{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5A4YLTUMSN4H3QAQ3WOWFSXMFC","short_pith_number":"pith:5A4YLTUM","canonical_record":{"source":{"id":"2603.29123","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-31T01:20:03Z","cross_cats_sorted":[],"title_canon_sha256":"9c0958d1adf10219f93675f73d40099a3445b9faed66fc12ca3241275b67eb90","abstract_canon_sha256":"a7c80835ea209eea5bf336472150761b60486fb1f532a9bd93f3f5e6e699643c"},"schema_version":"1.0"},"canonical_sha256":"e83985ce8c93787dc010dd9d62caec28a04c8e050f5d6ac0a213cb00316c2531","source":{"kind":"arxiv","id":"2603.29123","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.29123","created_at":"2026-05-26T02:04:09Z"},{"alias_kind":"arxiv_version","alias_value":"2603.29123v2","created_at":"2026-05-26T02:04:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.29123","created_at":"2026-05-26T02:04:09Z"},{"alias_kind":"pith_short_12","alias_value":"5A4YLTUMSN4H","created_at":"2026-05-26T02:04:09Z"},{"alias_kind":"pith_short_16","alias_value":"5A4YLTUMSN4H3QAQ","created_at":"2026-05-26T02:04:09Z"},{"alias_kind":"pith_short_8","alias_value":"5A4YLTUM","created_at":"2026-05-26T02:04:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5A4YLTUMSN4H3QAQ3WOWFSXMFC","target":"record","payload":{"canonical_record":{"source":{"id":"2603.29123","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-31T01:20:03Z","cross_cats_sorted":[],"title_canon_sha256":"9c0958d1adf10219f93675f73d40099a3445b9faed66fc12ca3241275b67eb90","abstract_canon_sha256":"a7c80835ea209eea5bf336472150761b60486fb1f532a9bd93f3f5e6e699643c"},"schema_version":"1.0"},"canonical_sha256":"e83985ce8c93787dc010dd9d62caec28a04c8e050f5d6ac0a213cb00316c2531","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:09.744206Z","signature_b64":"E7+8F0PjFm0ImtWcFHNi5gmEECwkfO/DCZwP8Y0kBHpKq/uxbSc4CWU8umVKpfiZ4AZsAs8WoNjggIBytIsDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e83985ce8c93787dc010dd9d62caec28a04c8e050f5d6ac0a213cb00316c2531","last_reissued_at":"2026-05-26T02:04:09.743429Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:09.743429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.29123","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":"2026-05-26T02:04:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EyrAhRLQ8t9D8vbWRAF6XLej0QtwO/5XiSImUGhzBJ9eMUM2KNqBmgY27Z9Z1L7hvv/PkuSbNQkkYiW8/cFuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T01:29:29.231481Z"},"content_sha256":"cc5e58918d5a9330de2a357ae3925c2e07df27cbcf25d05e327fefd53308cd97","schema_version":"1.0","event_id":"sha256:cc5e58918d5a9330de2a357ae3925c2e07df27cbcf25d05e327fefd53308cd97"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5A4YLTUMSN4H3QAQ3WOWFSXMFC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Concepts, Not Tokens: Self-Supervised Semantic Alignment for Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Shani, Christine Zhang, Dan Jurafsky","submitted_at":"2026-03-31T01:20:03Z","abstract_excerpt":"The next-token prediction (NTP) objective trains language models to predict a single token at each step, even though many continuations can express the same meaning. For example, in the sentence ``this sticker can be placed here'', positioned, attached, or put are all plausible alternatives. While standard NTP training treats these alternatives as mutually exclusive targets, we explore a self-supervised framework that encourages models to predict concepts, approximated as sets of semantically equivalent tokens. Models trained with this concept supervision align better with human similarity jud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.29123","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/2603.29123/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":"2026-05-26T02:04:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5hCce+lQFJ1ZnTibuBkssuPzN3ZR1y9f0WGlQCRFZlNicy5nM4seBrZBqmJ4YB6kzyco5KP6XQw1CtoDPsahAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T01:29:29.232279Z"},"content_sha256":"2f3ddf9e982bbd8b1b49d96c1c0d6d5b2cb03d784297cecd3b5a9e86befd9ac3","schema_version":"1.0","event_id":"sha256:2f3ddf9e982bbd8b1b49d96c1c0d6d5b2cb03d784297cecd3b5a9e86befd9ac3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5A4YLTUMSN4H3QAQ3WOWFSXMFC/bundle.json","state_url":"https://pith.science/pith/5A4YLTUMSN4H3QAQ3WOWFSXMFC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5A4YLTUMSN4H3QAQ3WOWFSXMFC/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":"2026-05-30T01:29:29Z","links":{"resolver":"https://pith.science/pith/5A4YLTUMSN4H3QAQ3WOWFSXMFC","bundle":"https://pith.science/pith/5A4YLTUMSN4H3QAQ3WOWFSXMFC/bundle.json","state":"https://pith.science/pith/5A4YLTUMSN4H3QAQ3WOWFSXMFC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5A4YLTUMSN4H3QAQ3WOWFSXMFC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5A4YLTUMSN4H3QAQ3WOWFSXMFC","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":"a7c80835ea209eea5bf336472150761b60486fb1f532a9bd93f3f5e6e699643c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-31T01:20:03Z","title_canon_sha256":"9c0958d1adf10219f93675f73d40099a3445b9faed66fc12ca3241275b67eb90"},"schema_version":"1.0","source":{"id":"2603.29123","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.29123","created_at":"2026-05-26T02:04:09Z"},{"alias_kind":"arxiv_version","alias_value":"2603.29123v2","created_at":"2026-05-26T02:04:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.29123","created_at":"2026-05-26T02:04:09Z"},{"alias_kind":"pith_short_12","alias_value":"5A4YLTUMSN4H","created_at":"2026-05-26T02:04:09Z"},{"alias_kind":"pith_short_16","alias_value":"5A4YLTUMSN4H3QAQ","created_at":"2026-05-26T02:04:09Z"},{"alias_kind":"pith_short_8","alias_value":"5A4YLTUM","created_at":"2026-05-26T02:04:09Z"}],"graph_snapshots":[{"event_id":"sha256:2f3ddf9e982bbd8b1b49d96c1c0d6d5b2cb03d784297cecd3b5a9e86befd9ac3","target":"graph","created_at":"2026-05-26T02:04:09Z","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/2603.29123/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The next-token prediction (NTP) objective trains language models to predict a single token at each step, even though many continuations can express the same meaning. For example, in the sentence ``this sticker can be placed here'', positioned, attached, or put are all plausible alternatives. While standard NTP training treats these alternatives as mutually exclusive targets, we explore a self-supervised framework that encourages models to predict concepts, approximated as sets of semantically equivalent tokens. Models trained with this concept supervision align better with human similarity jud","authors_text":"Chen Shani, Christine Zhang, Dan Jurafsky","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-31T01:20:03Z","title":"Learning Concepts, Not Tokens: Self-Supervised Semantic Alignment for Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.29123","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:cc5e58918d5a9330de2a357ae3925c2e07df27cbcf25d05e327fefd53308cd97","target":"record","created_at":"2026-05-26T02:04:09Z","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":"a7c80835ea209eea5bf336472150761b60486fb1f532a9bd93f3f5e6e699643c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-31T01:20:03Z","title_canon_sha256":"9c0958d1adf10219f93675f73d40099a3445b9faed66fc12ca3241275b67eb90"},"schema_version":"1.0","source":{"id":"2603.29123","kind":"arxiv","version":2}},"canonical_sha256":"e83985ce8c93787dc010dd9d62caec28a04c8e050f5d6ac0a213cb00316c2531","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e83985ce8c93787dc010dd9d62caec28a04c8e050f5d6ac0a213cb00316c2531","first_computed_at":"2026-05-26T02:04:09.743429Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:09.743429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E7+8F0PjFm0ImtWcFHNi5gmEECwkfO/DCZwP8Y0kBHpKq/uxbSc4CWU8umVKpfiZ4AZsAs8WoNjggIBytIsDBg==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:09.744206Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.29123","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc5e58918d5a9330de2a357ae3925c2e07df27cbcf25d05e327fefd53308cd97","sha256:2f3ddf9e982bbd8b1b49d96c1c0d6d5b2cb03d784297cecd3b5a9e86befd9ac3"],"state_sha256":"7f9e6ac7b9d33fc27ec9fb86f57f9e8f6a8c708fb11bf0c3d804fab4026a9e46"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v/UnNmxyhawPVvpMhVYXchcvoK8Rz2dYBtX5oIHpZ3BeRw6vOV986owLbwLtjLNcEGXa7l41JRePJCVKcLeVAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T01:29:29.236181Z","bundle_sha256":"a757f7eff753aecf90bf55e3f0d05f75fdc322edb69d6a9c3dccaae7abc3856e"}}