{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7UFGASQTXG4E7AEQMVJZNVEMHS","short_pith_number":"pith:7UFGASQT","canonical_record":{"source":{"id":"2509.00909","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-31T15:40:43Z","cross_cats_sorted":[],"title_canon_sha256":"367e55da556c930df250aeacd2d134f25ff355ec508c7dfe16c388e97b0d3e44","abstract_canon_sha256":"d4528de523fbbccd178f3be7861ee36715ef4d18e88cbae5f71eda20b1dff8da"},"schema_version":"1.0"},"canonical_sha256":"fd0a604a13b9b84f8090655396d48c3cb8562bb776f01ba6ca2068d36dcc0b8d","source":{"kind":"arxiv","id":"2509.00909","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00909","created_at":"2026-06-08T01:03:47Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00909v2","created_at":"2026-06-08T01:03:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00909","created_at":"2026-06-08T01:03:47Z"},{"alias_kind":"pith_short_12","alias_value":"7UFGASQTXG4E","created_at":"2026-06-08T01:03:47Z"},{"alias_kind":"pith_short_16","alias_value":"7UFGASQTXG4E7AEQ","created_at":"2026-06-08T01:03:47Z"},{"alias_kind":"pith_short_8","alias_value":"7UFGASQT","created_at":"2026-06-08T01:03:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7UFGASQTXG4E7AEQMVJZNVEMHS","target":"record","payload":{"canonical_record":{"source":{"id":"2509.00909","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-31T15:40:43Z","cross_cats_sorted":[],"title_canon_sha256":"367e55da556c930df250aeacd2d134f25ff355ec508c7dfe16c388e97b0d3e44","abstract_canon_sha256":"d4528de523fbbccd178f3be7861ee36715ef4d18e88cbae5f71eda20b1dff8da"},"schema_version":"1.0"},"canonical_sha256":"fd0a604a13b9b84f8090655396d48c3cb8562bb776f01ba6ca2068d36dcc0b8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:03:47.843838Z","signature_b64":"6AdkTEdHCmVlDUxWNmzS0uUgrNl3sY2KC3IqGbMfMlNMIqqZ/2r0EmjFFnp6weKn5Q6bZMya/LwwTTJCxB42Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd0a604a13b9b84f8090655396d48c3cb8562bb776f01ba6ca2068d36dcc0b8d","last_reissued_at":"2026-06-08T01:03:47.842781Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:03:47.842781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.00909","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":"2026-06-08T01:03:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PIWsjYz/Qo7a8A87X/2mEymzQ+fStBgzXIFwuDptYuYC0kccZ4p5DLK+WACSJ36qF5QtXuUfpyx/jgRokuN0Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T19:40:44.146302Z"},"content_sha256":"e003f8b3bfceb3ece74d200cc6033e4b2ed5b1200dfc5bab45d05633c38d41a7","schema_version":"1.0","event_id":"sha256:e003f8b3bfceb3ece74d200cc6033e4b2ed5b1200dfc5bab45d05633c38d41a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7UFGASQTXG4E7AEQMVJZNVEMHS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HiPS: Hierarchical PDF Segmentation of Doctrinal Legal Books","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Harikrishnan Changaramkulath, Ivan Habernal, Sabine Wehnert","submitted_at":"2025-08-31T15:40:43Z","abstract_excerpt":"PDF parsers have recently improved on page-level layout understanding. However, recovering a document-global section hierarchy with reliable boundaries remains brittle for deeply structured books: many systems expose only page-local heading roles, assume shallow depth, or rely on high-quality PDF tags or Table of Contents (TOC) metadata, and public gold-standard data for deep book hierarchies is scarce. We present HiPS for hierarchical PDF segmentation of doctrinal legal books and make two main contributions. First, we release a gold-standard benchmark of 49 open-access law books with 9,812 ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00909","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/2509.00909/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":"2026-06-08T01:03:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L8Ab+l+cWJbF9vPqta1i60j4RsjiCNC7yfv+6hERkJRxeWryR28XDOjMvi+EcJsgf12Oa22mcfNtNbPzDXkrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T19:40:44.147150Z"},"content_sha256":"f264ead21142d45fbddf996aed96c6bdb5a37bc8285d603b09f8856b4de0a5c5","schema_version":"1.0","event_id":"sha256:f264ead21142d45fbddf996aed96c6bdb5a37bc8285d603b09f8856b4de0a5c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7UFGASQTXG4E7AEQMVJZNVEMHS/bundle.json","state_url":"https://pith.science/pith/7UFGASQTXG4E7AEQMVJZNVEMHS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7UFGASQTXG4E7AEQMVJZNVEMHS/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":"2026-06-08T19:40:44Z","links":{"resolver":"https://pith.science/pith/7UFGASQTXG4E7AEQMVJZNVEMHS","bundle":"https://pith.science/pith/7UFGASQTXG4E7AEQMVJZNVEMHS/bundle.json","state":"https://pith.science/pith/7UFGASQTXG4E7AEQMVJZNVEMHS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7UFGASQTXG4E7AEQMVJZNVEMHS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7UFGASQTXG4E7AEQMVJZNVEMHS","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":"d4528de523fbbccd178f3be7861ee36715ef4d18e88cbae5f71eda20b1dff8da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-31T15:40:43Z","title_canon_sha256":"367e55da556c930df250aeacd2d134f25ff355ec508c7dfe16c388e97b0d3e44"},"schema_version":"1.0","source":{"id":"2509.00909","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00909","created_at":"2026-06-08T01:03:47Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00909v2","created_at":"2026-06-08T01:03:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00909","created_at":"2026-06-08T01:03:47Z"},{"alias_kind":"pith_short_12","alias_value":"7UFGASQTXG4E","created_at":"2026-06-08T01:03:47Z"},{"alias_kind":"pith_short_16","alias_value":"7UFGASQTXG4E7AEQ","created_at":"2026-06-08T01:03:47Z"},{"alias_kind":"pith_short_8","alias_value":"7UFGASQT","created_at":"2026-06-08T01:03:47Z"}],"graph_snapshots":[{"event_id":"sha256:f264ead21142d45fbddf996aed96c6bdb5a37bc8285d603b09f8856b4de0a5c5","target":"graph","created_at":"2026-06-08T01:03:47Z","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/2509.00909/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"PDF parsers have recently improved on page-level layout understanding. However, recovering a document-global section hierarchy with reliable boundaries remains brittle for deeply structured books: many systems expose only page-local heading roles, assume shallow depth, or rely on high-quality PDF tags or Table of Contents (TOC) metadata, and public gold-standard data for deep book hierarchies is scarce. We present HiPS for hierarchical PDF segmentation of doctrinal legal books and make two main contributions. First, we release a gold-standard benchmark of 49 open-access law books with 9,812 ma","authors_text":"Harikrishnan Changaramkulath, Ivan Habernal, Sabine Wehnert","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-31T15:40:43Z","title":"HiPS: Hierarchical PDF Segmentation of Doctrinal Legal Books"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00909","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:e003f8b3bfceb3ece74d200cc6033e4b2ed5b1200dfc5bab45d05633c38d41a7","target":"record","created_at":"2026-06-08T01:03:47Z","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":"d4528de523fbbccd178f3be7861ee36715ef4d18e88cbae5f71eda20b1dff8da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-31T15:40:43Z","title_canon_sha256":"367e55da556c930df250aeacd2d134f25ff355ec508c7dfe16c388e97b0d3e44"},"schema_version":"1.0","source":{"id":"2509.00909","kind":"arxiv","version":2}},"canonical_sha256":"fd0a604a13b9b84f8090655396d48c3cb8562bb776f01ba6ca2068d36dcc0b8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd0a604a13b9b84f8090655396d48c3cb8562bb776f01ba6ca2068d36dcc0b8d","first_computed_at":"2026-06-08T01:03:47.842781Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:03:47.842781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6AdkTEdHCmVlDUxWNmzS0uUgrNl3sY2KC3IqGbMfMlNMIqqZ/2r0EmjFFnp6weKn5Q6bZMya/LwwTTJCxB42Bg==","signature_status":"signed_v1","signed_at":"2026-06-08T01:03:47.843838Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00909","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e003f8b3bfceb3ece74d200cc6033e4b2ed5b1200dfc5bab45d05633c38d41a7","sha256:f264ead21142d45fbddf996aed96c6bdb5a37bc8285d603b09f8856b4de0a5c5"],"state_sha256":"fc65249f6558138ab39f0bcd62724607f36718cadde474209cd05be4d62f2f4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pIGylXDHt0a+35AxvtCpYwxImsqW/bZSUUzpJ3C/Ta5Nl+NiJtcFdN8oUkQ075KqExxWlD7zhJLKNqPtZJMlBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T19:40:44.152180Z","bundle_sha256":"28b69b819bf22b39a3b3f84b9b5c257dce685c17efbd346daa0f3f19f4cf86b5"}}