{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:M4PGT7E3S73QQ25VWXPNX3OE3O","short_pith_number":"pith:M4PGT7E3","canonical_record":{"source":{"id":"2506.01919","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T17:39:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2fae666385466dbd041c4cd874bd4c43113a3bca755a9c259a6d255d1facc0bb","abstract_canon_sha256":"b0a5491a08ef72c8d5c3dc16a48343a6fa4a4635050c104c0b66a95f185bd486"},"schema_version":"1.0"},"canonical_sha256":"671e69fc9b97f7086bb5b5dedbedc4dbb5adf8fad992907f9039c230f916991c","source":{"kind":"arxiv","id":"2506.01919","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01919","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01919v1","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01919","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"pith_short_12","alias_value":"M4PGT7E3S73Q","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"pith_short_16","alias_value":"M4PGT7E3S73QQ25V","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"pith_short_8","alias_value":"M4PGT7E3","created_at":"2026-07-05T11:14:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:M4PGT7E3S73QQ25VWXPNX3OE3O","target":"record","payload":{"canonical_record":{"source":{"id":"2506.01919","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T17:39:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2fae666385466dbd041c4cd874bd4c43113a3bca755a9c259a6d255d1facc0bb","abstract_canon_sha256":"b0a5491a08ef72c8d5c3dc16a48343a6fa4a4635050c104c0b66a95f185bd486"},"schema_version":"1.0"},"canonical_sha256":"671e69fc9b97f7086bb5b5dedbedc4dbb5adf8fad992907f9039c230f916991c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:21.401631Z","signature_b64":"qp5L7nX398Tjpfy860jYGDVEwFPOrW9HpyRqWMSCR26LLmmNR2kufWxDk8Q1B4Ejom/NaGcD4QHIwexbGE0aDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"671e69fc9b97f7086bb5b5dedbedc4dbb5adf8fad992907f9039c230f916991c","last_reissued_at":"2026-07-05T11:14:21.401173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:21.401173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.01919","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":"2026-07-05T11:14:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WlpUhqda4bKnI3riJxHXYcMLB2eJQlYLv0+IJ2E+0nQY50NXhPvKrtQ90THi9f+yPJfRFveInebjvONwMXLrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:24:18.927744Z"},"content_sha256":"623fa9ffe7ee8cae217a007847e98cea81443e3c054f6bd54e389f32b861992e","schema_version":"1.0","event_id":"sha256:623fa9ffe7ee8cae217a007847e98cea81443e3c054f6bd54e389f32b861992e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:M4PGT7E3S73QQ25VWXPNX3OE3O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenlu Ye, Chi Han, Tong Zhang, Yifan Hao","submitted_at":"2025-06-02T17:39:31Z","abstract_excerpt":"Transformer based models have shown remarkable capabilities in sequence learning across a wide range of tasks, often performing well on specific task by leveraging input-output examples. Despite their empirical success, a comprehensive theoretical understanding of this phenomenon remains limited. In this work, we investigate the layerwise behavior of Transformers to uncover the mechanisms underlying their multi-task generalization ability. Taking explorations on a typical sequence model, i.e, Hidden Markov Models, which are fundamental to many language tasks, we observe that: first, lower laye"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01919","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/2506.01919/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":"2026-07-05T11:14:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RE+QhJLZ7aj9aJH9sfjOxNRLNAqgKBZXo98K8meQPqZ3qO4zNPGQO6P3mHHe705ilxONLesRe/Viw9xFgn6SBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:24:18.928241Z"},"content_sha256":"54c93f870d02e90fd39a5e6bee244a7824b451aab06ac6f3c40a189518d3c55e","schema_version":"1.0","event_id":"sha256:54c93f870d02e90fd39a5e6bee244a7824b451aab06ac6f3c40a189518d3c55e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M4PGT7E3S73QQ25VWXPNX3OE3O/bundle.json","state_url":"https://pith.science/pith/M4PGT7E3S73QQ25VWXPNX3OE3O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M4PGT7E3S73QQ25VWXPNX3OE3O/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":"2026-08-23T18:24:18Z","links":{"resolver":"https://pith.science/pith/M4PGT7E3S73QQ25VWXPNX3OE3O","bundle":"https://pith.science/pith/M4PGT7E3S73QQ25VWXPNX3OE3O/bundle.json","state":"https://pith.science/pith/M4PGT7E3S73QQ25VWXPNX3OE3O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M4PGT7E3S73QQ25VWXPNX3OE3O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M4PGT7E3S73QQ25VWXPNX3OE3O","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":"b0a5491a08ef72c8d5c3dc16a48343a6fa4a4635050c104c0b66a95f185bd486","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T17:39:31Z","title_canon_sha256":"2fae666385466dbd041c4cd874bd4c43113a3bca755a9c259a6d255d1facc0bb"},"schema_version":"1.0","source":{"id":"2506.01919","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01919","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01919v1","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01919","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"pith_short_12","alias_value":"M4PGT7E3S73Q","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"pith_short_16","alias_value":"M4PGT7E3S73QQ25V","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"pith_short_8","alias_value":"M4PGT7E3","created_at":"2026-07-05T11:14:21Z"}],"graph_snapshots":[{"event_id":"sha256:54c93f870d02e90fd39a5e6bee244a7824b451aab06ac6f3c40a189518d3c55e","target":"graph","created_at":"2026-07-05T11:14:21Z","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/2506.01919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer based models have shown remarkable capabilities in sequence learning across a wide range of tasks, often performing well on specific task by leveraging input-output examples. Despite their empirical success, a comprehensive theoretical understanding of this phenomenon remains limited. In this work, we investigate the layerwise behavior of Transformers to uncover the mechanisms underlying their multi-task generalization ability. Taking explorations on a typical sequence model, i.e, Hidden Markov Models, which are fundamental to many language tasks, we observe that: first, lower laye","authors_text":"Chenlu Ye, Chi Han, Tong Zhang, Yifan Hao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T17:39:31Z","title":"Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01919","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":"sha256:623fa9ffe7ee8cae217a007847e98cea81443e3c054f6bd54e389f32b861992e","target":"record","created_at":"2026-07-05T11:14:21Z","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":"b0a5491a08ef72c8d5c3dc16a48343a6fa4a4635050c104c0b66a95f185bd486","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T17:39:31Z","title_canon_sha256":"2fae666385466dbd041c4cd874bd4c43113a3bca755a9c259a6d255d1facc0bb"},"schema_version":"1.0","source":{"id":"2506.01919","kind":"arxiv","version":1}},"canonical_sha256":"671e69fc9b97f7086bb5b5dedbedc4dbb5adf8fad992907f9039c230f916991c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"671e69fc9b97f7086bb5b5dedbedc4dbb5adf8fad992907f9039c230f916991c","first_computed_at":"2026-07-05T11:14:21.401173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:21.401173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qp5L7nX398Tjpfy860jYGDVEwFPOrW9HpyRqWMSCR26LLmmNR2kufWxDk8Q1B4Ejom/NaGcD4QHIwexbGE0aDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:21.401631Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01919","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:623fa9ffe7ee8cae217a007847e98cea81443e3c054f6bd54e389f32b861992e","sha256:54c93f870d02e90fd39a5e6bee244a7824b451aab06ac6f3c40a189518d3c55e"],"state_sha256":"bf5aa42617b4f259dbb03d193973d4c3dd5906944d7ea3aab4bdedb2db7e8cf4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AQrbcNGI/VTXWVydEEl3/KAPQcPRZ7NWDCKMJ+65ShILoQNvtM5eip7Z4BUVdwkEgeZP4Qf7zjZTZZNbPclWAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T18:24:18.932879Z","bundle_sha256":"6e5a3acfb3888269e06f000fb8ab206da538744e8c71da12104eb813a4030e0f"}}