{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2YAA7DSYRPQEOL64FFAVGBQQZK","short_pith_number":"pith:2YAA7DSY","canonical_record":{"source":{"id":"2607.24875","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T07:05:22Z","cross_cats_sorted":[],"title_canon_sha256":"162f0230b4bf193f2da8d14c5b594d1076de58a01eeabe61b1c9f7f6ed23b1ab","abstract_canon_sha256":"c59ee7a27b635501829df9cb5984a12d8882cff19f3c8f331522e7f67e6f1f3c"},"schema_version":"1.0"},"canonical_sha256":"d6000f8e588be0472fdc2941530610ca8e2b69409eda09129322434f62e36a7e","source":{"kind":"arxiv","id":"2607.24875","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24875","created_at":"2026-07-29T00:24:49Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24875v1","created_at":"2026-07-29T00:24:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24875","created_at":"2026-07-29T00:24:49Z"},{"alias_kind":"pith_short_12","alias_value":"2YAA7DSYRPQE","created_at":"2026-07-29T00:24:49Z"},{"alias_kind":"pith_short_16","alias_value":"2YAA7DSYRPQEOL64","created_at":"2026-07-29T00:24:49Z"},{"alias_kind":"pith_short_8","alias_value":"2YAA7DSY","created_at":"2026-07-29T00:24:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2YAA7DSYRPQEOL64FFAVGBQQZK","target":"record","payload":{"canonical_record":{"source":{"id":"2607.24875","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T07:05:22Z","cross_cats_sorted":[],"title_canon_sha256":"162f0230b4bf193f2da8d14c5b594d1076de58a01eeabe61b1c9f7f6ed23b1ab","abstract_canon_sha256":"c59ee7a27b635501829df9cb5984a12d8882cff19f3c8f331522e7f67e6f1f3c"},"schema_version":"1.0"},"canonical_sha256":"d6000f8e588be0472fdc2941530610ca8e2b69409eda09129322434f62e36a7e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:24:49.181654Z","signature_b64":"3+U2LLF6zvCesFfQOIWiBHTKIrRIR3/uUgRhaJFhNPiQNLLllvqW3IfSObJXBtWR8D/ZW9/rBSHGxucBVOpvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6000f8e588be0472fdc2941530610ca8e2b69409eda09129322434f62e36a7e","last_reissued_at":"2026-07-29T00:24:49.180764Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:24:49.180764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.24875","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-29T00:24:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XcFIAJISrH9XPBosG+kwVxUTKD/oA0AqaYnCROpxtDeRNP7nN5oEnZ3V+dGwEL1b6CmfyoDKlXL2IuCoBeK0Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:35:33.991872Z"},"content_sha256":"08dbc40f2f926ac8427d7092008e1601c071167862d03a06ac4738a83dcce6ae","schema_version":"1.0","event_id":"sha256:08dbc40f2f926ac8427d7092008e1601c071167862d03a06ac4738a83dcce6ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2YAA7DSYRPQEOL64FFAVGBQQZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FinAbstain: Uncertainty-Calibrated Multimodal RAG for Selective Financial Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dorothy Torres, Henan Huang, Wei Cheng","submitted_at":"2026-07-27T07:05:22Z","abstract_excerpt":"Large language models (LLMs) can synthesize financial narratives but may express high confidence when evidence is sparse, stale, or contradictory. This failure is especially consequential in forecasting, where filings, news, prices, volume, and technical signals can disagree. We present FinAbstain, a research framework for uncertainty-calibrated multimodal retrieval-augmented generation (RAG) with selective prediction. A point-in-time retriever admits only information public at the forecast timestamp and supplies modality-specific evidence to fundamental, news, technical, risk, and verificatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24875","kind":"arxiv","version":1},"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/2607.24875/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":"2026-07-29T00:24:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TXEHYBaziijl7IaANYCINusK69lmIHxKPv4ThUpHgIznDpuzCNHhaaXv7l/WNE3NQB5QwN7JmNYFLia0xSazBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:35:33.992387Z"},"content_sha256":"04c4a169514eef9d0ba10559abadd794532fb383b1af6ffe25551131f9c0e7a0","schema_version":"1.0","event_id":"sha256:04c4a169514eef9d0ba10559abadd794532fb383b1af6ffe25551131f9c0e7a0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2YAA7DSYRPQEOL64FFAVGBQQZK/bundle.json","state_url":"https://pith.science/pith/2YAA7DSYRPQEOL64FFAVGBQQZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2YAA7DSYRPQEOL64FFAVGBQQZK/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":"2026-08-03T18:35:33Z","links":{"resolver":"https://pith.science/pith/2YAA7DSYRPQEOL64FFAVGBQQZK","bundle":"https://pith.science/pith/2YAA7DSYRPQEOL64FFAVGBQQZK/bundle.json","state":"https://pith.science/pith/2YAA7DSYRPQEOL64FFAVGBQQZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2YAA7DSYRPQEOL64FFAVGBQQZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2YAA7DSYRPQEOL64FFAVGBQQZK","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":"c59ee7a27b635501829df9cb5984a12d8882cff19f3c8f331522e7f67e6f1f3c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T07:05:22Z","title_canon_sha256":"162f0230b4bf193f2da8d14c5b594d1076de58a01eeabe61b1c9f7f6ed23b1ab"},"schema_version":"1.0","source":{"id":"2607.24875","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24875","created_at":"2026-07-29T00:24:49Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24875v1","created_at":"2026-07-29T00:24:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24875","created_at":"2026-07-29T00:24:49Z"},{"alias_kind":"pith_short_12","alias_value":"2YAA7DSYRPQE","created_at":"2026-07-29T00:24:49Z"},{"alias_kind":"pith_short_16","alias_value":"2YAA7DSYRPQEOL64","created_at":"2026-07-29T00:24:49Z"},{"alias_kind":"pith_short_8","alias_value":"2YAA7DSY","created_at":"2026-07-29T00:24:49Z"}],"graph_snapshots":[{"event_id":"sha256:04c4a169514eef9d0ba10559abadd794532fb383b1af6ffe25551131f9c0e7a0","target":"graph","created_at":"2026-07-29T00:24:49Z","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/2607.24875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) can synthesize financial narratives but may express high confidence when evidence is sparse, stale, or contradictory. This failure is especially consequential in forecasting, where filings, news, prices, volume, and technical signals can disagree. We present FinAbstain, a research framework for uncertainty-calibrated multimodal retrieval-augmented generation (RAG) with selective prediction. A point-in-time retriever admits only information public at the forecast timestamp and supplies modality-specific evidence to fundamental, news, technical, risk, and verificatio","authors_text":"Dorothy Torres, Henan Huang, Wei Cheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T07:05:22Z","title":"FinAbstain: Uncertainty-Calibrated Multimodal RAG for Selective Financial Forecasting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24875","kind":"arxiv","version":1},"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":"sha256:08dbc40f2f926ac8427d7092008e1601c071167862d03a06ac4738a83dcce6ae","target":"record","created_at":"2026-07-29T00:24:49Z","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":"c59ee7a27b635501829df9cb5984a12d8882cff19f3c8f331522e7f67e6f1f3c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T07:05:22Z","title_canon_sha256":"162f0230b4bf193f2da8d14c5b594d1076de58a01eeabe61b1c9f7f6ed23b1ab"},"schema_version":"1.0","source":{"id":"2607.24875","kind":"arxiv","version":1}},"canonical_sha256":"d6000f8e588be0472fdc2941530610ca8e2b69409eda09129322434f62e36a7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6000f8e588be0472fdc2941530610ca8e2b69409eda09129322434f62e36a7e","first_computed_at":"2026-07-29T00:24:49.180764Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T00:24:49.180764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3+U2LLF6zvCesFfQOIWiBHTKIrRIR3/uUgRhaJFhNPiQNLLllvqW3IfSObJXBtWR8D/ZW9/rBSHGxucBVOpvDA==","signature_status":"signed_v1","signed_at":"2026-07-29T00:24:49.181654Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24875","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08dbc40f2f926ac8427d7092008e1601c071167862d03a06ac4738a83dcce6ae","sha256:04c4a169514eef9d0ba10559abadd794532fb383b1af6ffe25551131f9c0e7a0"],"state_sha256":"b098ad7b44ef6df3efbaf16351159ddcae1923a8ad76e00d98f256c25c6bad7c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QFTZ3moUXXDcG8YecrrnX+vxXmDH6W3zD7nC04AXadsbflGaYRR69eAhBKk5dgCGDGqvdEswxFQpkAL6N708Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:35:33.997266Z","bundle_sha256":"f50c0dbcde8ed7c990c5f47f7e95639f964c12a9d4bdeb4f150d812cc6e5f4a5"}}