{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:24ROSZEVGYIALSX26NHCZHFVJF","short_pith_number":"pith:24ROSZEV","canonical_record":{"source":{"id":"2307.01784","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-04T15:44:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8fd925dcd703c1761eea535b46824caf93620334e022ec5997b7d6f8ffe64b5a","abstract_canon_sha256":"2c9af4d75e8b1e179f6f0fc356805da86e6adcd792bf289e69ecd9ca3c60e75e"},"schema_version":"1.0"},"canonical_sha256":"d722e96495361005cafaf34e2c9cb549455bba98c64e8bbd4808d158d1ed6049","source":{"kind":"arxiv","id":"2307.01784","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.01784","created_at":"2026-07-05T06:28:01Z"},{"alias_kind":"arxiv_version","alias_value":"2307.01784v1","created_at":"2026-07-05T06:28:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01784","created_at":"2026-07-05T06:28:01Z"},{"alias_kind":"pith_short_12","alias_value":"24ROSZEVGYIA","created_at":"2026-07-05T06:28:01Z"},{"alias_kind":"pith_short_16","alias_value":"24ROSZEVGYIALSX2","created_at":"2026-07-05T06:28:01Z"},{"alias_kind":"pith_short_8","alias_value":"24ROSZEV","created_at":"2026-07-05T06:28:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:24ROSZEVGYIALSX26NHCZHFVJF","target":"record","payload":{"canonical_record":{"source":{"id":"2307.01784","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-04T15:44:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8fd925dcd703c1761eea535b46824caf93620334e022ec5997b7d6f8ffe64b5a","abstract_canon_sha256":"2c9af4d75e8b1e179f6f0fc356805da86e6adcd792bf289e69ecd9ca3c60e75e"},"schema_version":"1.0"},"canonical_sha256":"d722e96495361005cafaf34e2c9cb549455bba98c64e8bbd4808d158d1ed6049","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:01.082736Z","signature_b64":"sXjUcqup/zFKilcpM67f5hJfnkS5Wp2OK662P3KdVwKG7UvOuqkSgxy4EdqpHdVJF4etRMML9Y7I5NByXGB6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d722e96495361005cafaf34e2c9cb549455bba98c64e8bbd4808d158d1ed6049","last_reissued_at":"2026-07-05T06:28:01.082287Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:01.082287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.01784","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":"2026-07-05T06:28:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8gXJ9sQTfrZHPTiIZwL8KbYVebqPXY7lJgwPUszKuGVNTMP/IGBX2TfZ3EnOpXcka5Igv7rbNvHuy0y0W6kuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:43:46.743514Z"},"content_sha256":"e86a8662791bbad8097841639985f272d88c07ef6dfd66533b69e0389c7ef4d8","schema_version":"1.0","event_id":"sha256:e86a8662791bbad8097841639985f272d88c07ef6dfd66533b69e0389c7ef4d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:24ROSZEVGYIALSX26NHCZHFVJF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Inner Sentiments of a Thought","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chris Gagne, Peter Dayan","submitted_at":"2023-07-04T15:44:37Z","abstract_excerpt":"Transformer-based large-scale language models (LLMs) are able to generate highly realistic text. They are duly able to express, and at least implicitly represent, a wide range of sentiments and color, from the obvious, such as valence and arousal to the subtle, such as determination and admiration. We provide a first exploration of these representations and how they can be used for understanding the inner sentimental workings of single sentences. We train predictors of the quantiles of the distributions of final sentiments of sentences from the hidden representations of an LLM applied to prefi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01784","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/2307.01784/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":"2026-07-05T06:28:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SfJqREELt6ovzu5ox1s3Cr0N3DenoDq5N5AU2sMnfShMLAS/0b58nHx6Vf5AgipV2pMbmPAQrMHSL/aNmVPoAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:43:46.744025Z"},"content_sha256":"1593b6c2cb1ec485db01f99faf3beea95329652ac7311635e9d210dcd11949bf","schema_version":"1.0","event_id":"sha256:1593b6c2cb1ec485db01f99faf3beea95329652ac7311635e9d210dcd11949bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/24ROSZEVGYIALSX26NHCZHFVJF/bundle.json","state_url":"https://pith.science/pith/24ROSZEVGYIALSX26NHCZHFVJF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/24ROSZEVGYIALSX26NHCZHFVJF/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":"2026-08-09T07:43:46Z","links":{"resolver":"https://pith.science/pith/24ROSZEVGYIALSX26NHCZHFVJF","bundle":"https://pith.science/pith/24ROSZEVGYIALSX26NHCZHFVJF/bundle.json","state":"https://pith.science/pith/24ROSZEVGYIALSX26NHCZHFVJF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/24ROSZEVGYIALSX26NHCZHFVJF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:24ROSZEVGYIALSX26NHCZHFVJF","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":"2c9af4d75e8b1e179f6f0fc356805da86e6adcd792bf289e69ecd9ca3c60e75e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-04T15:44:37Z","title_canon_sha256":"8fd925dcd703c1761eea535b46824caf93620334e022ec5997b7d6f8ffe64b5a"},"schema_version":"1.0","source":{"id":"2307.01784","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.01784","created_at":"2026-07-05T06:28:01Z"},{"alias_kind":"arxiv_version","alias_value":"2307.01784v1","created_at":"2026-07-05T06:28:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01784","created_at":"2026-07-05T06:28:01Z"},{"alias_kind":"pith_short_12","alias_value":"24ROSZEVGYIA","created_at":"2026-07-05T06:28:01Z"},{"alias_kind":"pith_short_16","alias_value":"24ROSZEVGYIALSX2","created_at":"2026-07-05T06:28:01Z"},{"alias_kind":"pith_short_8","alias_value":"24ROSZEV","created_at":"2026-07-05T06:28:01Z"}],"graph_snapshots":[{"event_id":"sha256:1593b6c2cb1ec485db01f99faf3beea95329652ac7311635e9d210dcd11949bf","target":"graph","created_at":"2026-07-05T06:28:01Z","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/2307.01784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer-based large-scale language models (LLMs) are able to generate highly realistic text. They are duly able to express, and at least implicitly represent, a wide range of sentiments and color, from the obvious, such as valence and arousal to the subtle, such as determination and admiration. We provide a first exploration of these representations and how they can be used for understanding the inner sentimental workings of single sentences. We train predictors of the quantiles of the distributions of final sentiments of sentences from the hidden representations of an LLM applied to prefi","authors_text":"Chris Gagne, Peter Dayan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-04T15:44:37Z","title":"The Inner Sentiments of a Thought"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01784","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:e86a8662791bbad8097841639985f272d88c07ef6dfd66533b69e0389c7ef4d8","target":"record","created_at":"2026-07-05T06:28:01Z","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":"2c9af4d75e8b1e179f6f0fc356805da86e6adcd792bf289e69ecd9ca3c60e75e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-04T15:44:37Z","title_canon_sha256":"8fd925dcd703c1761eea535b46824caf93620334e022ec5997b7d6f8ffe64b5a"},"schema_version":"1.0","source":{"id":"2307.01784","kind":"arxiv","version":1}},"canonical_sha256":"d722e96495361005cafaf34e2c9cb549455bba98c64e8bbd4808d158d1ed6049","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d722e96495361005cafaf34e2c9cb549455bba98c64e8bbd4808d158d1ed6049","first_computed_at":"2026-07-05T06:28:01.082287Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:28:01.082287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sXjUcqup/zFKilcpM67f5hJfnkS5Wp2OK662P3KdVwKG7UvOuqkSgxy4EdqpHdVJF4etRMML9Y7I5NByXGB6Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T06:28:01.082736Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.01784","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e86a8662791bbad8097841639985f272d88c07ef6dfd66533b69e0389c7ef4d8","sha256:1593b6c2cb1ec485db01f99faf3beea95329652ac7311635e9d210dcd11949bf"],"state_sha256":"3a5361d08903f21a23c437d17124805b8abb5c0c616e4873eecd77a6c9fe0e99"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FWWztvvRxBmiMaJQ+LqHCC37HZ2+bCQfUwz4bu6z3Iv37lNCro0e7v1SB74/yGdAcMEN1ZGBBBvX+sWvzWpbDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:43:46.749357Z","bundle_sha256":"97823cdca8e1b8f886e9c1d7880921581db8eb12f5ee4cd7acc3deeb478e60e5"}}