{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VJU5GF6FXYP3LGDPMYVWU7FSCR","short_pith_number":"pith:VJU5GF6F","canonical_record":{"source":{"id":"2406.00793","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-06-02T16:20:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6caa78374f08c9aa0e4d39ec47c5bbed8bdab7ee5b42f1821ded9dfe79edc053","abstract_canon_sha256":"7908fcddc145e83efa5439cf7be6522fa7eee74abc0ed7ef6eed36c6f5562c65"},"schema_version":"1.0"},"canonical_sha256":"aa69d317c5be1fb5986f662b6a7cb214632e603947c1b76394ec7abcbab5aeb2","source":{"kind":"arxiv","id":"2406.00793","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00793","created_at":"2026-07-05T08:26:30Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00793v1","created_at":"2026-07-05T08:26:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00793","created_at":"2026-07-05T08:26:30Z"},{"alias_kind":"pith_short_12","alias_value":"VJU5GF6FXYP3","created_at":"2026-07-05T08:26:30Z"},{"alias_kind":"pith_short_16","alias_value":"VJU5GF6FXYP3LGDP","created_at":"2026-07-05T08:26:30Z"},{"alias_kind":"pith_short_8","alias_value":"VJU5GF6F","created_at":"2026-07-05T08:26:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VJU5GF6FXYP3LGDPMYVWU7FSCR","target":"record","payload":{"canonical_record":{"source":{"id":"2406.00793","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-06-02T16:20:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6caa78374f08c9aa0e4d39ec47c5bbed8bdab7ee5b42f1821ded9dfe79edc053","abstract_canon_sha256":"7908fcddc145e83efa5439cf7be6522fa7eee74abc0ed7ef6eed36c6f5562c65"},"schema_version":"1.0"},"canonical_sha256":"aa69d317c5be1fb5986f662b6a7cb214632e603947c1b76394ec7abcbab5aeb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:30.850788Z","signature_b64":"LoZkkPpjyCwRoeUwEcvlA06L/6+7FWJLn9NEnp02oJRVcTj6kuAHmrFsdxmJM2VagWDj5i9oSTcyhNl2YJ4UAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa69d317c5be1fb5986f662b6a7cb214632e603947c1b76394ec7abcbab5aeb2","last_reissued_at":"2026-07-05T08:26:30.850387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:30.850387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.00793","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":"2026-07-05T08:26:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PTxanhqDwE4uk3jTQLYjK4ruf4DSKWRHax61UmK4gZ+JBNMHaMm8A6fILHyCgoduHfAMwPK2aW9+jTuiImo+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:17:07.753437Z"},"content_sha256":"cad89af139d03ee6b549ea520264d12cbf57ae3378162046dd0cca0f31a407e5","schema_version":"1.0","event_id":"sha256:cad89af139d03ee6b549ea520264d12cbf57ae3378162046dd0cca0f31a407e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VJU5GF6FXYP3LGDPMYVWU7FSCR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chris Holmes, Fabian Falck, Ziyu Wang","submitted_at":"2024-06-02T16:20:30Z","abstract_excerpt":"In-context learning (ICL) has emerged as a particularly remarkable characteristic of Large Language Models (LLM): given a pretrained LLM and an observed dataset, LLMs can make predictions for new data points from the same distribution without fine-tuning. Numerous works have postulated ICL as approximately Bayesian inference, rendering this a natural hypothesis. In this work, we analyse this hypothesis from a new angle through the martingale property, a fundamental requirement of a Bayesian learning system for exchangeable data. We show that the martingale property is a necessary condition for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00793","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/2406.00793/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":"2026-07-05T08:26:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v+CbCxDOS9MfilcmW221hYhaWrsBId2LC+VG7/PJyWbsycVrtJsYczBXHmVYF/+sZ1d5qyp8HS6vfDnok0prDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:17:07.754314Z"},"content_sha256":"47fa7bc46597f10fb3a99a667b3f20cbbfd7e8c6b1eac5148af5d4989170b718","schema_version":"1.0","event_id":"sha256:47fa7bc46597f10fb3a99a667b3f20cbbfd7e8c6b1eac5148af5d4989170b718"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VJU5GF6FXYP3LGDPMYVWU7FSCR/bundle.json","state_url":"https://pith.science/pith/VJU5GF6FXYP3LGDPMYVWU7FSCR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VJU5GF6FXYP3LGDPMYVWU7FSCR/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":"2026-08-04T04:17:07Z","links":{"resolver":"https://pith.science/pith/VJU5GF6FXYP3LGDPMYVWU7FSCR","bundle":"https://pith.science/pith/VJU5GF6FXYP3LGDPMYVWU7FSCR/bundle.json","state":"https://pith.science/pith/VJU5GF6FXYP3LGDPMYVWU7FSCR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VJU5GF6FXYP3LGDPMYVWU7FSCR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VJU5GF6FXYP3LGDPMYVWU7FSCR","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":"7908fcddc145e83efa5439cf7be6522fa7eee74abc0ed7ef6eed36c6f5562c65","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-06-02T16:20:30Z","title_canon_sha256":"6caa78374f08c9aa0e4d39ec47c5bbed8bdab7ee5b42f1821ded9dfe79edc053"},"schema_version":"1.0","source":{"id":"2406.00793","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00793","created_at":"2026-07-05T08:26:30Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00793v1","created_at":"2026-07-05T08:26:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00793","created_at":"2026-07-05T08:26:30Z"},{"alias_kind":"pith_short_12","alias_value":"VJU5GF6FXYP3","created_at":"2026-07-05T08:26:30Z"},{"alias_kind":"pith_short_16","alias_value":"VJU5GF6FXYP3LGDP","created_at":"2026-07-05T08:26:30Z"},{"alias_kind":"pith_short_8","alias_value":"VJU5GF6F","created_at":"2026-07-05T08:26:30Z"}],"graph_snapshots":[{"event_id":"sha256:47fa7bc46597f10fb3a99a667b3f20cbbfd7e8c6b1eac5148af5d4989170b718","target":"graph","created_at":"2026-07-05T08:26:30Z","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/2406.00793/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In-context learning (ICL) has emerged as a particularly remarkable characteristic of Large Language Models (LLM): given a pretrained LLM and an observed dataset, LLMs can make predictions for new data points from the same distribution without fine-tuning. Numerous works have postulated ICL as approximately Bayesian inference, rendering this a natural hypothesis. In this work, we analyse this hypothesis from a new angle through the martingale property, a fundamental requirement of a Bayesian learning system for exchangeable data. We show that the martingale property is a necessary condition for","authors_text":"Chris Holmes, Fabian Falck, Ziyu Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-06-02T16:20:30Z","title":"Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00793","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:cad89af139d03ee6b549ea520264d12cbf57ae3378162046dd0cca0f31a407e5","target":"record","created_at":"2026-07-05T08:26:30Z","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":"7908fcddc145e83efa5439cf7be6522fa7eee74abc0ed7ef6eed36c6f5562c65","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-06-02T16:20:30Z","title_canon_sha256":"6caa78374f08c9aa0e4d39ec47c5bbed8bdab7ee5b42f1821ded9dfe79edc053"},"schema_version":"1.0","source":{"id":"2406.00793","kind":"arxiv","version":1}},"canonical_sha256":"aa69d317c5be1fb5986f662b6a7cb214632e603947c1b76394ec7abcbab5aeb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa69d317c5be1fb5986f662b6a7cb214632e603947c1b76394ec7abcbab5aeb2","first_computed_at":"2026-07-05T08:26:30.850387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:30.850387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LoZkkPpjyCwRoeUwEcvlA06L/6+7FWJLn9NEnp02oJRVcTj6kuAHmrFsdxmJM2VagWDj5i9oSTcyhNl2YJ4UAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:30.850788Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00793","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cad89af139d03ee6b549ea520264d12cbf57ae3378162046dd0cca0f31a407e5","sha256:47fa7bc46597f10fb3a99a667b3f20cbbfd7e8c6b1eac5148af5d4989170b718"],"state_sha256":"55a78e1972f41d61f3b9496f65e54f344c77cf0d763584e7c6aa2a34f80c2d4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tI51TOz3/6kbzKI9DTX67mVN7GegEUI9O2e5DzDDyElECBLOdNAAivK30lJY0UnTBydfjMdqtY/q92+fnT8JBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:17:07.818885Z","bundle_sha256":"1bc15b81bf560b850400ca4d8b927f2984995104fdc3c718b7b1c01292c8a2bf"}}