{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OCBM3VPQHWNBJ3DLKNX2OH7DBV","short_pith_number":"pith:OCBM3VPQ","canonical_record":{"source":{"id":"2307.01189","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-03T17:53:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d565cb4519e50d25e2912241e19554541a6c44c7548e3be5a4dfd3653ad8ce65","abstract_canon_sha256":"e2ecaf5fe4aa14a73b07a9bc84cfbed74f7543d3e9d8134c78b29670c125ebec"},"schema_version":"1.0"},"canonical_sha256":"7082cdd5f03d9a14ec6b536fa71fe30d5ebb665b7dec119e5aa0a06699fff37f","source":{"kind":"arxiv","id":"2307.01189","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.01189","created_at":"2026-07-05T07:43:00Z"},{"alias_kind":"arxiv_version","alias_value":"2307.01189v2","created_at":"2026-07-05T07:43:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01189","created_at":"2026-07-05T07:43:00Z"},{"alias_kind":"pith_short_12","alias_value":"OCBM3VPQHWNB","created_at":"2026-07-05T07:43:00Z"},{"alias_kind":"pith_short_16","alias_value":"OCBM3VPQHWNBJ3DL","created_at":"2026-07-05T07:43:00Z"},{"alias_kind":"pith_short_8","alias_value":"OCBM3VPQ","created_at":"2026-07-05T07:43:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OCBM3VPQHWNBJ3DLKNX2OH7DBV","target":"record","payload":{"canonical_record":{"source":{"id":"2307.01189","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-03T17:53:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d565cb4519e50d25e2912241e19554541a6c44c7548e3be5a4dfd3653ad8ce65","abstract_canon_sha256":"e2ecaf5fe4aa14a73b07a9bc84cfbed74f7543d3e9d8134c78b29670c125ebec"},"schema_version":"1.0"},"canonical_sha256":"7082cdd5f03d9a14ec6b536fa71fe30d5ebb665b7dec119e5aa0a06699fff37f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:00.483871Z","signature_b64":"Ba6KqKRLyUMc/aVjQ+JFgiy9T04F8nWkWFFZZUA3YWLD33XLbNEOFFleFJs92y/zKS7aNjH1hEf8IaW5ek7sAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7082cdd5f03d9a14ec6b536fa71fe30d5ebb665b7dec119e5aa0a06699fff37f","last_reissued_at":"2026-07-05T07:43:00.483399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:00.483399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.01189","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":"2026-07-05T07:43:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cMIPZQCltJ2yIBdosKrdSwLMuC4jr7uJFP3WywGRFkYN1Bzd61ND/+ptIpvk14ueizwxahQNwfl3hJYDQCwnDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:12:17.482671Z"},"content_sha256":"4853d619b6fc2eaf062cbfef1163b1c19776528f82c651f713647020e3d8dce9","schema_version":"1.0","event_id":"sha256:4853d619b6fc2eaf062cbfef1163b1c19776528f82c651f713647020e3d8dce9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OCBM3VPQHWNBJ3DLKNX2OH7DBV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Trainable Transformer in Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhishek Panigrahi, Mengzhou Xia, Sadhika Malladi, Sanjeev Arora","submitted_at":"2023-07-03T17:53:39Z","abstract_excerpt":"Recent works attribute the capability of in-context learning (ICL) in large pre-trained language models to implicitly simulating and fine-tuning an internal model (e.g., linear or 2-layer MLP) during inference. However, such constructions require large memory overhead, which makes simulation of more sophisticated internal models intractable. In this work, we propose an efficient construction, Transformer in Transformer (in short, TinT), that allows a transformer to simulate and fine-tune complex models internally during inference (e.g., pre-trained language models). In particular, we introduce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01189","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/2307.01189/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":"2026-07-05T07:43:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xFOmTUm8wtWaD4uWgvyIwqDFcmACHJKnm2+Hqy1hcp+/CpmWwzmrh1aZwt025ywsJGbw878nqFQqdxAm/wnqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:12:17.483193Z"},"content_sha256":"e5d4aedbe7a4990c927bc14899ec21fe3f43166fe338e455d5553febd8b4626d","schema_version":"1.0","event_id":"sha256:e5d4aedbe7a4990c927bc14899ec21fe3f43166fe338e455d5553febd8b4626d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OCBM3VPQHWNBJ3DLKNX2OH7DBV/bundle.json","state_url":"https://pith.science/pith/OCBM3VPQHWNBJ3DLKNX2OH7DBV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OCBM3VPQHWNBJ3DLKNX2OH7DBV/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":"2026-08-19T00:12:17Z","links":{"resolver":"https://pith.science/pith/OCBM3VPQHWNBJ3DLKNX2OH7DBV","bundle":"https://pith.science/pith/OCBM3VPQHWNBJ3DLKNX2OH7DBV/bundle.json","state":"https://pith.science/pith/OCBM3VPQHWNBJ3DLKNX2OH7DBV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OCBM3VPQHWNBJ3DLKNX2OH7DBV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OCBM3VPQHWNBJ3DLKNX2OH7DBV","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":"e2ecaf5fe4aa14a73b07a9bc84cfbed74f7543d3e9d8134c78b29670c125ebec","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-03T17:53:39Z","title_canon_sha256":"d565cb4519e50d25e2912241e19554541a6c44c7548e3be5a4dfd3653ad8ce65"},"schema_version":"1.0","source":{"id":"2307.01189","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.01189","created_at":"2026-07-05T07:43:00Z"},{"alias_kind":"arxiv_version","alias_value":"2307.01189v2","created_at":"2026-07-05T07:43:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01189","created_at":"2026-07-05T07:43:00Z"},{"alias_kind":"pith_short_12","alias_value":"OCBM3VPQHWNB","created_at":"2026-07-05T07:43:00Z"},{"alias_kind":"pith_short_16","alias_value":"OCBM3VPQHWNBJ3DL","created_at":"2026-07-05T07:43:00Z"},{"alias_kind":"pith_short_8","alias_value":"OCBM3VPQ","created_at":"2026-07-05T07:43:00Z"}],"graph_snapshots":[{"event_id":"sha256:e5d4aedbe7a4990c927bc14899ec21fe3f43166fe338e455d5553febd8b4626d","target":"graph","created_at":"2026-07-05T07:43:00Z","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/2307.01189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent works attribute the capability of in-context learning (ICL) in large pre-trained language models to implicitly simulating and fine-tuning an internal model (e.g., linear or 2-layer MLP) during inference. However, such constructions require large memory overhead, which makes simulation of more sophisticated internal models intractable. In this work, we propose an efficient construction, Transformer in Transformer (in short, TinT), that allows a transformer to simulate and fine-tune complex models internally during inference (e.g., pre-trained language models). In particular, we introduce","authors_text":"Abhishek Panigrahi, Mengzhou Xia, Sadhika Malladi, Sanjeev Arora","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-03T17:53:39Z","title":"Trainable Transformer in Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01189","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":"sha256:4853d619b6fc2eaf062cbfef1163b1c19776528f82c651f713647020e3d8dce9","target":"record","created_at":"2026-07-05T07:43:00Z","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":"e2ecaf5fe4aa14a73b07a9bc84cfbed74f7543d3e9d8134c78b29670c125ebec","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-03T17:53:39Z","title_canon_sha256":"d565cb4519e50d25e2912241e19554541a6c44c7548e3be5a4dfd3653ad8ce65"},"schema_version":"1.0","source":{"id":"2307.01189","kind":"arxiv","version":2}},"canonical_sha256":"7082cdd5f03d9a14ec6b536fa71fe30d5ebb665b7dec119e5aa0a06699fff37f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7082cdd5f03d9a14ec6b536fa71fe30d5ebb665b7dec119e5aa0a06699fff37f","first_computed_at":"2026-07-05T07:43:00.483399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:00.483399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ba6KqKRLyUMc/aVjQ+JFgiy9T04F8nWkWFFZZUA3YWLD33XLbNEOFFleFJs92y/zKS7aNjH1hEf8IaW5ek7sAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:00.483871Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.01189","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4853d619b6fc2eaf062cbfef1163b1c19776528f82c651f713647020e3d8dce9","sha256:e5d4aedbe7a4990c927bc14899ec21fe3f43166fe338e455d5553febd8b4626d"],"state_sha256":"df3f3fb3d32aaa51665cd2d84b37b0bc113b4d8198f4e485ffb79bad5695a41a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9+QmMI4i4kY5ue0jw68Hmmif2CIrNQkrUqw+NmTc4RAU67Mj4zMrrOlRna6vQNlEtjsNplHDWd7oQYBOn+h+Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T00:12:17.488790Z","bundle_sha256":"377c9579d312e4fe44cfa3f72f2db7fbd1448d320e255e2395d348ce2a69b886"}}