{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SAVN5UMCIGFM3LGZRMV4RLHBGS","short_pith_number":"pith:SAVN5UMC","canonical_record":{"source":{"id":"2608.12756","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T03:08:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0bf997ea2332a0c1228366ff80af22c8f5508e40e37055ce41894905ec5b462b","abstract_canon_sha256":"3878f0b47f7aa36e13b21d29db82d065b70fff4f46cedb534d0a537af06db2e0"},"schema_version":"1.0"},"canonical_sha256":"902aded182418acdacd98b2bc8ace1348af7206b69f7ce9a3687964d20948c5b","source":{"kind":"arxiv","id":"2608.12756","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12756","created_at":"2026-08-14T00:47:33Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12756v1","created_at":"2026-08-14T00:47:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12756","created_at":"2026-08-14T00:47:33Z"},{"alias_kind":"pith_short_12","alias_value":"SAVN5UMCIGFM","created_at":"2026-08-14T00:47:33Z"},{"alias_kind":"pith_short_16","alias_value":"SAVN5UMCIGFM3LGZ","created_at":"2026-08-14T00:47:33Z"},{"alias_kind":"pith_short_8","alias_value":"SAVN5UMC","created_at":"2026-08-14T00:47:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SAVN5UMCIGFM3LGZRMV4RLHBGS","target":"record","payload":{"canonical_record":{"source":{"id":"2608.12756","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T03:08:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0bf997ea2332a0c1228366ff80af22c8f5508e40e37055ce41894905ec5b462b","abstract_canon_sha256":"3878f0b47f7aa36e13b21d29db82d065b70fff4f46cedb534d0a537af06db2e0"},"schema_version":"1.0"},"canonical_sha256":"902aded182418acdacd98b2bc8ace1348af7206b69f7ce9a3687964d20948c5b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:47:33.038599Z","signature_b64":"EWdCA5cO9uOff+k8K0dzsde7VEw4EL9q2eLZK/8QeQWHdZaXNYSdKEl2UmrSyX3IvJQEnM+Bj3tDVRWWSHRuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"902aded182418acdacd98b2bc8ace1348af7206b69f7ce9a3687964d20948c5b","last_reissued_at":"2026-08-14T00:47:33.032353Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:47:33.032353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.12756","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":"2026-08-14T00:47:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FIgGT32mP02oZtA1OoCczQTPakjU/dzQEMLyKHNas+nkUC5Eb037GUJD6r7rXvfvv38yHtFDnUW5AsLPLIk+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T06:58:57.721944Z"},"content_sha256":"1f6c9de36468ad3898f46ca6c1fdeb178dade8209b0188ffdd4aec199d8d760a","schema_version":"1.0","event_id":"sha256:1f6c9de36468ad3898f46ca6c1fdeb178dade8209b0188ffdd4aec199d8d760a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SAVN5UMCIGFM3LGZRMV4RLHBGS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ReconSpan: Reconstruction-Guided Adaptive Latent Tokenization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Lixing Li","submitted_at":"2026-08-13T03:08:40Z","abstract_excerpt":"Adaptive latent tokenization maps a fine-grained input to a shorter sequence of continuous representations associated with input-dependent spans. We introduce ReconSpan, which divides text into chunks that a backward decoder can reconstruct from a single contextual prefix code and retains one such code as the latent token for each chunk. The reconstruction criterion is applied when chunks are formed, allowing one trained autoencoder to produce average chunk lengths from 6.5 to 12.2. At matched average length, reconstruction-guided boundaries preserve more text than random boundaries. Readers o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12756","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/2608.12756/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":"2026-08-14T00:47:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W/J/M37/xiuwqQF/S9RNoUELLak3EOAV+qmTnLyYnsTsud/JQmydc3pMS/NaCRWdBbACyUVeua7d9iKUEbVfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T06:58:57.722461Z"},"content_sha256":"5f73176acb63fecd6d6ede8e60f5ae04c0f03c45960a8a984f6e21969e59959e","schema_version":"1.0","event_id":"sha256:5f73176acb63fecd6d6ede8e60f5ae04c0f03c45960a8a984f6e21969e59959e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SAVN5UMCIGFM3LGZRMV4RLHBGS/bundle.json","state_url":"https://pith.science/pith/SAVN5UMCIGFM3LGZRMV4RLHBGS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SAVN5UMCIGFM3LGZRMV4RLHBGS/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":"2026-08-21T06:58:57Z","links":{"resolver":"https://pith.science/pith/SAVN5UMCIGFM3LGZRMV4RLHBGS","bundle":"https://pith.science/pith/SAVN5UMCIGFM3LGZRMV4RLHBGS/bundle.json","state":"https://pith.science/pith/SAVN5UMCIGFM3LGZRMV4RLHBGS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SAVN5UMCIGFM3LGZRMV4RLHBGS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SAVN5UMCIGFM3LGZRMV4RLHBGS","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":"3878f0b47f7aa36e13b21d29db82d065b70fff4f46cedb534d0a537af06db2e0","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T03:08:40Z","title_canon_sha256":"0bf997ea2332a0c1228366ff80af22c8f5508e40e37055ce41894905ec5b462b"},"schema_version":"1.0","source":{"id":"2608.12756","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12756","created_at":"2026-08-14T00:47:33Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12756v1","created_at":"2026-08-14T00:47:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12756","created_at":"2026-08-14T00:47:33Z"},{"alias_kind":"pith_short_12","alias_value":"SAVN5UMCIGFM","created_at":"2026-08-14T00:47:33Z"},{"alias_kind":"pith_short_16","alias_value":"SAVN5UMCIGFM3LGZ","created_at":"2026-08-14T00:47:33Z"},{"alias_kind":"pith_short_8","alias_value":"SAVN5UMC","created_at":"2026-08-14T00:47:33Z"}],"graph_snapshots":[{"event_id":"sha256:5f73176acb63fecd6d6ede8e60f5ae04c0f03c45960a8a984f6e21969e59959e","target":"graph","created_at":"2026-08-14T00:47:33Z","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/2608.12756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adaptive latent tokenization maps a fine-grained input to a shorter sequence of continuous representations associated with input-dependent spans. We introduce ReconSpan, which divides text into chunks that a backward decoder can reconstruct from a single contextual prefix code and retains one such code as the latent token for each chunk. The reconstruction criterion is applied when chunks are formed, allowing one trained autoencoder to produce average chunk lengths from 6.5 to 12.2. At matched average length, reconstruction-guided boundaries preserve more text than random boundaries. Readers o","authors_text":"Lixing Li","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T03:08:40Z","title":"ReconSpan: Reconstruction-Guided Adaptive Latent Tokenization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12756","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":"sha256:1f6c9de36468ad3898f46ca6c1fdeb178dade8209b0188ffdd4aec199d8d760a","target":"record","created_at":"2026-08-14T00:47:33Z","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":"3878f0b47f7aa36e13b21d29db82d065b70fff4f46cedb534d0a537af06db2e0","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T03:08:40Z","title_canon_sha256":"0bf997ea2332a0c1228366ff80af22c8f5508e40e37055ce41894905ec5b462b"},"schema_version":"1.0","source":{"id":"2608.12756","kind":"arxiv","version":1}},"canonical_sha256":"902aded182418acdacd98b2bc8ace1348af7206b69f7ce9a3687964d20948c5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"902aded182418acdacd98b2bc8ace1348af7206b69f7ce9a3687964d20948c5b","first_computed_at":"2026-08-14T00:47:33.032353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T00:47:33.032353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EWdCA5cO9uOff+k8K0dzsde7VEw4EL9q2eLZK/8QeQWHdZaXNYSdKEl2UmrSyX3IvJQEnM+Bj3tDVRWWSHRuDQ==","signature_status":"signed_v1","signed_at":"2026-08-14T00:47:33.038599Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.12756","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f6c9de36468ad3898f46ca6c1fdeb178dade8209b0188ffdd4aec199d8d760a","sha256:5f73176acb63fecd6d6ede8e60f5ae04c0f03c45960a8a984f6e21969e59959e"],"state_sha256":"7b43f34a82cb113cf00d37586ff5f9e4e3e410e1dc82f4b76dd76bbc24a5d196"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZdS7ut3bDGzxlZnL67LQlVlE8AkEN4xw/NKk0HomyXzwYIOHVN2iZx+4xbjNoasqljLIFgT3geoMeWZhd7giAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T06:58:57.728647Z","bundle_sha256":"1d101104efca0f356636db8a74157d751f3b3994759ffd3c5d6b47f6695812ec"}}