ac4eecddb28bcd47d6a834a98b7fbee10428d65f42ec1a34794abd3201a28e78"},"schema_version":"1.0","source":{"id":"2505.21427","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21427","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21427v2","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21427","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"4ZYJBAYQGMQM","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"4ZYJBAYQGMQMBLPY","created_at":"2026-07-05T11:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"4ZYJBAYQ","created_at":"2026-07-05T11:15:47Z"}],"graph_snapshots":[{"event_id":"sha256:820d3ca53d40112775971ac9eb9cfde101c6257d1f46c7fab84da717dc516734","target":"graph","created_at":"2026-07-05T11:15:47Z","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/2505.21427/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Early-stage startup investment is a high-risk endeavor characterized by scarce data and uncertain outcomes. Traditional machine learning approaches often require large, labeled datasets and extensive fine-tuning, yet remain opaque and difficult for domain experts to interpret or improve. In this paper, we propose a transparent and data-efficient investment decision framework powered by memory-augmented large language models (LLMs) using in-context learning (ICL). Central to our method is a natural language policy embedded directly into the LLM prompt, enabling the model to apply explicit reaso","authors_text":"Fuat Alican, Joseph Ternasky, Xianling Mu, Yigit Ihlamur","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T16:57:07Z","title":"Policy Induction: Predicting Startup Success via Explainable Memory-Augmented In-Context Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21427","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:d46e7c2c47383eb8a279b5d451bfa48e592605c112096ac6b7dd47b474fae984","target":"record","created_at":"2026-07-05T11:15:47Z","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":"64e47fe4efd944307505f14f8428df6fe64928dc9111073d9dc925e4b0c10c1e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T16:57:07Z","title_canon_sha256":"ac4eecddb28bcd47d6a834a98b7fbee10428d65f42ec1a34794abd3201a28e78"},"schema_version":"1.0","source":{"id":"2505.21427","kind":"arxiv","version":2}},"canonical_sha256":"e6709083103320c0adf8cf6f358955ab505f03868a5fecd833c0a66d0bb2fd11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6709083103320c0adf8cf6f358955ab505f03868a5fecd833c0a66d0bb2fd11","first_computed_at":"2026-07-05T11:15:47.203192Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:47.203192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yefGs0VSXooEcHVpE7e7VL97vaJ3xzQmbBRrAFjSkQZ6oAOfbwAH0gdElwOs7nmOjfdcDNFpMiOmdJzwXVzSBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:47.203651Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21427","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d46e7c2c47383eb8a279b5d451bfa48e592605c112096ac6b7dd47b474fae984","sha256:820d3ca53d40112775971ac9eb9cfde101c6257d1f46c7fab84da717dc516734"],"state_sha256":"6b2ce9c1e52c1bd436c99b915f62530df1569bb98bc36bc8d6e4288d05499abd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QrQvUlr49jyUzsMjVsdRhHOKUVIMbYhuEeveVSX8Y+KB2is/pQiX+fF8YvnJEfmBPiFCrSri8kHc6c0KUNvMDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:58:57.744795Z","bundle_sha256":"fa7ac2170d7959b8bdaf7a3c0ac6c172fcdfe68af15d3089491333a02aef4fe1"}}